--- title: Messages url: https://platform.claude.com/docs/en/api/cli/beta/messages --- # Messages ## Create a Message `$ ant beta:messages create` **POST** `/v1/messages` Send a structured list of input messages with text and/or image content, and the model will generate the next message in the conversation. The Messages API can be used for either single queries or stateless multi-turn conversations. Learn more about the Messages API in our [user guide](https://platform.claude.com/docs/en/get-started?sdk_languages=cli) ### Parameters - `--max-tokens: number` The maximum number of tokens to generate before stopping. Note that our models may stop _before_ reaching this maximum. This parameter only specifies the absolute maximum number of tokens to generate. Set to `0` to populate the [prompt cache](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli#pre-warming-the-cache) without generating a response. Different models have different maximum values for this parameter. See [models](https://platform.claude.com/docs/en/about-claude/models/overview?sdk_languages=cli) for details. minimum: 0 - `--message: array of BetaMessageParam` Input messages. Our models are trained to operate on alternating `user` and `assistant` conversational turns. When creating a new `Message`, you specify the prior conversational turns with the `messages` parameter, and the model then generates the next `Message` in the conversation. Consecutive `user` or `assistant` turns in your request will be combined into a single turn. Each input message must be an object with a `role` and `content`. You can specify a single `user`-role message, or you can include multiple `user` and `assistant` messages. If the final message uses the `assistant` role, the response content will continue immediately from the content in that message. This can be used to constrain part of the model's response. This is called prefill. On models that don't support prefill, creating a message that ends with a partial `assistant` response returns a 400 error. See [Prefill not supported](https://platform.claude.com/docs/en/api/errors?sdk_languages=cli#prefill-not-supported). Example with a single `user` message: ```json [{"role": "user", "content": "Hello, Claude"}] ``` Example with multiple conversational turns: ```json [ {"role": "user", "content": "Hello there."}, {"role": "assistant", "content": "Hi, I'm Claude. How can I help you?"}, {"role": "user", "content": "Can you explain LLMs in plain English?"}, ] ``` Example with a partially-filled response from Claude, for models that support prefill: ```json [ {"role": "user", "content": "What's the Greek name for Sun? (A) Sol (B) Helios (C) Sun"}, {"role": "assistant", "content": "The best answer is ("}, ] ``` Each input message `content` may be either a single `string` or an array of content blocks, where each block has a specific `type`. Using a `string` for `content` is shorthand for an array of one content block of type `"text"`. The following input messages are equivalent: ```json {"role": "user", "content": "Hello, Claude"} ``` ```json {"role": "user", "content": [{"type": "text", "text": "Hello, Claude"}]} ``` See [input examples](https://platform.claude.com/docs/en/build-with-claude/working-with-messages?sdk_languages=cli). Note that if you want to include a [system prompt](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/claude-prompting-best-practices?sdk_languages=cli#give-claude-a-role), you can use the top-level `system` parameter — there is no `"system"` role for input messages in the Messages API. There is a limit of 100,000 messages in a single request. - `--model: "claude-haiku-5-5" or "claude-sonnet-5-5" or "claude-fable-5-1" or 17 more or string` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `--cache-control: optional object` Top-level cache control automatically applies a cache_control marker to the last cacheable block in the request. - `--compaction: optional object` Compaction configuration. When set on `POST /v1/messages`, the request is a compaction request: the conversation in `messages` is summarized and the response holds only the resulting `compaction` block (`stop_reason` `"compaction"`), which later requests send first in `messages` in place of the messages it summarizes. `POST /v1/messages/count_tokens` accepts this parameter and ignores it: the count it returns is for the conversation in `messages` as sent. Cannot be combined with `context_management`. - `--container: optional BetaContainerParams or string` Container identifier for reuse across requests. - `--context-management: optional object` Context management configuration. This allows you to control how Claude manages context across multiple requests, such as whether to clear function results or not. - `--diagnostics: optional object` Request-level diagnostics. Supply `previous_message_id` to have the response include `diagnostics.cache_miss_reason` explaining any prompt-cache divergence from that prior request. - `--fallback-credit-token: optional string or BetaFallbackCreditTokenParam` The `fallback_credit_token` from a prior refusal's `stop_details`. When a preceding request was refused and returned a `fallback_credit_token`, pass that code here on the retry to have the retry's cache-creation tokens for the prefix that was warm on the refused model billed at the cache-read rate. Must be redeemed by the same organization and workspace, with the same request body (optionally extended by one appended `assistant` message whose content is the partial text — with any trailing whitespace stripped from the final text block — and paired server-tool blocks streamed before the refusal; the appended-assistant form is not available for requests with `output_format` set or forced `tool_choice`), on an eligible fallback model, on the same platform, and within 5 minutes of the refusal; a mismatch is a 400. A token minted mid-server-tool-loop whose partial content was continuable may only be redeemed with the appended-assistant form — if an exact-body retry is rejected with a 400 saying the token must be redeemed by continuing the partial response, retry with the appended-assistant form instead. When the appended-assistant form is used on a model that otherwise disallows assistant-turn prefill, this token also authorizes that one prefill. - `--fallbacks: optional array of BetaFallbackParam or "default"` Opt-in server-side retry on one or more substitute models when the requested model declines for policy reasons. Tried in order: if the first entry also declines, the second is tried, and so on. Some models don't support fallbacks; on those models, a list of fallback models returns a 400 error. See [Server-side fallback](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback?sdk_languages=cli#server-side-fallback). The string "default" requests the requested model's server-defined default fallback configuration. On a model that doesn't support fallbacks, the request runs on the requested model alone, so a declined request stays declined. - `--inference-geo: optional string` Specifies the geographic region for inference processing. If not specified, the workspace's `default_inference_geo` is used. - `--mcp-server: optional array of BetaRequestMCPServerURLDefinition` MCP servers to be utilized in this request maxItems: 20 - `--metadata: optional object` An object describing metadata about the request. - `--output-config: optional object` Configuration options for the model's output, such as the output format. - `--output-format: optional object` Deprecated: Use `output_config.format` instead. See [structured outputs](https://platform.claude.com/docs/en/build-with-claude/structured-outputs?sdk_languages=cli) A schema to specify Claude's output format in responses. This parameter will be removed in a future release. - `--service-tier: optional "auto" or "standard_only"` Determines whether to use priority capacity (if available) or standard capacity for this request. Anthropic offers different levels of service for your API requests. See [service-tiers](https://platform.claude.com/docs/en/api/service-tiers?sdk_languages=cli) for details. - `--speed: optional "standard" or "fast"` The inference speed mode for this request. `"fast"` enables high output-tokens-per-second inference. Some models require the `fast-mode-2026-02-01` beta header for any `speed` value. See [fast mode](https://platform.claude.com/docs/en/build-with-claude/fast-mode?sdk_languages=cli) for which models. - `--stop-sequence: optional array of string` Custom text sequences that will cause the model to stop generating. Our models will normally stop when they have naturally completed their turn, which will result in a response `stop_reason` of `"end_turn"`. If you want the model to stop generating when it encounters custom strings of text, you can use the `stop_sequences` parameter. If the model encounters one of the custom sequences, the response `stop_reason` value will be `"stop_sequence"` and the response `stop_sequence` value will contain the matched stop sequence. - `--system: optional string or array of BetaTextBlockParam` System prompt. A system prompt is a way of providing context and instructions to Claude, such as specifying a particular goal or role. See our [guide to system prompts](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/claude-prompting-best-practices?sdk_languages=cli#give-claude-a-role). - `--thinking: optional BetaThinkingConfigEnabled or BetaThinkingConfigDisabled or BetaThinkingConfigBetweenTools or BetaThinkingConfigAdaptive` Configuration for Claude's thinking. With `{"type": "adaptive"}`, Claude decides when and how much to think. With `{"type": "enabled"}` (manual extended thinking), you set a `budget_tokens` of at least 1,024. Thinking tokens count toward your `max_tokens` limit. Which `type` values are accepted, and what happens when you omit `thinking`, depend on the model. See [thinking](https://platform.claude.com/docs/en/build-with-claude/thinking?sdk_languages=cli#configuring-thinking) for each model's behavior. - `--tool-choice: optional BetaToolChoiceAuto or BetaToolChoiceAny or BetaToolChoiceTool or BetaToolChoiceNone` How the model should use the provided tools. The model can use a specific tool, any available tool, decide by itself, or not use tools at all. - `--tool: optional array of BetaToolUnion` Definitions of tools that the model may use. If you include `tools` in your API request, the model may return `tool_use` content blocks that represent the model's use of those tools. You can then run those tools using the tool input generated by the model and then optionally return results back to the model using `tool_result` content blocks. There are two types of tools: **client tools** and **server tools**. The behavior described below applies to client tools. For [server tools](https://platform.claude.com/docs/en/agents-and-tools/tool-use/server-tools?sdk_languages=cli), see their individual documentation as each has its own behavior (e.g., the [web search tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/web-search-tool?sdk_languages=cli)). Each tool definition includes: * `name`: Name of the tool. * `description`: Optional, but strongly-recommended description of the tool. * `input_schema`: [JSON schema](https://json-schema.org/draft/2020-12) for the tool `input` shape that the model will produce in `tool_use` output content blocks. For example, if you defined `tools` as: ```json [ { "name": "get_stock_price", "description": "Get the current stock price for a given ticker symbol.", "input_schema": { "type": "object", "properties": { "ticker": { "type": "string", "description": "The stock ticker symbol, e.g. AAPL for Apple Inc." } }, "required": ["ticker"] } } ] ``` And then asked the model "What's the S&P 500 at today?", the model might produce `tool_use` content blocks in the response like this: ```json [ { "type": "tool_use", "id": "toolu_01D7FLrfh4GYq7yT1ULFeyMV", "name": "get_stock_price", "input": { "ticker": "^GSPC" } } ] ``` You might then run your `get_stock_price` tool with `{"ticker": "^GSPC"}` as an input, and return the following back to the model in a subsequent `user` message: ```json [ { "type": "tool_result", "tool_use_id": "toolu_01D7FLrfh4GYq7yT1ULFeyMV", "content": "259.75 USD" } ] ``` Tools can be used for workflows that include running client-side tools and functions, or more generally whenever you want the model to produce a particular JSON structure of output. See our [guide](https://platform.claude.com/docs/en/agents-and-tools/tool-use/overview?sdk_languages=cli) for more details. - `--beta: optional array of AnthropicBeta` (header parameter) Optional header to specify the beta version(s) you want to use. - `--user-profile-id: optional string` (header parameter) The user profile ID to attribute this request to. Use when acting on behalf of a party other than your organization. Requires the `user-profiles` beta header. - `--workspace-id: optional string` (header parameter) Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`). Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace. - `--temperature: optional number` **Deprecated**: Deprecated. Models released after Claude Opus 4.6 do not support setting temperature. A value of 1.0 will be accepted for backwards compatibility, all other values will be rejected with a 400 error. Amount of randomness injected into the response. Defaults to `1.0`. Ranges from `0.0` to `1.0`. Use `temperature` closer to `0.0` for analytical / multiple choice, and closer to `1.0` for creative and generative tasks. Note that even with `temperature` of `0.0`, the results will not be fully deterministic. minimum: 0, maximum: 1 - `--top-k: optional number` **Deprecated**: Deprecated. Models released after Claude Opus 4.6 do not accept top_k; any value will be rejected with a 400 error. Only sample from the top K options for each subsequent token. Used to remove "long tail" low probability responses. [Learn more technical details here](https://towardsdatascience.com/how-to-sample-from-language-models-682bceb97277). Recommended for advanced use cases only. minimum: 0 - `--top-p: optional number` **Deprecated**: Deprecated. Models released after Claude Opus 4.6 do not support setting top_p. A value >= 0.99 will be accepted for backwards compatibility, all other values will be rejected with a 400 error. Use nucleus sampling. In nucleus sampling, we compute the cumulative distribution over all the options for each subsequent token in decreasing probability order and cut it off once it reaches a particular probability specified by `top_p`. Recommended for advanced use cases only. minimum: 0, maximum: 1 ### Returns - `beta_message: object` - `type: "message"` Object type. For Messages, this is always `"message"`. - `id: string` Unique object identifier. The format and length of IDs may change over time. - `container: object` Information about the container used in this request. This will be non-null if a container tool (e.g. code execution) was used. - `id: string` Identifier for the container used in this request - `expires_at: string` The time at which the container will expire. format: date-time - `skills: array of BetaContainerSkill` Skills loaded in the container - `type: "anthropic" or "custom"` Type of skill - either 'anthropic' (built-in) or 'custom' (user-defined) - `"anthropic"` - `"custom"` - `skill_id: string` Skill ID minLength: 1, maxLength: 64 - `version: string` The resolved version: a skill version ID for custom skills. minLength: 1, maxLength: 64 - `content: array of BetaContentBlock` Content generated by the model. This is an array of content blocks, each of which has a `type` that determines its shape. Example: ```json [{"type": "text", "text": "Hi, I'm Claude."}] ``` If the request input `messages` ended with an `assistant` turn, then the response `content` will continue directly from that last turn. You can use this to constrain the model's output. For example, if the input `messages` were: ```json [ {"role": "user", "content": "What's the Greek name for Sun? (A) Sol (B) Helios (C) Sun"}, {"role": "assistant", "content": "The best answer is ("} ] ``` Then the response `content` might be: ```json [{"type": "text", "text": "B)"}] ``` - `beta_text_block: object` - `type: "text"` - `citations: array of BetaTextCitation` Citations supporting the text block. The type of citation returned will depend on the type of document being cited. Citing a PDF results in `page_location`, plain text results in `char_location`, and content document results in `content_block_location`. - `beta_citation_char_location: object` - `type: "char_location"` - `cited_text: string` - `document_index: number` minimum: 0 - `document_title: string` - `end_char_index: number` - `file_id: string` - `start_char_index: number` minimum: 0 - `beta_citation_page_location: object` - `type: "page_location"` - `cited_text: string` - `document_index: number` minimum: 0 - `document_title: string` - `end_page_number: number` - `file_id: string` - `start_page_number: number` minimum: 1 - `beta_citation_content_block_location: object` - `type: "content_block_location"` - `cited_text: string` The full text of the cited block range, concatenated. Always equals the contents of `content[start_block_index:end_block_index]` joined together. The text block is the minimal citable unit; this field is never a substring of a single block. Not counted toward output tokens, and not counted toward input tokens when sent back in subsequent turns. - `document_index: number` minimum: 0 - `document_title: string` - `end_block_index: number` Exclusive 0-based end index of the cited block range in the source's `content` array. Always greater than `start_block_index`; a single-block citation has `end_block_index = start_block_index + 1`. - `file_id: string` - `start_block_index: number` 0-based index of the first cited block in the source's `content` array. minimum: 0 - `beta_citations_web_search_result_location: object` - `type: "web_search_result_location"` - `cited_text: string` - `encrypted_index: string` - `title: string` maxLength: 512 - `url: string` - `beta_citation_search_result_location: object` - `type: "search_result_location"` - `cited_text: string` The full text of the cited block range, concatenated. Always equals the contents of `content[start_block_index:end_block_index]` joined together. The text block is the minimal citable unit; this field is never a substring of a single block. Not counted toward output tokens, and not counted toward input tokens when sent back in subsequent turns. - `end_block_index: number` Exclusive 0-based end index of the cited block range in the source's `content` array. Always greater than `start_block_index`; a single-block citation has `end_block_index = start_block_index + 1`. - `search_result_index: number` 0-based index of the cited search result among all `search_result` content blocks in the request, in the order they appear across messages and tool results. Counted separately from `document_index`; server-side web search results are not included in this count. minimum: 0 - `source: string` - `start_block_index: number` 0-based index of the first cited block in the source's `content` array. minimum: 0 - `title: string` - `text: string` - `beta_thinking_block: object` - `type: "thinking"` - `signature: string` A value used to verify that this thinking block was generated by Claude when it is passed back to the API. This is an opaque field and should not be interpreted or parsed. When passing thinking blocks back to the API (required when using tools with extended thinking), pass them back exactly as received, with this field intact. See [extended thinking](https://platform.claude.com/docs/en/build-with-claude/extended-thinking?sdk_languages=cli) for details. - `thinking: string` The text of Claude's thinking process for this block. - `beta_redacted_thinking_block: object` - `type: "redacted_thinking"` - `data: string` The contents of this redacted thinking block, returned when portions of the model's thinking were safety-redacted. This field is opaque and encrypted, with no readable content. Pass `redacted_thinking` blocks back to the API unchanged when continuing a multi-turn conversation. See [extended thinking](https://platform.claude.com/docs/en/build-with-claude/extended-thinking?sdk_languages=cli#redacted-thinking-blocks) for details. - `beta_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: map[unknown]` - `name: string` minLength: 1 - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` - `beta_direct_caller: object` Tool invocation directly from the model. - `type: "direct"` - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `type: "code_execution_20250825"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `beta_server_tool_caller_20260120: object` - `type: "code_execution_20260120"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `toolset_name: optional string` For a toolset member tool_use, the toolset family. minLength: 1, maxLength: 64, pattern: ^[a-zA-Z0-9_-]+$ - `beta_server_tool_use_block: object` - `type: "server_tool_use"` - `id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `input: map[unknown]` - `name: "advisor" or "web_search" or "web_fetch" or 5 more` - `"advisor"` - `"web_search"` - `"web_fetch"` - `"code_execution"` - `"bash_code_execution"` - `"text_editor_code_execution"` - `"tool_search_tool_regex"` - `"tool_search_tool_bm25"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` - `beta_direct_caller: object` Tool invocation directly from the model. - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `beta_server_tool_caller_20260120: object` - `beta_web_search_tool_result_block: object` - `type: "web_search_tool_result"` - `content: BetaWebSearchToolResultError or array of BetaWebSearchResultBlock` - `beta_web_search_tool_result_error: object` - `type: "web_search_tool_result_error"` - `error_code: "invalid_tool_input" or "unavailable" or "max_uses_exceeded" or 3 more` - `"invalid_tool_input"` - `"unavailable"` - `"max_uses_exceeded"` - `"too_many_requests"` - `"query_too_long"` - `"request_too_large"` - `union_member_1: array of BetaWebSearchResultBlock` - `type: "web_search_result"` - `encrypted_content: string` - `page_age: string` - `title: string` - `url: string` - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` - `beta_direct_caller: object` Tool invocation directly from the model. - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `beta_server_tool_caller_20260120: object` - `beta_web_fetch_tool_result_block: object` - `type: "web_fetch_tool_result"` - `content: BetaWebFetchToolResultErrorBlock or BetaWebFetchBlock` - `beta_web_fetch_tool_result_error_block: object` - `type: "web_fetch_tool_result_error"` - `error_code: "invalid_tool_input" or "url_too_long" or "url_not_allowed" or 7 more` - `"invalid_tool_input"` - `"url_too_long"` - `"url_not_allowed"` - `"url_not_in_prior_context"` - `"url_not_accessible"` - `"unsupported_content_type"` - `"too_many_requests"` - `"max_uses_exceeded"` - `"unavailable"` - `"content_too_large"` - `beta_web_fetch_block: object` - `type: "web_fetch_result"` - `content: object` - `type: "document"` - `citations: object` Citation configuration for the document - `enabled: boolean` - `source: BetaBase64PDFSource or BetaPlainTextSource` - `beta_base64_pdf_source: object` - `type: "base64"` - `data: string` format: byte - `media_type: "application/pdf"` - `beta_plain_text_source: object` - `type: "text"` - `data: string` - `media_type: "text/plain"` - `title: string` The title of the document - `retrieved_at: string` ISO 8601 timestamp when the content was retrieved - `url: string` Fetched content URL - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` - `beta_direct_caller: object` Tool invocation directly from the model. - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `beta_server_tool_caller_20260120: object` - `beta_advisor_tool_result_block: object` - `type: "advisor_tool_result"` - `content: BetaAdvisorToolResultError or BetaAdvisorResultBlock or BetaAdvisorRedactedResultBlock` - `beta_advisor_tool_result_error: object` - `type: "advisor_tool_result_error"` - `error_code: "max_uses_exceeded" or "prompt_too_long" or "too_many_requests" or 4 more` - `"max_uses_exceeded"` - `"prompt_too_long"` - `"too_many_requests"` - `"overloaded"` - `"unavailable"` - `"execution_time_exceeded"` - `"model_not_found"` - `beta_advisor_result_block: object` - `type: "advisor_result"` - `stop_reason: string` The advisor sub-inference's stop reason (same values as the top-level message `stop_reason`). `max_tokens` indicates the advisor's output was truncated at the tool's `max_tokens` value or the advisor model's policy cap. - `text: string` - `beta_advisor_redacted_result_block: object` - `type: "advisor_redacted_result"` - `encrypted_content: string` Opaque blob containing the advisor's output. Round-trip verbatim; do not inspect or modify. - `stop_reason: string` The advisor sub-inference's stop reason (same values as the top-level message `stop_reason`). - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `beta_code_execution_tool_result_block: object` - `type: "code_execution_tool_result"` - `content: BetaCodeExecutionToolResultError or BetaCodeExecutionResultBlock or BetaEncryptedCodeExecutionResultBlock` - `beta_code_execution_tool_result_error: object` - `type: "code_execution_tool_result_error"` - `error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or "execution_time_exceeded"` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `beta_code_execution_result_block: object` - `type: "code_execution_result"` - `content: array of BetaCodeExecutionOutputBlock` - `type: "code_execution_output"` - `file_id: string` - `return_code: number` - `stderr: string` - `stdout: string` - `beta_encrypted_code_execution_result_block: object` Code execution result with encrypted stdout for PFC + web_search results. - `type: "encrypted_code_execution_result"` - `content: array of BetaCodeExecutionOutputBlock` - `type: "code_execution_output"` - `file_id: string` - `encrypted_stdout: string` - `return_code: number` - `stderr: string` - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `beta_bash_code_execution_tool_result_block: object` - `type: "bash_code_execution_tool_result"` - `content: BetaBashCodeExecutionToolResultError or BetaBashCodeExecutionResultBlock` - `beta_bash_code_execution_tool_result_error: object` - `type: "bash_code_execution_tool_result_error"` - `error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or 2 more` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `"output_file_too_large"` - `beta_bash_code_execution_result_block: object` - `type: "bash_code_execution_result"` - `content: array of BetaBashCodeExecutionOutputBlock` - `type: "bash_code_execution_output"` - `file_id: string` - `return_code: number` - `stderr: string` - `stdout: string` - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `beta_text_editor_code_execution_tool_result_block: object` - `type: "text_editor_code_execution_tool_result"` - `content: BetaTextEditorCodeExecutionToolResultError or BetaTextEditorCodeExecutionViewResultBlock or BetaTextEditorCodeExecutionCreateResultBlock or BetaTextEditorCodeExecutionStrReplaceResultBlock` - `beta_text_editor_code_execution_tool_result_error: object` - `type: "text_editor_code_execution_tool_result_error"` - `error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or 2 more` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `"file_not_found"` - `error_message: string` - `beta_text_editor_code_execution_view_result_block: object` - `type: "text_editor_code_execution_view_result"` - `content: string` - `file_type: "text" or "image" or "pdf"` - `"text"` - `"image"` - `"pdf"` - `num_lines: number` - `start_line: number` - `total_lines: number` - `beta_text_editor_code_execution_create_result_block: object` - `type: "text_editor_code_execution_create_result"` - `is_file_update: boolean` - `beta_text_editor_code_execution_str_replace_result_block: object` - `type: "text_editor_code_execution_str_replace_result"` - `lines: array of string` - `new_lines: number` - `new_start: number` - `old_lines: number` - `old_start: number` - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `beta_tool_search_tool_result_block: object` - `type: "tool_search_tool_result"` - `content: BetaToolSearchToolResultError or BetaToolSearchToolSearchResultBlock` - `beta_tool_search_tool_result_error: object` - `type: "tool_search_tool_result_error"` - `error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or "execution_time_exceeded"` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `error_message: string` - `beta_tool_search_tool_search_result_block: object` - `type: "tool_search_tool_search_result"` - `tool_references: array of BetaToolReferenceBlock` - `type: "tool_reference"` - `tool_name: string` minLength: 1, maxLength: 256, pattern: ^[a-zA-Z0-9_-]{1,256}$ - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `beta_mcp_tool_use_block: object` - `type: "mcp_tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: map[unknown]` - `name: string` The name of the MCP tool - `server_name: string` The name of the MCP server - `beta_mcp_tool_result_block: object` - `type: "mcp_tool_result"` - `content: string or array of BetaTextBlock` - `union_member_0: string` - `beta_mcp_tool_result_block_content: array of BetaTextBlock` - `type: "text"` - `citations: array of BetaTextCitation` Citations supporting the text block. The type of citation returned will depend on the type of document being cited. Citing a PDF results in `page_location`, plain text results in `char_location`, and content document results in `content_block_location`. - `text: string` - `is_error: boolean` - `tool_use_id: string` pattern: ^[a-zA-Z0-9_-]+$ - `beta_container_upload_block: object` Response model for a file uploaded to the container. - `type: "container_upload"` - `file_id: string` - `beta_compaction_block: object` A compaction block returned when autocompact is triggered. When content is None, it indicates the compaction failed to produce a valid summary (e.g., malformed output from the model). Clients may round-trip compaction blocks with null content; the server treats them as no-ops. - `type: "compaction"` - `content: string` Summary of compacted content, or null if compaction failed - `encrypted_content: string` Opaque metadata from prior compaction, to be round-tripped verbatim - `signature: optional string` Signature over the summary, to be sent back with the block verbatim - `tool_changes: optional array of BetaResponseToolAdditionBlock or BetaResponseToolRemovalBlock` The tool changes of the compacted range: the `tool_addition` and `tool_removal` blocks that take the request's `tools` to the tool set in effect at the end of the range, or `[]` when the range changed no tool. Absent when the server did not compute them. Send the block back unchanged. - `beta_response_tool_addition_block: object` An entry of a `compaction` block's `tool_changes`: a tool the compacted range made available, as a reference to a `tools` entry or MCP toolset, or as the tool definition in effect at the end of the range, by value. Send it back unchanged. - `type: "tool_addition"` - `tool: BetaResponseToolChangeToolReference or BetaResponseToolChangeMCPToolReference or BetaResponseToolChangeMCPToolsetReference or BetaToolChangeToolDefinition` The tool made available: a reference to a `tools` entry or MCP toolset, or a `tool_definition` carrying the definition by value. - `beta_response_tool_change_tool_reference: object` Reference to a single tool, by the name the model uses to call it, as a `compaction` block's `tool_changes` entry reports it: a tool declared in `tools` or defined by an earlier `tool_addition` block. Send it back unchanged with the block. - `type: "tool_reference"` - `name: string` - `beta_response_tool_change_mcp_tool_reference: object` Reference to a single MCP tool, by its server and its name on that server, as a `compaction` block's `tool_changes` entry reports it. Send it back unchanged with the block. - `type: "mcp_tool_reference"` - `name: string` - `server_name: string` - `beta_response_tool_change_mcp_toolset_reference: object` Reference to every tool in the named MCP server's toolset, as a `compaction` block's `tool_changes` entry reports it. Send it back unchanged with the block. - `type: "mcp_toolset_reference"` - `server_name: string` - `beta_tool_change_tool_definition: object` A tool defined by value, as a `compaction` block's `tool_changes` entry reports it: `definition` is the tool's definition as it was sent, in the form of a `tools` entry, without `cache_control`. Send it back unchanged with the block. - `type: "tool_definition"` - `definition: BetaResponseTool or BetaToolBash20241022 or BetaToolBash20250124 or 25 more` - `beta_response_tool: object` A custom tool definition, as sent. - `type: optional "custom"` - `input_schema: object` [JSON schema](https://json-schema.org/draft/2020-12) for this tool's input. This defines the shape of the `input` that your tool accepts and that the model will produce. - `type: "object"` - `properties: optional map[unknown]` - `required: optional array of string` - `name: string` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. minLength: 1, maxLength: 128, pattern: ^[a-zA-Z0-9_-]{1,128}$ - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `description: optional string` Description of what this tool does. Tool descriptions should be as detailed as possible. The more information that the model has about what the tool is and how to use it, the better it will perform. You can use natural language descriptions to reinforce important aspects of the tool input JSON schema. - `eager_input_streaming: optional boolean` Enable eager input streaming for this tool. When true, tool input parameters will be streamed incrementally as they are generated, and types will be inferred on-the-fly rather than buffering the full JSON output. When false, streaming is disabled for this tool even if the fine-grained-tool-streaming beta is active. When null (default), uses the default behavior based on beta headers. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_bash_20241022: object` - `type: "bash_20241022"` - `name: "bash"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `"5m"` - `"1h"` - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_bash_20250124: object` - `type: "bash_20250124"` - `name: "bash"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_code_execution_tool_20250522: object` - `type: "code_execution_20250522"` - `name: "code_execution"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_code_execution_tool_20250825: object` - `type: "code_execution_20250825"` - `name: "code_execution"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_code_execution_tool_20260120: object` Code execution tool with REPL state persistence (daemon mode + gVisor checkpoint). - `type: "code_execution_20260120"` - `name: "code_execution"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_code_execution_tool_20260521: object` Code execution tool with REPL state persistence. - `type: "code_execution_20260521"` - `name: "code_execution"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_browser_toolset_20260801: object` The browser toolset: a single `tools[]` entry (carrying no `name`) that declares the browser tool family. The model is served the family's tool with any members disabled via `configs` removed from its schema. - `type: "browser_toolset_20260801"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `configs: optional object` Sparse per-member overrides, keyed by member name. Absent, null, and {} are equivalent; a member's defaults apply wherever its key is absent. - `type: optional object` `type`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `close_tab: optional object` `close_tab`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `double_click: optional object` `double_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `file_upload: optional object` `file_upload`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `find: optional object` `find`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `form_input: optional object` `form_input`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `get_page_text: optional object` `get_page_text`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `hold_key: optional object` `hold_key`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `hover: optional object` `hover`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `javascript_exec: optional object` `javascript_exec`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `key: optional object` `key`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_click: optional object` `left_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_click_drag: optional object` `left_click_drag`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_mouse_down: optional object` `left_mouse_down`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_mouse_up: optional object` `left_mouse_up`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `list_tabs: optional object` `list_tabs`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `middle_click: optional object` `middle_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `mouse_move: optional object` `mouse_move`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `navigate: optional object` `navigate`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `new_tab: optional object` `new_tab`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `read_console: optional object` `read_console`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `read_network: optional object` `read_network`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `read_page: optional object` `read_page`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `right_click: optional object` `right_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `screenshot: optional object` `screenshot`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `scroll: optional object` `scroll`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `scroll_to: optional object` `scroll_to`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `switch_tab: optional object` `switch_tab`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `triple_click: optional object` `triple_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `wait: optional object` `wait`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `zoom: optional object` `zoom`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `beta_tool_computer_use_20241022: object` - `type: "computer_20241022"` - `display_height_px: number` The height of the display in pixels. minimum: 1 - `display_width_px: number` The width of the display in pixels. minimum: 1 - `name: "computer"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `display_number: optional number` The X11 display number (e.g. 0, 1) for the display. minimum: 0 - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_memory_tool_20250818: object` - `type: "memory_20250818"` - `name: "memory"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_computer_use_20250124: object` - `type: "computer_20250124"` - `display_height_px: number` The height of the display in pixels. minimum: 1 - `display_width_px: number` The width of the display in pixels. minimum: 1 - `name: "computer"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `display_number: optional number` The X11 display number (e.g. 0, 1) for the display. minimum: 0 - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_text_editor_20241022: object` - `type: "text_editor_20241022"` - `name: "str_replace_editor"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_computer_use_20251124: object` - `type: "computer_20251124"` - `display_height_px: number` The height of the display in pixels. minimum: 1 - `display_width_px: number` The width of the display in pixels. minimum: 1 - `name: "computer"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `display_number: optional number` The X11 display number (e.g. 0, 1) for the display. minimum: 0 - `enable_zoom: optional boolean` Whether to enable an action to take a zoomed-in screenshot of the screen. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_computer_toolset_20260801: object` The computer toolset: a single `tools[]` entry (carrying no `name`) that declares the computer tool family. The model is served the family's tool with any members disabled via `configs` removed from its schema. Every member is enabled by default, zoom included. The single-tool options `display_number` and `enable_zoom` are not fields of a toolset entry — it carries only `type`, `configs`, and `cache_control`; zoom is controlled via `configs.zoom.enabled`. - `type: "computer_toolset_20260801"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `configs: optional object` Sparse per-member overrides, keyed by member name. Absent, null, and {} are equivalent; a member's defaults apply wherever its key is absent. - `type: optional object` `type`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `cursor_position: optional object` `cursor_position`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `double_click: optional object` `double_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `hold_key: optional object` `hold_key`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `key: optional object` `key`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_click: optional object` `left_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_click_drag: optional object` `left_click_drag`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_mouse_down: optional object` `left_mouse_down`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_mouse_up: optional object` `left_mouse_up`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `middle_click: optional object` `middle_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `mouse_move: optional object` `mouse_move`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `right_click: optional object` `right_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `screenshot: optional object` `screenshot`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `scroll: optional object` `scroll`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `triple_click: optional object` `triple_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `wait: optional object` `wait`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `zoom: optional object` `zoom`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `beta_tool_text_editor_20250124: object` - `type: "text_editor_20250124"` - `name: "str_replace_editor"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_text_editor_20250429: object` - `type: "text_editor_20250429"` - `name: "str_replace_based_edit_tool"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_text_editor_20250728: object` - `type: "text_editor_20250728"` - `name: "str_replace_based_edit_tool"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: optional array of map[unknown]` - `max_characters: optional number` Maximum number of characters to display when viewing a file. If not specified, defaults to displaying the full file. minimum: 1 - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_web_search_tool_20250305: object` - `type: "web_search_20250305"` - `name: "web_search"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: optional array of string` If provided, only these domains will be included in results. Cannot be used alongside `blocked_domains`. - `blocked_domains: optional array of string` If provided, these domains will never appear in results. Cannot be used alongside `allowed_domains`. - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `user_location: optional object` Parameters for the user's location. Used to provide more relevant search results. - `type: "approximate"` - `city: optional string` The city of the user. minLength: 1, maxLength: 255 - `country: optional string` The two letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1_alpha-2) of the user. minLength: 2, maxLength: 2 - `region: optional string` The region of the user. minLength: 1, maxLength: 255 - `timezone: optional string` The [IANA timezone](https://nodatime.org/TimeZones) of the user. minLength: 1, maxLength: 255 - `beta_web_fetch_tool_20250910: object` - `type: "web_fetch_20250910"` - `name: "web_fetch"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: optional array of string` List of domains to allow fetching from - `blocked_domains: optional array of string` List of domains to block fetching from - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `citations: optional object` Citations configuration for fetched documents. Citations are disabled by default. - `enabled: optional boolean` - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_content_tokens: optional number` Maximum number of tokens used by including web page text content in the context. The limit is approximate and does not apply to binary content such as PDFs. minimum: 1 - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `url_sources: optional object` Which sources contribute to the set of URLs the tool may fetch. Omitted means every source. - `client_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which client tools' results contribute fetchable URLs: "all", "none", or an only or except list of client tool names from tools[]. - `beta_web_fetch_url_source_all: object` The `url_sources` variant under which a source contributes in full: every result of the tool filter's source, or all user input. - `type: "all"` - `beta_web_fetch_url_source_none: object` The `url_sources` variant under which a source contributes nothing: no result of the tool filter's source, or no user input. - `type: "none"` - `beta_web_fetch_url_source_only: object` The tool filter variant under which only the named tools' results contribute. - `type: "only"` - `tools: array of BetaWebFetchURLSourceToolReference` - `type: "tool_reference"` - `name: string` - `beta_web_fetch_url_source_except: object` The tool filter variant under which every result but the named tools' contributes. - `type: "except"` - `tools: array of BetaWebFetchURLSourceToolReference` - `type: "tool_reference"` - `name: string` - `server_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which server tools' results contribute fetchable URLs: "all", "none", or an only or except list of server tool names from tools[]; only web_search and web_fetch results ever contribute. - `beta_web_fetch_url_source_all: object` The `url_sources` variant under which a source contributes in full: every result of the tool filter's source, or all user input. - `beta_web_fetch_url_source_none: object` The `url_sources` variant under which a source contributes nothing: no result of the tool filter's source, or no user input. - `beta_web_fetch_url_source_only: object` The tool filter variant under which only the named tools' results contribute. - `beta_web_fetch_url_source_except: object` The tool filter variant under which every result but the named tools' contributes. - `user_input: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone` Whether URLs in user messages are fetchable: "all" or "none". - `beta_web_fetch_url_source_all: object` The `url_sources` variant under which a source contributes in full: every result of the tool filter's source, or all user input. - `beta_web_fetch_url_source_none: object` The `url_sources` variant under which a source contributes nothing: no result of the tool filter's source, or no user input. - `beta_web_search_tool_20260209: object` - `type: "web_search_20260209"` - `name: "web_search"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: optional array of string` If provided, only these domains will be included in results. Cannot be used alongside `blocked_domains`. - `blocked_domains: optional array of string` If provided, these domains will never appear in results. Cannot be used alongside `allowed_domains`. - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `user_location: optional object` Parameters for the user's location. Used to provide more relevant search results. - `type: "approximate"` - `city: optional string` The city of the user. minLength: 1, maxLength: 255 - `country: optional string` The two letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1_alpha-2) of the user. minLength: 2, maxLength: 2 - `region: optional string` The region of the user. minLength: 1, maxLength: 255 - `timezone: optional string` The [IANA timezone](https://nodatime.org/TimeZones) of the user. minLength: 1, maxLength: 255 - `beta_web_fetch_tool_20260209: object` - `type: "web_fetch_20260209"` - `name: "web_fetch"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: optional array of string` List of domains to allow fetching from - `blocked_domains: optional array of string` List of domains to block fetching from - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `citations: optional object` Citations configuration for fetched documents. Citations are disabled by default. - `enabled: optional boolean` - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_content_tokens: optional number` Maximum number of tokens used by including web page text content in the context. The limit is approximate and does not apply to binary content such as PDFs. minimum: 1 - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `url_sources: optional object` Which sources contribute to the set of URLs the tool may fetch. Omitted means every source. - `client_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which client tools' results contribute fetchable URLs: "all", "none", or an only or except list of client tool names from tools[]. - `server_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which server tools' results contribute fetchable URLs: "all", "none", or an only or except list of server tool names from tools[]; only web_search and web_fetch results ever contribute. - `user_input: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone` Whether URLs in user messages are fetchable: "all" or "none". - `beta_web_fetch_tool_20260309: object` Web fetch tool with use_cache parameter for bypassing cached content. - `type: "web_fetch_20260309"` - `name: "web_fetch"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: optional array of string` List of domains to allow fetching from - `blocked_domains: optional array of string` List of domains to block fetching from - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `citations: optional object` Citations configuration for fetched documents. Citations are disabled by default. - `enabled: optional boolean` - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_content_tokens: optional number` Maximum number of tokens used by including web page text content in the context. The limit is approximate and does not apply to binary content such as PDFs. minimum: 1 - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `url_sources: optional object` Which sources contribute to the set of URLs the tool may fetch. Omitted means every source. - `client_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which client tools' results contribute fetchable URLs: "all", "none", or an only or except list of client tool names from tools[]. - `server_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which server tools' results contribute fetchable URLs: "all", "none", or an only or except list of server tool names from tools[]; only web_search and web_fetch results ever contribute. - `user_input: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone` Whether URLs in user messages are fetchable: "all" or "none". - `use_cache: optional boolean` Whether to use cached content. Set to false to bypass the cache and fetch fresh content. Only set to false when the user explicitly requests fresh content or when fetching rapidly-changing sources. - `beta_web_search_tool_20260318: object` - `type: "web_search_20260318"` - `name: "web_search"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: optional array of string` If provided, only these domains will be included in results. Cannot be used alongside `blocked_domains`. - `blocked_domains: optional array of string` If provided, these domains will never appear in results. Cannot be used alongside `allowed_domains`. - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `response_inclusion: optional "full" or "excluded"` How this tool's result blocks appear in the API response when the result was consumed by a completed code_execution call in the same turn. 'full' returns the complete content (default). 'excluded' drops the nested server_tool_use and result block pair entirely. Results from direct calls, or from code_execution calls that paused before completing, are always returned in full so they can be sent back on the next turn. - `"full"` - `"excluded"` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `user_location: optional object` Parameters for the user's location. Used to provide more relevant search results. - `type: "approximate"` - `city: optional string` The city of the user. minLength: 1, maxLength: 255 - `country: optional string` The two letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1_alpha-2) of the user. minLength: 2, maxLength: 2 - `region: optional string` The region of the user. minLength: 1, maxLength: 255 - `timezone: optional string` The [IANA timezone](https://nodatime.org/TimeZones) of the user. minLength: 1, maxLength: 255 - `beta_web_fetch_tool_20260318: object` - `type: "web_fetch_20260318"` - `name: "web_fetch"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: optional array of string` List of domains to allow fetching from - `blocked_domains: optional array of string` List of domains to block fetching from - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `citations: optional object` Citations configuration for fetched documents. Citations are disabled by default. - `enabled: optional boolean` - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_content_tokens: optional number` Maximum number of tokens used by including web page text content in the context. The limit is approximate and does not apply to binary content such as PDFs. minimum: 1 - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `response_inclusion: optional "full" or "excluded"` How this tool's result blocks appear in the API response when the result was consumed by a completed code_execution call in the same turn. 'full' returns the complete content (default). 'excluded' drops the nested server_tool_use and result block pair entirely. Results from direct calls, or from code_execution calls that paused before completing, are always returned in full so they can be sent back on the next turn. - `"full"` - `"excluded"` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `url_sources: optional object` Which sources contribute to the set of URLs the tool may fetch. Omitted means every source. - `client_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which client tools' results contribute fetchable URLs: "all", "none", or an only or except list of client tool names from tools[]. - `server_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which server tools' results contribute fetchable URLs: "all", "none", or an only or except list of server tool names from tools[]; only web_search and web_fetch results ever contribute. - `user_input: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone` Whether URLs in user messages are fetchable: "all" or "none". - `use_cache: optional boolean` Whether to use cached content. Set to false to bypass the cache and fetch fresh content. Only set to false when the user explicitly requests fresh content or when fetching rapidly-changing sources. - `beta_advisor_tool_20260301: object` - `type: "advisor_20260301"` - `model: "claude-haiku-5-5" or "claude-sonnet-5-5" or "claude-fable-5-1" or 17 more or string` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-haiku-5-5"` Fastest model for high-volume, real-time tasks - `"claude-sonnet-5-5"` Efficient model for coding and agents - `"claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows - `"claude-opus-5-5"` Powerful intelligence for coding, knowledge work, and long-running agents - `"claude-mythos-5-1"` Our most capable model for cybersecurity and biology research, available through trusted access programs - `"claude-sonnet-5"` Efficient model for coding and agents - `"claude-fable-5"` Next generation of intelligence for the hardest knowledge work and coding problems - `"claude-mythos-5"` Most capable model for cybersecurity and biology research - `"claude-opus-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-8"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-7"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-6"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-6"` Best combination of speed and intelligence - `"claude-haiku-4-5"` - `"claude-haiku-4-5-20251001"` - `"claude-opus-4-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-5-20251101"` Powerful intelligence for long-running agents and coding - `"claude-mythos-preview"` **Deprecated**: Will reach end-of-life on June 30, 2026. Please migrate to claude-mythos-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. New class of intelligence, strongest in coding and cybersecurity - `"claude-sonnet-4-5"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `"claude-sonnet-4-5-20250929"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `name: "advisor"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `caching: optional object` Caching for the advisor's own prompt. When set, each advisor call writes a cache entry at the given TTL so subsequent calls in the same conversation read the stable prefix. When omitted, the advisor prompt is not cached. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_tokens: optional number` Bounds the advisor's total output (thinking + text) per call. When the advisor hits this cap, the returned advisor_result or advisor_redacted_result block carries stop_reason='max_tokens', and a truncation note is appended to the advice text the worker model sees (inside the encrypted blob in redacted mode). When set, the server also emits a remaining-tokens budget block in the advisor's prompt so the advisor self-shapes toward the cap. When omitted, the advisor model's default output cap applies and no budget block is emitted. minimum: 1024 - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_search_tool_bm25_20251119: object` - `type: "tool_search_tool_bm25_20251119" or "tool_search_tool_bm25"` - `"tool_search_tool_bm25_20251119"` - `"tool_search_tool_bm25"` - `name: "tool_search_tool_bm25"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_search_tool_regex_20251119: object` - `type: "tool_search_tool_regex_20251119" or "tool_search_tool_regex"` - `"tool_search_tool_regex_20251119"` - `"tool_search_tool_regex"` - `name: "tool_search_tool_regex"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_mcp_toolset: object` Configuration for a group of tools from an MCP server. Allows configuring enabled status and defer_loading for all tools from an MCP server, with optional per-tool overrides. - `type: "mcp_toolset"` - `mcp_server_name: string` Name of the MCP server to configure tools for minLength: 1, maxLength: 255 - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `configs: optional map[BetaMCPToolConfig]` Configuration overrides for specific tools, keyed by tool name - `defer_loading: optional boolean` - `enabled: optional boolean` - `default_config: optional object` Default configuration applied to all tools from this server - `defer_loading: optional boolean` - `enabled: optional boolean` - `tools: optional array of BetaMCPToolParam` The server's tool listing, pinned: when present, the server is not asked for its tools before sampling and exactly these entries, with `default_config` and `configs` applied, are the toolset's tools. Copy it from the `mcp_tool_listing` block of an earlier response. - `input_schema: map[unknown]` The tool's input schema as the MCP server lists it, verbatim. - `name: string` The tool's name as the MCP server lists it (not prefixed with the server name). minLength: 1 - `description: optional string` The tool's description as the MCP server lists it. - `beta_response_tool_removal_block: object` An entry of a `compaction` block's `tool_changes`: a tool of the request's `tools` (or an MCP tool or toolset) that the compacted range withdrew. Send it back unchanged. - `type: "tool_removal"` - `tool: BetaResponseToolChangeToolReference or BetaResponseToolChangeMCPToolReference or BetaResponseToolChangeMCPToolsetReference` A reference to the withdrawn `tools` entry, MCP tool or MCP toolset. - `beta_response_tool_change_tool_reference: object` Reference to a single tool, by the name the model uses to call it, as a `compaction` block's `tool_changes` entry reports it: a tool declared in `tools` or defined by an earlier `tool_addition` block. Send it back unchanged with the block. - `beta_response_tool_change_mcp_tool_reference: object` Reference to a single MCP tool, by its server and its name on that server, as a `compaction` block's `tool_changes` entry reports it. Send it back unchanged with the block. - `beta_response_tool_change_mcp_toolset_reference: object` Reference to every tool in the named MCP server's toolset, as a `compaction` block's `tool_changes` entry reports it. Send it back unchanged with the block. - `beta_fallback_block: object` Marks the point in `content` where one model's output gives way to the next. One block appears per hop where a preceding model actually ran this turn and declined. A turn where no preceding model ran and declined has no such boundary and carries no block — the signal for whether a fallback model served the response is the presence of a `fallback_message` entry in `usage.iterations`, not this block. The block is treated like a server-tool content block for streaming: it arrives via the standard `content_block_start` / `content_block_stop` pair and carries no deltas. - `type: "fallback"` - `from: object` The model whose output ends at this point — the model that declined at this hop. When the declining hop is the requested model, its `model` echoes the top-level `model` string the caller sent (alias or canonical); when the declining hop is a fallback model, its `model` is that model's canonical id. - `model: "claude-haiku-5-5" or "claude-sonnet-5-5" or "claude-fable-5-1" or 17 more or string` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-haiku-5-5"` Fastest model for high-volume, real-time tasks - `"claude-sonnet-5-5"` Efficient model for coding and agents - `"claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows - `"claude-opus-5-5"` Powerful intelligence for coding, knowledge work, and long-running agents - `"claude-mythos-5-1"` Our most capable model for cybersecurity and biology research, available through trusted access programs - `"claude-sonnet-5"` Efficient model for coding and agents - `"claude-fable-5"` Next generation of intelligence for the hardest knowledge work and coding problems - `"claude-mythos-5"` Most capable model for cybersecurity and biology research - `"claude-opus-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-8"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-7"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-6"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-6"` Best combination of speed and intelligence - `"claude-haiku-4-5"` - `"claude-haiku-4-5-20251001"` - `"claude-opus-4-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-5-20251101"` Powerful intelligence for long-running agents and coding - `"claude-mythos-preview"` **Deprecated**: Will reach end-of-life on June 30, 2026. Please migrate to claude-mythos-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. New class of intelligence, strongest in coding and cybersecurity - `"claude-sonnet-4-5"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `"claude-sonnet-4-5-20250929"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `to: object` The fallback model producing the content that follows this block. Its `model` is always the canonical id. - `model: "claude-haiku-5-5" or "claude-sonnet-5-5" or "claude-fable-5-1" or 17 more or string` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `trigger: object` What caused the `from` model to hand over at this hop. - `type: "refusal"` - `category: "cyber" or "bio" or "frontier_llm" or 2 more` The policy category that triggered the `from` model's refusal at this hop. `null` when the refusal doesn't map to a named category. Same vocabulary as `stop_details.category`. - `"cyber"` The request could enable cyber harm, such as malware or exploit development. Benign cybersecurity work can also trigger this category. - `"bio"` The request could enable biological harm, such as dangerous lab methods. Beneficial life sciences work can also trigger this category. - `"frontier_llm"` The request could assist the development of competing AI models, which is restricted under [Anthropic's commercial terms](https://www.anthropic.com/legal/commercial-terms). Benign machine learning work can also trigger this category. - `"reasoning_extraction"` The request asks the model to reproduce its internal reasoning in the response text. To get reasoning in a structured form instead, use [adaptive thinking](https://platform.claude.com/docs/en/build-with-claude/adaptive-thinking?sdk_languages=cli). - `"general_harms"` The request could be related to an area that was determined as harmful. Benign work might sometimes trigger this category. - `beta_mcp_tool_listing_block: object` The tool listing the server fetched from an MCP server while producing this response. Send the assistant message back unchanged, this block included, so later requests use this listing instead of asking the MCP server again. - `type: "mcp_tool_listing"` - `mcp_server_name: string` - `tools: array of BetaMCPTool` - `input_schema: map[unknown]` - `name: string` - `description: optional string` - `context_management: object` Context management response. Information about context management strategies applied during the request. - `applied_edits: array of BetaClearToolUses20250919EditResponse or BetaClearThinking20251015EditResponse` List of context management edits that were applied. - `beta_clear_tool_uses_20250919_edit_response: object` - `type: "clear_tool_uses_20250919"` The type of context management edit applied. - `cleared_input_tokens: number` Number of input tokens cleared by this edit. minimum: 0 - `cleared_tool_uses: number` Number of tool uses that were cleared. minimum: 0 - `beta_clear_thinking_20251015_edit_response: object` - `type: "clear_thinking_20251015"` The type of context management edit applied. - `cleared_input_tokens: number` Number of input tokens cleared by this edit. minimum: 0 - `cleared_thinking_turns: number` Number of thinking turns that were cleared. minimum: 0 - `diagnostics: object` Request-level diagnostics. `null` when the request did not supply `diagnostics`, or when it did and no prompt-cache divergence was detected. - `cache_miss_reason: BetaCacheMissModelChanged or BetaCacheMissSystemChanged or BetaCacheMissToolsChanged or 3 more` Explains why the prompt cache could not fully reuse the prefix from the request identified by `diagnostics.previous_message_id`. `null` means diagnosis is still pending — the response was serialized before the background comparison completed. - `beta_cache_miss_model_changed: object` - `type: "model_changed"` - `cache_missed_input_tokens: number` Approximate number of input tokens that would have been read from cache had the prefix matched the previous request. - `beta_cache_miss_system_changed: object` - `type: "system_changed"` - `cache_missed_input_tokens: number` Approximate number of input tokens that would have been read from cache had the prefix matched the previous request. - `beta_cache_miss_tools_changed: object` - `type: "tools_changed"` - `cache_missed_input_tokens: number` Approximate number of input tokens that would have been read from cache had the prefix matched the previous request. - `beta_cache_miss_messages_changed: object` - `type: "messages_changed"` - `cache_missed_input_tokens: number` Approximate number of input tokens that would have been read from cache had the prefix matched the previous request. - `beta_cache_miss_previous_message_not_found: object` - `type: "previous_message_not_found"` - `beta_cache_miss_unavailable: object` - `type: "unavailable"` - `model: "claude-haiku-5-5" or "claude-sonnet-5-5" or "claude-fable-5-1" or 17 more or string` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-haiku-5-5"` Fastest model for high-volume, real-time tasks - `"claude-sonnet-5-5"` Efficient model for coding and agents - `"claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows - `"claude-opus-5-5"` Powerful intelligence for coding, knowledge work, and long-running agents - `"claude-mythos-5-1"` Our most capable model for cybersecurity and biology research, available through trusted access programs - `"claude-sonnet-5"` Efficient model for coding and agents - `"claude-fable-5"` Next generation of intelligence for the hardest knowledge work and coding problems - `"claude-mythos-5"` Most capable model for cybersecurity and biology research - `"claude-opus-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-8"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-7"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-6"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-6"` Best combination of speed and intelligence - `"claude-haiku-4-5"` - `"claude-haiku-4-5-20251001"` - `"claude-opus-4-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-5-20251101"` Powerful intelligence for long-running agents and coding - `"claude-mythos-preview"` **Deprecated**: Will reach end-of-life on June 30, 2026. Please migrate to claude-mythos-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. New class of intelligence, strongest in coding and cybersecurity - `"claude-sonnet-4-5"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `"claude-sonnet-4-5-20250929"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `role: "assistant"` Conversational role of the generated message. This will always be `"assistant"`. - `stop_details: object` Structured information about why model output stopped. This is `null` when the `stop_reason` has no additional detail to report. - `type: "refusal"` - `category: "cyber" or "bio" or "frontier_llm" or 2 more` The policy category that triggered the refusal. `null` when the refusal doesn't map to a named category. - `"cyber"` The request could enable cyber harm, such as malware or exploit development. Benign cybersecurity work can also trigger this category. - `"bio"` The request could enable biological harm, such as dangerous lab methods. Beneficial life sciences work can also trigger this category. - `"frontier_llm"` The request could assist the development of competing AI models, which is restricted under [Anthropic's commercial terms](https://www.anthropic.com/legal/commercial-terms). Benign machine learning work can also trigger this category. - `"reasoning_extraction"` The request asks the model to reproduce its internal reasoning in the response text. To get reasoning in a structured form instead, use [adaptive thinking](https://platform.claude.com/docs/en/build-with-claude/adaptive-thinking?sdk_languages=cli). - `"general_harms"` The request could be related to an area that was determined as harmful. Benign work might sometimes trigger this category. - `explanation: string` Human-readable explanation of the refusal. This text is not guaranteed to be stable. `null` when no explanation is available for the category. - `fallback_credit_token: string` Opaque code that refunds the cache-miss cost when retrying this refused request on the fallback model. Pass it as `fallback_credit_token` on the retry request. Expires 5 minutes after the refusal. The retry is sent either with the same request body (`system`, `messages`, `tools`, and other render-shaping fields), or with the same body plus one appended `assistant` message whose content is the partial text (with any trailing whitespace stripped from the final text block) and paired server-tool blocks from this refusal — which also authorizes that appended turn as an assistant-prefill continuation on models that otherwise disallow prefill. A token minted mid-server-tool-loop whose partial content was continuable may only be redeemed the second way — if a same-body retry is rejected with a 400 saying the token must be redeemed by continuing the partial response, retry the second way instead. Either way: same workspace, same platform; a mismatch is a 400. Resending a token for an already-warm prefix is permitted but yields no additional credit. `null` when the refused model isn't eligible for a fallback credit. - `fallback_has_prefill_claim: boolean` Whether the accompanying `fallback_credit_token` may be redeemed with the appended-assistant retry form. Only set when `fallback_credit_token` is present. `true`: retry by resending the same request body plus one appended `assistant` message whose content is this response's `content` with any trailing whitespace stripped from the final text block and unpaired `tool_use` blocks omitted (the same appended-turn shape described on `fallback_credit_token`), with the token attached. `false`: retry by resending the original request body unchanged, with the token attached — the appended-assistant form is not available for this refusal (no continuable partial content, or the request uses `output_format` or a `tool_choice` that forces tool use). One exception: when the request used `output_format` or a forced `tool_choice` and the refusal arrived after server tools (including MCP connector tools) had already executed, the token may not be redeemable by either retry form; if the exact-body retry is then rejected with a 400 saying the token must be redeemed by continuing the partial response, discard the token and retry without it. Advisory: if an appended-assistant retry is rejected with a 400 despite `true`, fall back to resending the original request body with the token. - `recommended_model: string` The server's suggested retry target for this refusal. Populated when a fallback attempt could not be made (the fallback model's rate limit was exhausted, or it was overloaded); names the fallback model the caller can retry directly. Null otherwise. - `stop_reason: "end_turn" or "max_tokens" or "stop_sequence" or 5 more` The reason that we stopped. This may be one the following values: * `"end_turn"`: the model reached a natural stopping point * `"max_tokens"`: we exceeded the requested `max_tokens` or the model's maximum * `"stop_sequence"`: one of your provided custom `stop_sequences` was generated * `"tool_use"`: the model invoked one or more tools * `"pause_turn"`: we paused a long-running turn. You may provide the response back as-is in a subsequent request to let the model continue. * `"refusal"`: when streaming classifiers intervene to handle potential policy violations * `"model_context_window_exceeded"`: we exceeded the model's context window In non-streaming mode this value is always non-null. In streaming mode, it is null in the `message_start` event and non-null otherwise. - `"end_turn"` - `"max_tokens"` - `"stop_sequence"` - `"tool_use"` - `"pause_turn"` - `"compaction"` - `"refusal"` - `"model_context_window_exceeded"` - `stop_sequence: string` Which custom stop sequence was generated, if any. This value will be a non-null string if one of your custom stop sequences was generated. - `usage: object` Billing and rate-limit usage. Anthropic's API bills and rate-limits by token counts, as tokens represent the underlying cost to our systems. Under the hood, the API transforms requests into a format suitable for the model. The model's output then goes through a parsing stage before becoming an API response. As a result, the token counts in `usage` will not match one-to-one with the exact visible content of an API request or response. For example, `output_tokens` will be non-zero, even for an empty string response from Claude. Total input tokens in a request is the summation of `input_tokens`, `cache_creation_input_tokens`, and `cache_read_input_tokens`. - `cache_creation: object` Breakdown of cached tokens by TTL - `ephemeral_1h_input_tokens: number` The number of input tokens used to create the 1 hour cache entry. minimum: 0 - `ephemeral_5m_input_tokens: number` The number of input tokens used to create the 5 minute cache entry. minimum: 0 - `cache_creation_input_tokens: number` The number of input tokens used to create the cache entry. minimum: 0 - `cache_read_input_tokens: number` The number of input tokens read from the cache. minimum: 0 - `fallback_credit: object` Outcome of the `fallback_credit_token` presented on this request. Present on every response to a non-batch request that carried a `fallback_credit_token`, in either redemption mode; absent otherwise (batch items accept and ignore the token and carry no outcome object). - `status: BetaFallbackCreditRedeemed or BetaFallbackCreditNotApplied` Whether the fallback-credit reprice was applied to this response's billing. A union discriminated on `type`. `redeemed`: the retry is billed as if the conversation had been on the retry model all along — including when the resulting shift is zero because there was nothing to move. `not_applied`: no reprice was applied; the arm's `reason` says why. - `beta_fallback_credit_redeemed: object` The reprice was applied: the retry is billed as if the conversation had been on the retry model all along. - `type: "redeemed"` - `beta_fallback_credit_not_applied: object` No reprice was applied; `reason` says why. - `type: "not_applied"` - `reason: "body_mismatch" or "continuation_excluded" or "continuation_only" or 9 more` Why the reprice was not applied. A closed enum; additions to the redemption-check vocabulary arrive as deliberate schema updates. - `"body_mismatch"` - `"continuation_excluded"` - `"continuation_only"` - `"expired"` - `"invalid_target_model"` - `"not_enabled"` - `"reprice_unavailable"` - `"temporarily_unavailable"` - `"variant_fields_present"` - `"wrong_organization"` - `"wrong_platform"` - `"wrong_workspace"` - `remove_to_redeem: optional array of string` Request fields to remove before retrying, so the retry can redeem this token. Present exactly when `reason` is `variant_fields_present` — never null, never an empty array; absent otherwise. Fields are named only from your own request, and only after the sealed variant hash matched. A served best-effort retry has already been billed at normal price; nothing redeems retroactively, but a corrected re-send inside the token's five-minute window can still redeem. - `inference_geo: string` The geographic region where inference was performed for this request. - `input_tokens: number` The number of input tokens which were used. minimum: 0 - `iterations: array of BetaMessageIterationUsage or BetaCompactionIterationUsage or BetaAdvisorMessageIterationUsage or BetaFallbackMessageIterationUsage` Per-iteration token usage breakdown. Each entry represents one sampling iteration, with its own input/output token counts and cache statistics, discriminated by `type`. For `message` entries (model sampling iterations, such as the turns of a server-side tool use loop), this allows you to: - Calculate the context window size from the last `message` entry - Understand token accumulation across server-side tool use loops A `compaction` entry reports the token usage of the compaction operation itself — the server-side request that summarizes the context being closed — NOT the size of the context that was compacted away, and its token counts can be much smaller than that closed context (for example, a compaction that closes a ~200k-token context can report only a few thousand tokens). Do not derive the context window size from a `compaction` entry, even when it is the last entry. A `compaction` entry's tokens are not included in the top-level `usage` fields. When an input-token trigger is in effect (the default — 150,000 tokens unless configured otherwise), each `compaction` entry closes a context that had reached at least that threshold, though the context can exceed it by the final iteration's output and tool results. - `beta_message_iteration_usage: object` Token usage for a sampling iteration. - `type: "message"` Usage for a sampling iteration - `cache_creation: object` Breakdown of cached tokens by TTL - `ephemeral_1h_input_tokens: number` The number of input tokens used to create the 1 hour cache entry. minimum: 0 - `ephemeral_5m_input_tokens: number` The number of input tokens used to create the 5 minute cache entry. minimum: 0 - `cache_creation_input_tokens: number` The number of input tokens used to create the cache entry. minimum: 0 - `cache_read_input_tokens: number` The number of input tokens read from the cache. minimum: 0 - `input_tokens: number` The number of input tokens which were used. minimum: 0 - `model: "claude-haiku-5-5" or "claude-sonnet-5-5" or "claude-fable-5-1" or 17 more or string` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-haiku-5-5"` Fastest model for high-volume, real-time tasks - `"claude-sonnet-5-5"` Efficient model for coding and agents - `"claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows - `"claude-opus-5-5"` Powerful intelligence for coding, knowledge work, and long-running agents - `"claude-mythos-5-1"` Our most capable model for cybersecurity and biology research, available through trusted access programs - `"claude-sonnet-5"` Efficient model for coding and agents - `"claude-fable-5"` Next generation of intelligence for the hardest knowledge work and coding problems - `"claude-mythos-5"` Most capable model for cybersecurity and biology research - `"claude-opus-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-8"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-7"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-6"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-6"` Best combination of speed and intelligence - `"claude-haiku-4-5"` - `"claude-haiku-4-5-20251001"` - `"claude-opus-4-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-5-20251101"` Powerful intelligence for long-running agents and coding - `"claude-mythos-preview"` **Deprecated**: Will reach end-of-life on June 30, 2026. Please migrate to claude-mythos-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. New class of intelligence, strongest in coding and cybersecurity - `"claude-sonnet-4-5"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `"claude-sonnet-4-5-20250929"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `output_tokens: number` The number of output tokens which were used. minimum: 0 - `beta_compaction_iteration_usage: object` Token usage for a compaction iteration. - `type: "compaction"` Usage for a compaction iteration - `cache_creation: object` Breakdown of cached tokens by TTL - `ephemeral_1h_input_tokens: number` The number of input tokens used to create the 1 hour cache entry. minimum: 0 - `ephemeral_5m_input_tokens: number` The number of input tokens used to create the 5 minute cache entry. minimum: 0 - `cache_creation_input_tokens: number` The number of input tokens used to create the cache entry. minimum: 0 - `cache_read_input_tokens: number` The number of input tokens read from the cache. minimum: 0 - `input_tokens: number` The number of input tokens which were used. minimum: 0 - `output_tokens: number` The number of output tokens which were used. minimum: 0 - `beta_advisor_message_iteration_usage: object` Token usage for an advisor sub-inference iteration. - `type: "advisor_message"` Usage for an advisor sub-inference iteration - `cache_creation: object` Breakdown of cached tokens by TTL - `ephemeral_1h_input_tokens: number` The number of input tokens used to create the 1 hour cache entry. minimum: 0 - `ephemeral_5m_input_tokens: number` The number of input tokens used to create the 5 minute cache entry. minimum: 0 - `cache_creation_input_tokens: number` The number of input tokens used to create the cache entry. minimum: 0 - `cache_read_input_tokens: number` The number of input tokens read from the cache. minimum: 0 - `input_tokens: number` The number of input tokens which were used. minimum: 0 - `model: "claude-haiku-5-5" or "claude-sonnet-5-5" or "claude-fable-5-1" or 17 more or string` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-haiku-5-5"` Fastest model for high-volume, real-time tasks - `"claude-sonnet-5-5"` Efficient model for coding and agents - `"claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows - `"claude-opus-5-5"` Powerful intelligence for coding, knowledge work, and long-running agents - `"claude-mythos-5-1"` Our most capable model for cybersecurity and biology research, available through trusted access programs - `"claude-sonnet-5"` Efficient model for coding and agents - `"claude-fable-5"` Next generation of intelligence for the hardest knowledge work and coding problems - `"claude-mythos-5"` Most capable model for cybersecurity and biology research - `"claude-opus-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-8"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-7"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-6"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-6"` Best combination of speed and intelligence - `"claude-haiku-4-5"` - `"claude-haiku-4-5-20251001"` - `"claude-opus-4-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-5-20251101"` Powerful intelligence for long-running agents and coding - `"claude-mythos-preview"` **Deprecated**: Will reach end-of-life on June 30, 2026. Please migrate to claude-mythos-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. New class of intelligence, strongest in coding and cybersecurity - `"claude-sonnet-4-5"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `"claude-sonnet-4-5-20250929"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `output_tokens: number` The number of output tokens which were used. minimum: 0 - `beta_fallback_message_iteration_usage: object` Token usage for the fallback-model attempt of a server-side fallback request. The terminal entry of a fallback-served turn: when a fallback hop's output is the returned message, the entry for the iteration that completed it carries this type in place of `message`. A declined hop and the serving hop's earlier tool-loop iterations produce `message` entries. Whether a fallback model served the response is signalled by the presence of this entry in `usage.iterations`. - `type: "fallback_message"` Usage for the fallback-model attempt that served the response - `cache_creation: object` Breakdown of cached tokens by TTL - `ephemeral_1h_input_tokens: number` The number of input tokens used to create the 1 hour cache entry. minimum: 0 - `ephemeral_5m_input_tokens: number` The number of input tokens used to create the 5 minute cache entry. minimum: 0 - `cache_creation_input_tokens: number` The number of input tokens used to create the cache entry. minimum: 0 - `cache_read_input_tokens: number` The number of input tokens read from the cache. minimum: 0 - `input_tokens: number` The number of input tokens which were used. minimum: 0 - `model: "claude-haiku-5-5" or "claude-sonnet-5-5" or "claude-fable-5-1" or 17 more or string` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-haiku-5-5"` Fastest model for high-volume, real-time tasks - `"claude-sonnet-5-5"` Efficient model for coding and agents - `"claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows - `"claude-opus-5-5"` Powerful intelligence for coding, knowledge work, and long-running agents - `"claude-mythos-5-1"` Our most capable model for cybersecurity and biology research, available through trusted access programs - `"claude-sonnet-5"` Efficient model for coding and agents - `"claude-fable-5"` Next generation of intelligence for the hardest knowledge work and coding problems - `"claude-mythos-5"` Most capable model for cybersecurity and biology research - `"claude-opus-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-8"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-7"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-6"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-6"` Best combination of speed and intelligence - `"claude-haiku-4-5"` - `"claude-haiku-4-5-20251001"` - `"claude-opus-4-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-5-20251101"` Powerful intelligence for long-running agents and coding - `"claude-mythos-preview"` **Deprecated**: Will reach end-of-life on June 30, 2026. Please migrate to claude-mythos-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. New class of intelligence, strongest in coding and cybersecurity - `"claude-sonnet-4-5"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `"claude-sonnet-4-5-20250929"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `output_tokens: number` The number of output tokens which were used. minimum: 0 - `output_tokens: number` The number of output tokens which were used. minimum: 0 - `output_tokens_details: object` Breakdown of output tokens by category. `output_tokens` remains the inclusive, authoritative total used for billing. This object provides a read-only decomposition for observability — for example, how many of the billed output tokens were spent on internal reasoning that may have been summarized before being returned to you. - `thinking_tokens: number` Number of output tokens the model generated as internal reasoning, including the thinking-block delimiter tokens. Reflects the raw reasoning the model produced, not the (possibly shorter) summarized thinking text returned in the response body. Computed by re-tokenizing the raw reasoning text, so it may differ from the model's exact generation count by a small number of tokens. Always ≤ `output_tokens`; `output_tokens - thinking_tokens` approximates the non-reasoning output. minimum: 0 - `server_tool_use: object` The number of server tool requests. - `web_fetch_requests: number` The number of web fetch tool requests. minimum: 0 - `web_search_requests: number` The number of web search tool requests. minimum: 0 - `service_tier: "standard" or "priority" or "batch"` If the request used the priority, standard, or batch tier. - `"standard"` - `"priority"` - `"batch"` - `speed: "standard" or "fast"` The inference speed mode used for this request. - `"standard"` - `"fast"` - `input_transformations: optional array of BetaInputTransformation` Changes the API made to the request's input before showing it to the model, and blocks that failed a binding check but were left unchanged: one entry per block, in request order. Two entry types today. `thinking_dropped` — a `thinking`, `redacted_thinking` or `connector_text` block from the request's `messages` that was removed from the prompt instead of being shown to the model because it failed a binding check. `thinking_mismatch_allowed` — a `thinking` or `redacted_thinking` block that failed the conversation check (the conversation before it differs from the one it was created in, or it carries no record of one on a model that requires it) and was shown to the model all the same, because that check is not enforced for this request. More entry types may be added over time; ignore types you do not recognize. Requires `anthropic-beta: thinking-binding-controls-2026-08-01`. Present on every such response from a model that supports extended thinking, as `[]` when there is no entry to report; without the beta, blocks are removed or left in place all the same but nothing is reported. Removed blocks contribute nothing to `usage.input_tokens`; blocks left in place count as sent. When streaming, the array is final in `message_start`; the final `message_delta` event carries it only when a server-side model fallback happened mid-stream, in which case it holds the serving model's entries and replaces the one in `message_start`. - `beta_thinking_dropped_input_transformation: object` - `type: "thinking_dropped"` Always `thinking_dropped` for this entry type. - `path: string` Where the removed block was in your request, as `messages.{i}.content.{j}`: `i` indexes the `messages` array you sent and `j` that message's `content` array — the same form error messages use. - `reason: "model_binding_mismatch" or "prefix_binding_mismatch" or "organization_binding_mismatch" or "end_user_binding_mismatch"` Which binding check removed the block: `model_binding_mismatch` — it was created by a model whose reasoning the requested model may not read; `prefix_binding_mismatch` — the conversation before it differs from the conversation it was created in (the rest of that turn's consecutive thinking blocks are removed with it, each with this reason); `organization_binding_mismatch` — it was created under a different organization (an Anthropic organization, AWS account or Google Cloud project) and this organization is not one of its additional organizations; `end_user_binding_mismatch` — it was created for a different end user, or was removed by the consumer-organization binding. A block that would fail several checks reports one reason, in this order of precedence: `organization_binding_mismatch`, `end_user_binding_mismatch`, `model_binding_mismatch`, `prefix_binding_mismatch`. - `"model_binding_mismatch"` - `"prefix_binding_mismatch"` - `"organization_binding_mismatch"` - `"end_user_binding_mismatch"` - `beta_thinking_mismatch_allowed_input_transformation: object` - `type: "thinking_mismatch_allowed"` Always `thinking_mismatch_allowed` for this entry type. - `path: string` Where the block is in your request, as `messages.{i}.content.{j}`: `i` indexes the `messages` array you sent and `j` that message's `content` array — the same form error messages use. - `reason: "model_binding_mismatch" or "prefix_binding_mismatch" or "organization_binding_mismatch" or "end_user_binding_mismatch"` Which binding check the block failed; the block was shown to the model all the same. Always `prefix_binding_mismatch` today — the conversation before the block differs from the conversation it was created in, or the block carries no record of one on a model that requires it. Were the check enforced for this request, the block would have been removed or the request rejected (`thinking.block_binding.prefix_mismatch_behavior`). A removal also takes the rest of that turn's consecutive thinking blocks, whereas here each block is checked on its own, so `thinking_mismatch_allowed` entries are a lower bound on what enforcement would remove. - `"model_binding_mismatch"` - `"prefix_binding_mismatch"` - `"organization_binding_mismatch"` - `"end_user_binding_mismatch"` - `beta_raw_message_stream_event: BetaRawMessageStartEvent or BetaRawMessageDeltaEvent or BetaRawMessageStopEvent or 3 more` - `beta_raw_message_start_event: object` - `type: "message_start"` - `message: object` - `type: "message"` Object type. For Messages, this is always `"message"`. - `id: string` Unique object identifier. The format and length of IDs may change over time. - `container: object` Information about the container used in this request. This will be non-null if a container tool (e.g. code execution) was used. - `content: array of BetaContentBlock` Content generated by the model. This is an array of content blocks, each of which has a `type` that determines its shape. Example: ```json [{"type": "text", "text": "Hi, I'm Claude."}] ``` If the request input `messages` ended with an `assistant` turn, then the response `content` will continue directly from that last turn. You can use this to constrain the model's output. For example, if the input `messages` were: ```json [ {"role": "user", "content": "What's the Greek name for Sun? (A) Sol (B) Helios (C) Sun"}, {"role": "assistant", "content": "The best answer is ("} ] ``` Then the response `content` might be: ```json [{"type": "text", "text": "B)"}] ``` - `context_management: object` Context management response. Information about context management strategies applied during the request. - `diagnostics: object` Request-level diagnostics. `null` when the request did not supply `diagnostics`, or when it did and no prompt-cache divergence was detected. - `model: "claude-haiku-5-5" or "claude-sonnet-5-5" or "claude-fable-5-1" or 17 more or string` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `role: "assistant"` Conversational role of the generated message. This will always be `"assistant"`. - `stop_details: object` Structured information about why model output stopped. This is `null` when the `stop_reason` has no additional detail to report. - `stop_reason: "end_turn" or "max_tokens" or "stop_sequence" or 5 more` The reason that we stopped. This may be one the following values: * `"end_turn"`: the model reached a natural stopping point * `"max_tokens"`: we exceeded the requested `max_tokens` or the model's maximum * `"stop_sequence"`: one of your provided custom `stop_sequences` was generated * `"tool_use"`: the model invoked one or more tools * `"pause_turn"`: we paused a long-running turn. You may provide the response back as-is in a subsequent request to let the model continue. * `"refusal"`: when streaming classifiers intervene to handle potential policy violations * `"model_context_window_exceeded"`: we exceeded the model's context window In non-streaming mode this value is always non-null. In streaming mode, it is null in the `message_start` event and non-null otherwise. - `stop_sequence: string` Which custom stop sequence was generated, if any. This value will be a non-null string if one of your custom stop sequences was generated. - `usage: object` Billing and rate-limit usage. Anthropic's API bills and rate-limits by token counts, as tokens represent the underlying cost to our systems. Under the hood, the API transforms requests into a format suitable for the model. The model's output then goes through a parsing stage before becoming an API response. As a result, the token counts in `usage` will not match one-to-one with the exact visible content of an API request or response. For example, `output_tokens` will be non-zero, even for an empty string response from Claude. Total input tokens in a request is the summation of `input_tokens`, `cache_creation_input_tokens`, and `cache_read_input_tokens`. - `input_transformations: optional array of BetaInputTransformation` Changes the API made to the request's input before showing it to the model, and blocks that failed a binding check but were left unchanged: one entry per block, in request order. Two entry types today. `thinking_dropped` — a `thinking`, `redacted_thinking` or `connector_text` block from the request's `messages` that was removed from the prompt instead of being shown to the model because it failed a binding check. `thinking_mismatch_allowed` — a `thinking` or `redacted_thinking` block that failed the conversation check (the conversation before it differs from the one it was created in, or it carries no record of one on a model that requires it) and was shown to the model all the same, because that check is not enforced for this request. More entry types may be added over time; ignore types you do not recognize. Requires `anthropic-beta: thinking-binding-controls-2026-08-01`. Present on every such response from a model that supports extended thinking, as `[]` when there is no entry to report; without the beta, blocks are removed or left in place all the same but nothing is reported. Removed blocks contribute nothing to `usage.input_tokens`; blocks left in place count as sent. When streaming, the array is final in `message_start`; the final `message_delta` event carries it only when a server-side model fallback happened mid-stream, in which case it holds the serving model's entries and replaces the one in `message_start`. - `beta_raw_message_delta_event: object` - `type: "message_delta"` - `context_management: object` Information about context management strategies applied during the request - `applied_edits: array of BetaClearToolUses20250919EditResponse or BetaClearThinking20251015EditResponse` List of context management edits that were applied. - `delta: object` - `container: object` Information about the container used in this request. This will be non-null if a container tool (e.g. code execution) was used. - `id: string` Identifier for the container used in this request - `expires_at: string` The time at which the container will expire. format: date-time - `skills: array of BetaContainerSkill` Skills loaded in the container - `stop_details: object` Structured information about why model output stopped. This is `null` when the `stop_reason` has no additional detail to report. - `type: "refusal"` - `category: "cyber" or "bio" or "frontier_llm" or 2 more` The policy category that triggered the refusal. `null` when the refusal doesn't map to a named category. - `explanation: string` Human-readable explanation of the refusal. This text is not guaranteed to be stable. `null` when no explanation is available for the category. - `fallback_credit_token: string` Opaque code that refunds the cache-miss cost when retrying this refused request on the fallback model. Pass it as `fallback_credit_token` on the retry request. Expires 5 minutes after the refusal. The retry is sent either with the same request body (`system`, `messages`, `tools`, and other render-shaping fields), or with the same body plus one appended `assistant` message whose content is the partial text (with any trailing whitespace stripped from the final text block) and paired server-tool blocks from this refusal — which also authorizes that appended turn as an assistant-prefill continuation on models that otherwise disallow prefill. A token minted mid-server-tool-loop whose partial content was continuable may only be redeemed the second way — if a same-body retry is rejected with a 400 saying the token must be redeemed by continuing the partial response, retry the second way instead. Either way: same workspace, same platform; a mismatch is a 400. Resending a token for an already-warm prefix is permitted but yields no additional credit. `null` when the refused model isn't eligible for a fallback credit. - `fallback_has_prefill_claim: boolean` Whether the accompanying `fallback_credit_token` may be redeemed with the appended-assistant retry form. Only set when `fallback_credit_token` is present. `true`: retry by resending the same request body plus one appended `assistant` message whose content is this response's `content` with any trailing whitespace stripped from the final text block and unpaired `tool_use` blocks omitted (the same appended-turn shape described on `fallback_credit_token`), with the token attached. `false`: retry by resending the original request body unchanged, with the token attached — the appended-assistant form is not available for this refusal (no continuable partial content, or the request uses `output_format` or a `tool_choice` that forces tool use). One exception: when the request used `output_format` or a forced `tool_choice` and the refusal arrived after server tools (including MCP connector tools) had already executed, the token may not be redeemable by either retry form; if the exact-body retry is then rejected with a 400 saying the token must be redeemed by continuing the partial response, discard the token and retry without it. Advisory: if an appended-assistant retry is rejected with a 400 despite `true`, fall back to resending the original request body with the token. - `recommended_model: string` The server's suggested retry target for this refusal. Populated when a fallback attempt could not be made (the fallback model's rate limit was exhausted, or it was overloaded); names the fallback model the caller can retry directly. Null otherwise. - `stop_reason: "end_turn" or "max_tokens" or "stop_sequence" or 5 more` - `"end_turn"` - `"max_tokens"` - `"stop_sequence"` - `"tool_use"` - `"pause_turn"` - `"compaction"` - `"refusal"` - `"model_context_window_exceeded"` - `stop_sequence: string` - `usage: object` Billing and rate-limit usage. Anthropic's API bills and rate-limits by token counts, as tokens represent the underlying cost to our systems. Under the hood, the API transforms requests into a format suitable for the model. The model's output then goes through a parsing stage before becoming an API response. As a result, the token counts in `usage` will not match one-to-one with the exact visible content of an API request or response. For example, `output_tokens` will be non-zero, even for an empty string response from Claude. Total input tokens in a request is the summation of `input_tokens`, `cache_creation_input_tokens`, and `cache_read_input_tokens`. - `cache_creation_input_tokens: number` The cumulative number of input tokens used to create the cache entry. minimum: 0 - `cache_read_input_tokens: number` The cumulative number of input tokens read from the cache. minimum: 0 - `fallback_credit: object` Outcome of the `fallback_credit_token` presented on this request. Present on every response to a non-batch request that carried a `fallback_credit_token`, in either redemption mode; absent otherwise (batch items accept and ignore the token and carry no outcome object). - `status: BetaFallbackCreditRedeemed or BetaFallbackCreditNotApplied` Whether the fallback-credit reprice was applied to this response's billing. A union discriminated on `type`. `redeemed`: the retry is billed as if the conversation had been on the retry model all along — including when the resulting shift is zero because there was nothing to move. `not_applied`: no reprice was applied; the arm's `reason` says why. - `input_tokens: number` The cumulative number of input tokens which were used. minimum: 0 - `iterations: array of BetaMessageIterationUsage or BetaCompactionIterationUsage or BetaAdvisorMessageIterationUsage or BetaFallbackMessageIterationUsage` Per-iteration token usage breakdown. Each entry represents one sampling iteration, with its own input/output token counts and cache statistics, discriminated by `type`. For `message` entries (model sampling iterations, such as the turns of a server-side tool use loop), this allows you to: - Calculate the context window size from the last `message` entry - Understand token accumulation across server-side tool use loops A `compaction` entry reports the token usage of the compaction operation itself — the server-side request that summarizes the context being closed — NOT the size of the context that was compacted away, and its token counts can be much smaller than that closed context (for example, a compaction that closes a ~200k-token context can report only a few thousand tokens). Do not derive the context window size from a `compaction` entry, even when it is the last entry. A `compaction` entry's tokens are not included in the top-level `usage` fields. When an input-token trigger is in effect (the default — 150,000 tokens unless configured otherwise), each `compaction` entry closes a context that had reached at least that threshold, though the context can exceed it by the final iteration's output and tool results. - `beta_message_iteration_usage: object` Token usage for a sampling iteration. - `beta_compaction_iteration_usage: object` Token usage for a compaction iteration. - `beta_advisor_message_iteration_usage: object` Token usage for an advisor sub-inference iteration. - `beta_fallback_message_iteration_usage: object` Token usage for the fallback-model attempt of a server-side fallback request. The terminal entry of a fallback-served turn: when a fallback hop's output is the returned message, the entry for the iteration that completed it carries this type in place of `message`. A declined hop and the serving hop's earlier tool-loop iterations produce `message` entries. Whether a fallback model served the response is signalled by the presence of this entry in `usage.iterations`. - `output_tokens: number` The cumulative number of output tokens which were used. - `output_tokens_details: object` Breakdown of output tokens by category. `output_tokens` remains the inclusive, authoritative total used for billing. This object provides a read-only decomposition for observability — for example, how many of the billed output tokens were spent on internal reasoning that may have been summarized before being returned to you. - `thinking_tokens: number` Number of output tokens the model generated as internal reasoning, including the thinking-block delimiter tokens. Reflects the raw reasoning the model produced, not the (possibly shorter) summarized thinking text returned in the response body. Computed by re-tokenizing the raw reasoning text, so it may differ from the model's exact generation count by a small number of tokens. Always ≤ `output_tokens`; `output_tokens - thinking_tokens` approximates the non-reasoning output. minimum: 0 - `server_tool_use: object` The number of server tool requests. - `web_fetch_requests: number` The number of web fetch tool requests. minimum: 0 - `web_search_requests: number` The number of web search tool requests. minimum: 0 - `input_transformations: optional array of BetaInputTransformation` Changes the API made to the request's input before showing it to the model, and blocks that failed a binding check but were left unchanged: one entry per block, in request order. Two entry types today. `thinking_dropped` — a `thinking`, `redacted_thinking` or `connector_text` block from the request's `messages` that was removed from the prompt instead of being shown to the model because it failed a binding check. `thinking_mismatch_allowed` — a `thinking` or `redacted_thinking` block that failed the conversation check (the conversation before it differs from the one it was created in, or it carries no record of one on a model that requires it) and was shown to the model all the same, because that check is not enforced for this request. More entry types may be added over time; ignore types you do not recognize. Requires `anthropic-beta: thinking-binding-controls-2026-08-01`. Present on every such response from a model that supports extended thinking, as `[]` when there is no entry to report; without the beta, blocks are removed or left in place all the same but nothing is reported. Removed blocks contribute nothing to `usage.input_tokens`; blocks left in place count as sent. When streaming, the array is final in `message_start`; the final `message_delta` event carries it only when a server-side model fallback happened mid-stream, in which case it holds the serving model's entries and replaces the one in `message_start`. - `beta_thinking_dropped_input_transformation: object` - `beta_thinking_mismatch_allowed_input_transformation: object` - `beta_raw_message_stop_event: object` - `type: "message_stop"` - `beta_raw_content_block_start_event: object` - `type: "content_block_start"` - `content_block: BetaTextBlock or BetaThinkingBlock or BetaRedactedThinkingBlock or 15 more` - `beta_text_block: object` - `type: "text"` - `citations: array of BetaTextCitation` Citations supporting the text block. The type of citation returned will depend on the type of document being cited. Citing a PDF results in `page_location`, plain text results in `char_location`, and content document results in `content_block_location`. - `text: string` - `beta_thinking_block: object` - `type: "thinking"` - `signature: string` A value used to verify that this thinking block was generated by Claude when it is passed back to the API. This is an opaque field and should not be interpreted or parsed. When passing thinking blocks back to the API (required when using tools with extended thinking), pass them back exactly as received, with this field intact. See [extended thinking](https://platform.claude.com/docs/en/build-with-claude/extended-thinking?sdk_languages=cli) for details. - `thinking: string` The text of Claude's thinking process for this block. - `beta_redacted_thinking_block: object` - `type: "redacted_thinking"` - `data: string` The contents of this redacted thinking block, returned when portions of the model's thinking were safety-redacted. This field is opaque and encrypted, with no readable content. Pass `redacted_thinking` blocks back to the API unchanged when continuing a multi-turn conversation. See [extended thinking](https://platform.claude.com/docs/en/build-with-claude/extended-thinking?sdk_languages=cli#redacted-thinking-blocks) for details. - `beta_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: map[unknown]` - `name: string` minLength: 1 - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` - `toolset_name: optional string` For a toolset member tool_use, the toolset family. minLength: 1, maxLength: 64, pattern: ^[a-zA-Z0-9_-]+$ - `beta_server_tool_use_block: object` - `type: "server_tool_use"` - `id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `input: map[unknown]` - `name: "advisor" or "web_search" or "web_fetch" or 5 more` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` - `beta_web_search_tool_result_block: object` - `type: "web_search_tool_result"` - `content: BetaWebSearchToolResultError or array of BetaWebSearchResultBlock` - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` - `beta_web_fetch_tool_result_block: object` - `type: "web_fetch_tool_result"` - `content: BetaWebFetchToolResultErrorBlock or BetaWebFetchBlock` - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` - `beta_advisor_tool_result_block: object` - `type: "advisor_tool_result"` - `content: BetaAdvisorToolResultError or BetaAdvisorResultBlock or BetaAdvisorRedactedResultBlock` - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `beta_code_execution_tool_result_block: object` - `type: "code_execution_tool_result"` - `content: BetaCodeExecutionToolResultError or BetaCodeExecutionResultBlock or BetaEncryptedCodeExecutionResultBlock` - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `beta_bash_code_execution_tool_result_block: object` - `type: "bash_code_execution_tool_result"` - `content: BetaBashCodeExecutionToolResultError or BetaBashCodeExecutionResultBlock` - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `beta_text_editor_code_execution_tool_result_block: object` - `type: "text_editor_code_execution_tool_result"` - `content: BetaTextEditorCodeExecutionToolResultError or BetaTextEditorCodeExecutionViewResultBlock or BetaTextEditorCodeExecutionCreateResultBlock or BetaTextEditorCodeExecutionStrReplaceResultBlock` - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `beta_tool_search_tool_result_block: object` - `type: "tool_search_tool_result"` - `content: BetaToolSearchToolResultError or BetaToolSearchToolSearchResultBlock` - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `beta_mcp_tool_use_block: object` - `type: "mcp_tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: map[unknown]` - `name: string` The name of the MCP tool - `server_name: string` The name of the MCP server - `beta_mcp_tool_result_block: object` - `type: "mcp_tool_result"` - `content: string or array of BetaTextBlock` - `is_error: boolean` - `tool_use_id: string` pattern: ^[a-zA-Z0-9_-]+$ - `beta_container_upload_block: object` Response model for a file uploaded to the container. - `type: "container_upload"` - `file_id: string` - `beta_compaction_block: object` A compaction block returned when autocompact is triggered. When content is None, it indicates the compaction failed to produce a valid summary (e.g., malformed output from the model). Clients may round-trip compaction blocks with null content; the server treats them as no-ops. - `type: "compaction"` - `content: string` Summary of compacted content, or null if compaction failed - `encrypted_content: string` Opaque metadata from prior compaction, to be round-tripped verbatim - `signature: optional string` Signature over the summary, to be sent back with the block verbatim - `tool_changes: optional array of BetaResponseToolAdditionBlock or BetaResponseToolRemovalBlock` The tool changes of the compacted range: the `tool_addition` and `tool_removal` blocks that take the request's `tools` to the tool set in effect at the end of the range, or `[]` when the range changed no tool. Absent when the server did not compute them. Send the block back unchanged. - `beta_fallback_block: object` Marks the point in `content` where one model's output gives way to the next. One block appears per hop where a preceding model actually ran this turn and declined. A turn where no preceding model ran and declined has no such boundary and carries no block — the signal for whether a fallback model served the response is the presence of a `fallback_message` entry in `usage.iterations`, not this block. The block is treated like a server-tool content block for streaming: it arrives via the standard `content_block_start` / `content_block_stop` pair and carries no deltas. - `type: "fallback"` - `from: object` The model whose output ends at this point — the model that declined at this hop. When the declining hop is the requested model, its `model` echoes the top-level `model` string the caller sent (alias or canonical); when the declining hop is a fallback model, its `model` is that model's canonical id. - `to: object` The fallback model producing the content that follows this block. Its `model` is always the canonical id. - `trigger: object` What caused the `from` model to hand over at this hop. - `beta_mcp_tool_listing_block: object` The tool listing the server fetched from an MCP server while producing this response. Send the assistant message back unchanged, this block included, so later requests use this listing instead of asking the MCP server again. - `type: "mcp_tool_listing"` - `mcp_server_name: string` - `tools: array of BetaMCPTool` - `index: number` - `beta_raw_content_block_delta_event: object` - `type: "content_block_delta"` - `delta: BetaTextDelta or BetaInputJSONDelta or BetaCitationsDelta or 3 more` - `beta_text_delta: object` - `type: "text_delta"` - `text: string` - `beta_input_json_delta: object` - `type: "input_json_delta"` - `partial_json: string` - `beta_citations_delta: object` - `type: "citations_delta"` - `citation: BetaCitationCharLocation or BetaCitationPageLocation or BetaCitationContentBlockLocation or 2 more` - `beta_citation_char_location: object` - `type: "char_location"` - `cited_text: string` - `document_index: number` minimum: 0 - `document_title: string` - `end_char_index: number` - `file_id: string` - `start_char_index: number` minimum: 0 - `beta_citation_page_location: object` - `type: "page_location"` - `cited_text: string` - `document_index: number` minimum: 0 - `document_title: string` - `end_page_number: number` - `file_id: string` - `start_page_number: number` minimum: 1 - `beta_citation_content_block_location: object` - `type: "content_block_location"` - `cited_text: string` The full text of the cited block range, concatenated. Always equals the contents of `content[start_block_index:end_block_index]` joined together. The text block is the minimal citable unit; this field is never a substring of a single block. Not counted toward output tokens, and not counted toward input tokens when sent back in subsequent turns. - `document_index: number` minimum: 0 - `document_title: string` - `end_block_index: number` Exclusive 0-based end index of the cited block range in the source's `content` array. Always greater than `start_block_index`; a single-block citation has `end_block_index = start_block_index + 1`. - `file_id: string` - `start_block_index: number` 0-based index of the first cited block in the source's `content` array. minimum: 0 - `beta_citations_web_search_result_location: object` - `type: "web_search_result_location"` - `cited_text: string` - `encrypted_index: string` - `title: string` maxLength: 512 - `url: string` - `beta_citation_search_result_location: object` - `type: "search_result_location"` - `cited_text: string` The full text of the cited block range, concatenated. Always equals the contents of `content[start_block_index:end_block_index]` joined together. The text block is the minimal citable unit; this field is never a substring of a single block. Not counted toward output tokens, and not counted toward input tokens when sent back in subsequent turns. - `end_block_index: number` Exclusive 0-based end index of the cited block range in the source's `content` array. Always greater than `start_block_index`; a single-block citation has `end_block_index = start_block_index + 1`. - `search_result_index: number` 0-based index of the cited search result among all `search_result` content blocks in the request, in the order they appear across messages and tool results. Counted separately from `document_index`; server-side web search results are not included in this count. minimum: 0 - `source: string` - `start_block_index: number` 0-based index of the first cited block in the source's `content` array. minimum: 0 - `title: string` - `beta_thinking_delta: object` - `type: "thinking_delta"` - `estimated_tokens: number` Per-frame increment of a coarse, running estimate of the tokens this thinking block has produced so far. Present whenever the `thinking-token-count-2026-05-13` beta is set; `null` unless `thinking.display` resolves to `"omitted"` and a count is due this frame. Sum the increments across `thinking_delta` frames on this block for a progress indicator. Each increment is a non-negative multiple of a fixed quantum and the cadence is rate-limited, so this is a deliberately lossy display hint, not a billable count; `usage.output_tokens` remains authoritative. - `thinking: string` The incremental `thinking` text for this content block. Concatenate the `thinking` values of successive `thinking_delta` events to assemble the block's full `thinking` value. - `beta_signature_delta: object` - `type: "signature_delta"` - `signature: string` The `signature` for this thinking block: an opaque value used to verify that the block was generated by Claude when it is passed back to the API. Delivered in a `signature_delta` event just before the block's `content_block_stop` event. - `beta_compaction_content_block_delta: object` - `type: "compaction_delta"` - `content: string` - `encrypted_content: string` Opaque metadata from prior compaction, to be round-tripped verbatim - `index: number` - `beta_raw_content_block_stop_event: object` - `type: "content_block_stop"` - `index: number` ### Example ```bash ant beta:messages create \ --api-key my-anthropic-api-key \ --max-tokens 1024 \ --message '{content: [{text: x, type: text}], role: user}' \ --model claude-opus-5-5 ``` #### Response (200) ```json { "id": "msg_013Zva2CMHLNnXjNJJKqJ2EF", "container": { "id": "container_011CpZohnwH4vuy7gazohgSP", "expires_at": "2019-12-27T18:11:19.117Z", "skills": [ { "skill_id": "pdf", "type": "anthropic", "version": "latest" } ] }, "content": [ { "citations": [ { "cited_text": "The grass is green. The sky is blue.", "document_index": 0, "document_title": "My Document", "end_char_index": 0, "file_id": "file_011CNha8iCJcU1wXNR6q4V8w", "start_char_index": 0, "type": "char_location" } ], "text": "Hi! My name is Claude.", "type": "text" } ], "context_management": { "applied_edits": [ { "cleared_input_tokens": 0, "cleared_tool_uses": 0, "type": "clear_tool_uses_20250919" } ] }, "diagnostics": { "cache_miss_reason": { "cache_missed_input_tokens": 0, "type": "model_changed" } }, "model": "claude-opus-5-5", "role": "assistant", "stop_details": { "category": "cyber", "explanation": "This request was declined because it conflicts with Anthropic's Usage Policy.", "fallback_credit_token": "QW50aHJvcGljL0NsYXVkZQ==", "fallback_has_prefill_claim": true, "recommended_model": "claude-opus-4-8", "type": "refusal" }, "stop_reason": "end_turn", "stop_sequence": null, "type": "message", "usage": { "cache_creation": { "ephemeral_1h_input_tokens": 0, "ephemeral_5m_input_tokens": 0 }, "cache_creation_input_tokens": 2051, "cache_read_input_tokens": 2051, "fallback_credit": { "status": { "type": "redeemed" } }, "inference_geo": "global", "input_tokens": 2095, "iterations": [ { "cache_creation": { "ephemeral_1h_input_tokens": 0, "ephemeral_5m_input_tokens": 0 }, "cache_creation_input_tokens": 0, "cache_read_input_tokens": 0, "input_tokens": 0, "model": "claude-haiku-5-5", "output_tokens": 0, "type": "message" } ], "output_tokens": 503, "output_tokens_details": { "thinking_tokens": 0 }, "server_tool_use": { "web_fetch_requests": 2, "web_search_requests": 0 }, "service_tier": "standard", "speed": "standard" }, "input_transformations": [ { "path": "path", "reason": "model_binding_mismatch", "type": "thinking_dropped" } ] } ``` ## Count tokens in a Message `$ ant beta:messages count-tokens` **POST** `/v1/messages/count_tokens` Count the number of tokens in a Message. The Token Count API can be used to count the number of tokens in a Message, including tools, images, and documents, without creating it. Learn more about token counting in our [user guide](https://platform.claude.com/docs/en/build-with-claude/token-counting?sdk_languages=cli) ### Parameters - `--message: array of BetaMessageParam` Input messages. Our models are trained to operate on alternating `user` and `assistant` conversational turns. When creating a new `Message`, you specify the prior conversational turns with the `messages` parameter, and the model then generates the next `Message` in the conversation. Consecutive `user` or `assistant` turns in your request will be combined into a single turn. Each input message must be an object with a `role` and `content`. You can specify a single `user`-role message, or you can include multiple `user` and `assistant` messages. If the final message uses the `assistant` role, the response content will continue immediately from the content in that message. This can be used to constrain part of the model's response. This is called prefill. On models that don't support prefill, creating a message that ends with a partial `assistant` response returns a 400 error. See [Prefill not supported](https://platform.claude.com/docs/en/api/errors?sdk_languages=cli#prefill-not-supported). Example with a single `user` message: ```json [{"role": "user", "content": "Hello, Claude"}] ``` Example with multiple conversational turns: ```json [ {"role": "user", "content": "Hello there."}, {"role": "assistant", "content": "Hi, I'm Claude. How can I help you?"}, {"role": "user", "content": "Can you explain LLMs in plain English?"}, ] ``` Example with a partially-filled response from Claude, for models that support prefill: ```json [ {"role": "user", "content": "What's the Greek name for Sun? (A) Sol (B) Helios (C) Sun"}, {"role": "assistant", "content": "The best answer is ("}, ] ``` Each input message `content` may be either a single `string` or an array of content blocks, where each block has a specific `type`. Using a `string` for `content` is shorthand for an array of one content block of type `"text"`. The following input messages are equivalent: ```json {"role": "user", "content": "Hello, Claude"} ``` ```json {"role": "user", "content": [{"type": "text", "text": "Hello, Claude"}]} ``` See [input examples](https://platform.claude.com/docs/en/build-with-claude/working-with-messages?sdk_languages=cli). Note that if you want to include a [system prompt](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/claude-prompting-best-practices?sdk_languages=cli#give-claude-a-role), you can use the top-level `system` parameter — there is no `"system"` role for input messages in the Messages API. There is a limit of 100,000 messages in a single request. - `--model: "claude-haiku-5-5" or "claude-sonnet-5-5" or "claude-fable-5-1" or 17 more or string` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `--cache-control: optional object` Top-level cache control automatically applies a cache_control marker to the last cacheable block in the request. - `--compaction: optional object` Compaction configuration. When set on `POST /v1/messages`, the request is a compaction request: the conversation in `messages` is summarized and the response holds only the resulting `compaction` block (`stop_reason` `"compaction"`), which later requests send first in `messages` in place of the messages it summarizes. `POST /v1/messages/count_tokens` accepts this parameter and ignores it: the count it returns is for the conversation in `messages` as sent. Cannot be combined with `context_management`. - `--context-management: optional object` Context management configuration. This allows you to control how Claude manages context across multiple requests, such as whether to clear function results or not. - `--mcp-server: optional array of BetaRequestMCPServerURLDefinition` MCP servers to be utilized in this request maxItems: 20 - `--output-config: optional object` Configuration options for the model's output, such as the output format. - `--output-format: optional object` Deprecated: Use `output_config.format` instead. See [structured outputs](https://platform.claude.com/docs/en/build-with-claude/structured-outputs?sdk_languages=cli) A schema to specify Claude's output format in responses. This parameter will be removed in a future release. - `--speed: optional "standard" or "fast"` The inference speed mode for this request. `"fast"` enables high output-tokens-per-second inference. Some models require the `fast-mode-2026-02-01` beta header for any `speed` value. See [fast mode](https://platform.claude.com/docs/en/build-with-claude/fast-mode?sdk_languages=cli) for which models. - `--system: optional string or array of BetaTextBlockParam` System prompt. A system prompt is a way of providing context and instructions to Claude, such as specifying a particular goal or role. See our [guide to system prompts](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/claude-prompting-best-practices?sdk_languages=cli#give-claude-a-role). - `--thinking: optional BetaThinkingConfigEnabled or BetaThinkingConfigDisabled or BetaThinkingConfigBetweenTools or BetaThinkingConfigAdaptive` Configuration for Claude's thinking. With `{"type": "adaptive"}`, Claude decides when and how much to think. With `{"type": "enabled"}` (manual extended thinking), you set a `budget_tokens` of at least 1,024. Thinking tokens count toward your `max_tokens` limit. Which `type` values are accepted, and what happens when you omit `thinking`, depend on the model. See [thinking](https://platform.claude.com/docs/en/build-with-claude/thinking?sdk_languages=cli#configuring-thinking) for each model's behavior. - `--tool-choice: optional BetaToolChoiceAuto or BetaToolChoiceAny or BetaToolChoiceTool or BetaToolChoiceNone` How the model should use the provided tools. The model can use a specific tool, any available tool, decide by itself, or not use tools at all. - `--tool: optional array of BetaTool or BetaToolBash20241022 or BetaToolBash20250124 or 25 more` Definitions of tools that the model may use. If you include `tools` in your API request, the model may return `tool_use` content blocks that represent the model's use of those tools. You can then run those tools using the tool input generated by the model and then optionally return results back to the model using `tool_result` content blocks. There are two types of tools: **client tools** and **server tools**. The behavior described below applies to client tools. For [server tools](https://platform.claude.com/docs/en/agents-and-tools/tool-use/server-tools?sdk_languages=cli), see their individual documentation as each has its own behavior (e.g., the [web search tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/web-search-tool?sdk_languages=cli)). Each tool definition includes: * `name`: Name of the tool. * `description`: Optional, but strongly-recommended description of the tool. * `input_schema`: [JSON schema](https://json-schema.org/draft/2020-12) for the tool `input` shape that the model will produce in `tool_use` output content blocks. For example, if you defined `tools` as: ```json [ { "name": "get_stock_price", "description": "Get the current stock price for a given ticker symbol.", "input_schema": { "type": "object", "properties": { "ticker": { "type": "string", "description": "The stock ticker symbol, e.g. AAPL for Apple Inc." } }, "required": ["ticker"] } } ] ``` And then asked the model "What's the S&P 500 at today?", the model might produce `tool_use` content blocks in the response like this: ```json [ { "type": "tool_use", "id": "toolu_01D7FLrfh4GYq7yT1ULFeyMV", "name": "get_stock_price", "input": { "ticker": "^GSPC" } } ] ``` You might then run your `get_stock_price` tool with `{"ticker": "^GSPC"}` as an input, and return the following back to the model in a subsequent `user` message: ```json [ { "type": "tool_result", "tool_use_id": "toolu_01D7FLrfh4GYq7yT1ULFeyMV", "content": "259.75 USD" } ] ``` Tools can be used for workflows that include running client-side tools and functions, or more generally whenever you want the model to produce a particular JSON structure of output. See our [guide](https://platform.claude.com/docs/en/agents-and-tools/tool-use/overview?sdk_languages=cli) for more details. - `--beta: optional array of AnthropicBeta` (header parameter) Optional header to specify the beta version(s) you want to use. - `--user-profile-id: optional string` (header parameter) The user profile ID to attribute this request to. Use when acting on behalf of a party other than your organization. Requires the `user-profiles` beta header. - `--workspace-id: optional string` (header parameter) Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`). Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace. ### Returns - `beta_message_tokens_count: object` - `context_management: object` Information about context management applied to the message. - `original_input_tokens: number` The original token count before context management was applied - `input_tokens: number` The total number of tokens across the provided list of messages, system prompt, and tools. ### Example ```bash ant beta:messages count-tokens \ --api-key my-anthropic-api-key \ --message '{content: [{text: x, type: text}], role: user}' \ --model claude-opus-5-5 ``` #### Response (200) ```json { "context_management": { "original_input_tokens": 0 }, "input_tokens": 2095 } ``` ## Domain types ### Beta Advisor Message Iteration Usage - `beta_advisor_message_iteration_usage: object` Token usage for an advisor sub-inference iteration. - `type: "advisor_message"` Usage for an advisor sub-inference iteration - `cache_creation: object` Breakdown of cached tokens by TTL - `ephemeral_1h_input_tokens: number` The number of input tokens used to create the 1 hour cache entry. minimum: 0 - `ephemeral_5m_input_tokens: number` The number of input tokens used to create the 5 minute cache entry. minimum: 0 - `cache_creation_input_tokens: number` The number of input tokens used to create the cache entry. minimum: 0 - `cache_read_input_tokens: number` The number of input tokens read from the cache. minimum: 0 - `input_tokens: number` The number of input tokens which were used. minimum: 0 - `model: "claude-haiku-5-5" or "claude-sonnet-5-5" or "claude-fable-5-1" or 17 more or string` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-haiku-5-5"` Fastest model for high-volume, real-time tasks - `"claude-sonnet-5-5"` Efficient model for coding and agents - `"claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows - `"claude-opus-5-5"` Powerful intelligence for coding, knowledge work, and long-running agents - `"claude-mythos-5-1"` Our most capable model for cybersecurity and biology research, available through trusted access programs - `"claude-sonnet-5"` Efficient model for coding and agents - `"claude-fable-5"` Next generation of intelligence for the hardest knowledge work and coding problems - `"claude-mythos-5"` Most capable model for cybersecurity and biology research - `"claude-opus-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-8"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-7"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-6"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-6"` Best combination of speed and intelligence - `"claude-haiku-4-5"` - `"claude-haiku-4-5-20251001"` - `"claude-opus-4-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-5-20251101"` Powerful intelligence for long-running agents and coding - `"claude-mythos-preview"` **Deprecated**: Will reach end-of-life on June 30, 2026. Please migrate to claude-mythos-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. New class of intelligence, strongest in coding and cybersecurity - `"claude-sonnet-4-5"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `"claude-sonnet-4-5-20250929"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `output_tokens: number` The number of output tokens which were used. minimum: 0 ### Beta Advisor Redacted Result Block - `beta_advisor_redacted_result_block: object` - `type: "advisor_redacted_result"` - `encrypted_content: string` Opaque blob containing the advisor's output. Round-trip verbatim; do not inspect or modify. - `stop_reason: string` The advisor sub-inference's stop reason (same values as the top-level message `stop_reason`). ### Beta Advisor Redacted Result Block Param - `beta_advisor_redacted_result_block_param: object` - `type: "advisor_redacted_result"` - `encrypted_content: string` Opaque blob produced by a prior response; must be round-tripped verbatim. - `stop_reason: optional string` ### Beta Advisor Result Block - `beta_advisor_result_block: object` - `type: "advisor_result"` - `stop_reason: string` The advisor sub-inference's stop reason (same values as the top-level message `stop_reason`). `max_tokens` indicates the advisor's output was truncated at the tool's `max_tokens` value or the advisor model's policy cap. - `text: string` ### Beta Advisor Result Block Param - `beta_advisor_result_block_param: object` - `type: "advisor_result"` - `text: string` - `stop_reason: optional string` ### Beta Advisor Tool 20260301 - `beta_advisor_tool_20260301: object` - `type: "advisor_20260301"` - `model: "claude-haiku-5-5" or "claude-sonnet-5-5" or "claude-fable-5-1" or 17 more or string` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-haiku-5-5"` Fastest model for high-volume, real-time tasks - `"claude-sonnet-5-5"` Efficient model for coding and agents - `"claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows - `"claude-opus-5-5"` Powerful intelligence for coding, knowledge work, and long-running agents - `"claude-mythos-5-1"` Our most capable model for cybersecurity and biology research, available through trusted access programs - `"claude-sonnet-5"` Efficient model for coding and agents - `"claude-fable-5"` Next generation of intelligence for the hardest knowledge work and coding problems - `"claude-mythos-5"` Most capable model for cybersecurity and biology research - `"claude-opus-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-8"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-7"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-6"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-6"` Best combination of speed and intelligence - `"claude-haiku-4-5"` - `"claude-haiku-4-5-20251001"` - `"claude-opus-4-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-5-20251101"` Powerful intelligence for long-running agents and coding - `"claude-mythos-preview"` **Deprecated**: Will reach end-of-life on June 30, 2026. Please migrate to claude-mythos-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. New class of intelligence, strongest in coding and cybersecurity - `"claude-sonnet-4-5"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `"claude-sonnet-4-5-20250929"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `name: "advisor"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `"5m"` - `"1h"` - `caching: optional object` Caching for the advisor's own prompt. When set, each advisor call writes a cache entry at the given TTL so subsequent calls in the same conversation read the stable prefix. When omitted, the advisor prompt is not cached. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_tokens: optional number` Bounds the advisor's total output (thinking + text) per call. When the advisor hits this cap, the returned advisor_result or advisor_redacted_result block carries stop_reason='max_tokens', and a truncation note is appended to the advice text the worker model sees (inside the encrypted blob in redacted mode). When set, the server also emits a remaining-tokens budget block in the advisor's prompt so the advisor self-shapes toward the cap. When omitted, the advisor model's default output cap applies and no budget block is emitted. minimum: 1024 - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs ### Beta Advisor Tool Result Block - `beta_advisor_tool_result_block: object` - `type: "advisor_tool_result"` - `content: BetaAdvisorToolResultError or BetaAdvisorResultBlock or BetaAdvisorRedactedResultBlock` - `beta_advisor_tool_result_error: object` - `type: "advisor_tool_result_error"` - `error_code: "max_uses_exceeded" or "prompt_too_long" or "too_many_requests" or 4 more` - `"max_uses_exceeded"` - `"prompt_too_long"` - `"too_many_requests"` - `"overloaded"` - `"unavailable"` - `"execution_time_exceeded"` - `"model_not_found"` - `beta_advisor_result_block: object` - `type: "advisor_result"` - `stop_reason: string` The advisor sub-inference's stop reason (same values as the top-level message `stop_reason`). `max_tokens` indicates the advisor's output was truncated at the tool's `max_tokens` value or the advisor model's policy cap. - `text: string` - `beta_advisor_redacted_result_block: object` - `type: "advisor_redacted_result"` - `encrypted_content: string` Opaque blob containing the advisor's output. Round-trip verbatim; do not inspect or modify. - `stop_reason: string` The advisor sub-inference's stop reason (same values as the top-level message `stop_reason`). - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ ### Beta Advisor Tool Result Block Param - `beta_advisor_tool_result_block_param: object` - `type: "advisor_tool_result"` - `content: BetaAdvisorToolResultErrorParam or BetaAdvisorResultBlockParam or BetaAdvisorRedactedResultBlockParam` - `beta_advisor_tool_result_error_param: object` - `type: "advisor_tool_result_error"` - `error_code: "max_uses_exceeded" or "prompt_too_long" or "too_many_requests" or 4 more` - `"max_uses_exceeded"` - `"prompt_too_long"` - `"too_many_requests"` - `"overloaded"` - `"unavailable"` - `"execution_time_exceeded"` - `"model_not_found"` - `beta_advisor_result_block_param: object` - `type: "advisor_result"` - `text: string` - `stop_reason: optional string` - `beta_advisor_redacted_result_block_param: object` - `type: "advisor_redacted_result"` - `encrypted_content: string` Opaque blob produced by a prior response; must be round-tripped verbatim. - `stop_reason: optional string` - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `"5m"` - `"1h"` ### Beta Advisor Tool Result Error - `beta_advisor_tool_result_error: object` - `type: "advisor_tool_result_error"` - `error_code: "max_uses_exceeded" or "prompt_too_long" or "too_many_requests" or 4 more` - `"max_uses_exceeded"` - `"prompt_too_long"` - `"too_many_requests"` - `"overloaded"` - `"unavailable"` - `"execution_time_exceeded"` - `"model_not_found"` ### Beta Advisor Tool Result Error Param - `beta_advisor_tool_result_error_param: object` - `type: "advisor_tool_result_error"` - `error_code: "max_uses_exceeded" or "prompt_too_long" or "too_many_requests" or 4 more` - `"max_uses_exceeded"` - `"prompt_too_long"` - `"too_many_requests"` - `"overloaded"` - `"unavailable"` - `"execution_time_exceeded"` - `"model_not_found"` ### Beta All Thinking Turns - `beta_all_thinking_turns: object` - `type: "all"` ### Beta Base64 Image Source - `beta_base64_image_source: object` - `type: "base64"` - `data: string` format: byte - `media_type: "image/jpeg" or "image/png" or "image/gif" or "image/webp"` - `"image/jpeg"` - `"image/png"` - `"image/gif"` - `"image/webp"` ### Beta Base64 PDF Source - `beta_base64_pdf_source: object` - `type: "base64"` - `data: string` format: byte - `media_type: "application/pdf"` ### Beta Bash Code Execution Output Block - `beta_bash_code_execution_output_block: object` - `type: "bash_code_execution_output"` - `file_id: string` ### Beta Bash Code Execution Output Block Param - `beta_bash_code_execution_output_block_param: object` - `type: "bash_code_execution_output"` - `file_id: string` ### Beta Bash Code Execution Result Block - `beta_bash_code_execution_result_block: object` - `type: "bash_code_execution_result"` - `content: array of BetaBashCodeExecutionOutputBlock` - `type: "bash_code_execution_output"` - `file_id: string` - `return_code: number` - `stderr: string` - `stdout: string` ### Beta Bash Code Execution Result Block Param - `beta_bash_code_execution_result_block_param: object` - `type: "bash_code_execution_result"` - `content: array of BetaBashCodeExecutionOutputBlockParam` - `type: "bash_code_execution_output"` - `file_id: string` - `return_code: number` - `stderr: string` - `stdout: string` ### Beta Bash Code Execution Tool Result Block - `beta_bash_code_execution_tool_result_block: object` - `type: "bash_code_execution_tool_result"` - `content: BetaBashCodeExecutionToolResultError or BetaBashCodeExecutionResultBlock` - `beta_bash_code_execution_tool_result_error: object` - `type: "bash_code_execution_tool_result_error"` - `error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or 2 more` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `"output_file_too_large"` - `beta_bash_code_execution_result_block: object` - `type: "bash_code_execution_result"` - `content: array of BetaBashCodeExecutionOutputBlock` - `type: "bash_code_execution_output"` - `file_id: string` - `return_code: number` - `stderr: string` - `stdout: string` - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ ### Beta Bash Code Execution Tool Result Block Param - `beta_bash_code_execution_tool_result_block_param: object` - `type: "bash_code_execution_tool_result"` - `content: BetaBashCodeExecutionToolResultErrorParam or BetaBashCodeExecutionResultBlockParam` - `beta_bash_code_execution_tool_result_error_param: object` - `type: "bash_code_execution_tool_result_error"` - `error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or 2 more` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `"output_file_too_large"` - `beta_bash_code_execution_result_block_param: object` - `type: "bash_code_execution_result"` - `content: array of BetaBashCodeExecutionOutputBlockParam` - `type: "bash_code_execution_output"` - `file_id: string` - `return_code: number` - `stderr: string` - `stdout: string` - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `"5m"` - `"1h"` ### Beta Bash Code Execution Tool Result Error - `beta_bash_code_execution_tool_result_error: object` - `type: "bash_code_execution_tool_result_error"` - `error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or 2 more` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `"output_file_too_large"` ### Beta Bash Code Execution Tool Result Error Param - `beta_bash_code_execution_tool_result_error_param: object` - `type: "bash_code_execution_tool_result_error"` - `error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or 2 more` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `"output_file_too_large"` ### Beta Browser Click Target - `beta_browser_click_target: BetaBrowserCoordinateTarget or BetaBrowserRefTarget` Where to act: either a viewport coordinate or an element reference. - `beta_browser_coordinate_target: object` A point in the browser viewport, in viewport pixels (the same frame as a full-viewport screenshot). - `type: "coordinate"` - `x: number` Pixels from the left edge of the viewport. minimum: 0 - `y: number` Pixels from the top edge of the viewport. minimum: 0 - `beta_browser_ref_target: object` An element on the page, identified by a reference from a prior `read_page` or `find` result. References are scoped to the tab that produced them and become stale after navigation or a major re-render. - `type: "ref"` - `ref: string` An element reference (e.g. "ref_7") returned by a prior `read_page` or `find` result. ### Beta Browser Close Tab Config - `beta_browser_close_tab_config: object` `close_tab`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. ### Beta Browser Close Tab Input - `beta_browser_close_tab_input: object` Close the tab with the given tab_id. - `tab_id: string` The tab to close. ### Beta Browser Close Tab Tool Use Block - `beta_browser_close_tab_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Close the tab with the given tab_id. - `tab_id: string` The tab to close. - `name: "close_tab"` - `toolset_name: "browser"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `type: "direct"` - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `type: "code_execution_20250825"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `beta_server_tool_caller_20260120: object` - `type: "code_execution_20260120"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ ### Beta Browser Coordinate Target - `beta_browser_coordinate_target: object` A point in the browser viewport, in viewport pixels (the same frame as a full-viewport screenshot). - `type: "coordinate"` - `x: number` Pixels from the left edge of the viewport. minimum: 0 - `y: number` Pixels from the top edge of the viewport. minimum: 0 ### Beta Browser Double Click Config - `beta_browser_double_click_config: object` `double_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. ### Beta Browser Double Click Input - `beta_browser_double_click_input: object` Double left-click at a viewport coordinate or on an element by reference. - `target: BetaBrowserCoordinateTarget or BetaBrowserRefTarget` Where to act: either a viewport coordinate or an element reference. - `beta_browser_coordinate_target: object` A point in the browser viewport, in viewport pixels (the same frame as a full-viewport screenshot). - `type: "coordinate"` - `x: number` Pixels from the left edge of the viewport. minimum: 0 - `y: number` Pixels from the top edge of the viewport. minimum: 0 - `beta_browser_ref_target: object` An element on the page, identified by a reference from a prior `read_page` or `find` result. References are scoped to the tab that produced them and become stale after navigation or a major re-render. - `type: "ref"` - `ref: string` An element reference (e.g. "ref_7") returned by a prior `read_page` or `find` result. - `modifiers: optional string` Optional modifier key chord to hold for the duration of this action (e.g. "shift", "ctrl+shift", "cmd+alt"). - `tab_id: optional string` Tab to act on. Defaults to the active tab when omitted. ### Beta Browser Double Click Tool Use Block - `beta_browser_double_click_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Double left-click at a viewport coordinate or on an element by reference. - `target: BetaBrowserCoordinateTarget or BetaBrowserRefTarget` Where to act: either a viewport coordinate or an element reference. - `beta_browser_coordinate_target: object` A point in the browser viewport, in viewport pixels (the same frame as a full-viewport screenshot). - `type: "coordinate"` - `x: number` Pixels from the left edge of the viewport. minimum: 0 - `y: number` Pixels from the top edge of the viewport. minimum: 0 - `beta_browser_ref_target: object` An element on the page, identified by a reference from a prior `read_page` or `find` result. References are scoped to the tab that produced them and become stale after navigation or a major re-render. - `type: "ref"` - `ref: string` An element reference (e.g. "ref_7") returned by a prior `read_page` or `find` result. - `modifiers: optional string` Optional modifier key chord to hold for the duration of this action (e.g. "shift", "ctrl+shift", "cmd+alt"). - `tab_id: optional string` Tab to act on. Defaults to the active tab when omitted. - `name: "double_click"` - `toolset_name: "browser"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `type: "direct"` - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `type: "code_execution_20250825"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `beta_server_tool_caller_20260120: object` - `type: "code_execution_20260120"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ ### Beta Browser File Upload Config - `beta_browser_file_upload_config: object` `file_upload`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. ### Beta Browser File Upload Input - `beta_browser_file_upload_input: object` Set the value of a file-input element to one or more files. The target must be an element reference; at least one of paths or document_ids is required. - `target: object` An element on the page, identified by a reference from a prior `read_page` or `find` result. References are scoped to the tab that produced them and become stale after navigation or a major re-render. - `type: "ref"` - `ref: string` An element reference (e.g. "ref_7") returned by a prior `read_page` or `find` result. - `document_ids: optional array of string` References to files the harness has staged, for deployments where the browser executor cannot read the caller's filesystem. minItems: 1 - `paths: optional array of string` File paths on the browser executor's filesystem. minItems: 1 - `tab_id: optional string` Tab to act on. Defaults to the active tab when omitted. ### Beta Browser File Upload Tool Use Block - `beta_browser_file_upload_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Set the value of a file-input element to one or more files. The target must be an element reference; at least one of paths or document_ids is required. - `target: object` An element on the page, identified by a reference from a prior `read_page` or `find` result. References are scoped to the tab that produced them and become stale after navigation or a major re-render. - `type: "ref"` - `ref: string` An element reference (e.g. "ref_7") returned by a prior `read_page` or `find` result. - `document_ids: optional array of string` References to files the harness has staged, for deployments where the browser executor cannot read the caller's filesystem. minItems: 1 - `paths: optional array of string` File paths on the browser executor's filesystem. minItems: 1 - `tab_id: optional string` Tab to act on. Defaults to the active tab when omitted. - `name: "file_upload"` - `toolset_name: "browser"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `type: "direct"` - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `type: "code_execution_20250825"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `beta_server_tool_caller_20260120: object` - `type: "code_execution_20260120"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ ### Beta Browser Find Config - `beta_browser_find_config: object` `find`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. ### Beta Browser Find Input - `beta_browser_find_input: object` Find elements matching a natural-language description (e.g. "search bar", "add to cart button") and return up to 20 matches with element references. - `query: string` Natural-language description of the element(s) to find. - `tab_id: optional string` Tab to act on. Defaults to the active tab when omitted. ### Beta Browser Find Tool Use Block - `beta_browser_find_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Find elements matching a natural-language description (e.g. "search bar", "add to cart button") and return up to 20 matches with element references. - `query: string` Natural-language description of the element(s) to find. - `tab_id: optional string` Tab to act on. Defaults to the active tab when omitted. - `name: "find"` - `toolset_name: "browser"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `type: "direct"` - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `type: "code_execution_20250825"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `beta_server_tool_caller_20260120: object` - `type: "code_execution_20260120"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ ### Beta Browser Form Input Config - `beta_browser_form_input_config: object` `form_input`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. ### Beta Browser Form Input Input - `beta_browser_form_input_input: object` Set the value of a form element (input, textarea, select, checkbox). Use a boolean for checkboxes, an option value or text for selects. - `target: object` An element on the page, identified by a reference from a prior `read_page` or `find` result. References are scoped to the tab that produced them and become stale after navigation or a major re-render. - `type: "ref"` - `ref: string` An element reference (e.g. "ref_7") returned by a prior `read_page` or `find` result. - `value: string or number or boolean` The value to set. - `union_member_0: string` - `union_member_1: number` - `union_member_2: boolean` - `tab_id: optional string` Tab to act on. Defaults to the active tab when omitted. ### Beta Browser Form Input Tool Use Block - `beta_browser_form_input_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Set the value of a form element (input, textarea, select, checkbox). Use a boolean for checkboxes, an option value or text for selects. - `target: object` An element on the page, identified by a reference from a prior `read_page` or `find` result. References are scoped to the tab that produced them and become stale after navigation or a major re-render. - `type: "ref"` - `ref: string` An element reference (e.g. "ref_7") returned by a prior `read_page` or `find` result. - `value: string or number or boolean` The value to set. - `union_member_0: string` - `union_member_1: number` - `union_member_2: boolean` - `tab_id: optional string` Tab to act on. Defaults to the active tab when omitted. - `name: "form_input"` - `toolset_name: "browser"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `type: "direct"` - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `type: "code_execution_20250825"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `beta_server_tool_caller_20260120: object` - `type: "code_execution_20260120"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ ### Beta Browser Form Input Value - `beta_browser_form_input_value: string or number or boolean` - `union_member_0: string` - `union_member_1: number` - `union_member_2: boolean` ### Beta Browser Get Page Text Config - `beta_browser_get_page_text_config: object` `get_page_text`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. ### Beta Browser Get Page Text Input - `beta_browser_get_page_text_input: object` Return the page's visible text content as plain text, prioritizing article content. Suited to articles, documentation, and other text-heavy pages. - `tab_id: optional string` Tab to act on. Defaults to the active tab when omitted. ### Beta Browser Get Page Text Tool Use Block - `beta_browser_get_page_text_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Return the page's visible text content as plain text, prioritizing article content. Suited to articles, documentation, and other text-heavy pages. - `tab_id: optional string` Tab to act on. Defaults to the active tab when omitted. - `name: "get_page_text"` - `toolset_name: "browser"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `type: "direct"` - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `type: "code_execution_20250825"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `beta_server_tool_caller_20260120: object` - `type: "code_execution_20260120"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ ### Beta Browser Hold Key Config - `beta_browser_hold_key_config: object` `hold_key`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. ### Beta Browser Hold Key Input - `beta_browser_hold_key_input: object` Hold a key or key chord down for a duration, then release it. Uses the same key names and "+" chord syntax as the key action. - `duration: number` Seconds to hold the key down (maximum 30). minimum: 0, maximum: 30 - `text: string` The key or chord to hold. - `tab_id: optional string` Tab to act on. Defaults to the active tab when omitted. ### Beta Browser Hold Key Tool Use Block - `beta_browser_hold_key_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Hold a key or key chord down for a duration, then release it. Uses the same key names and "+" chord syntax as the key action. - `duration: number` Seconds to hold the key down (maximum 30). minimum: 0, maximum: 30 - `text: string` The key or chord to hold. - `tab_id: optional string` Tab to act on. Defaults to the active tab when omitted. - `name: "hold_key"` - `toolset_name: "browser"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `type: "direct"` - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `type: "code_execution_20250825"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `beta_server_tool_caller_20260120: object` - `type: "code_execution_20260120"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ ### Beta Browser Hover Config - `beta_browser_hover_config: object` `hover`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. ### Beta Browser Hover Input - `beta_browser_hover_input: object` Move the cursor to a coordinate or element without clicking. - `target: BetaBrowserCoordinateTarget or BetaBrowserRefTarget` Where to act: either a viewport coordinate or an element reference. - `beta_browser_coordinate_target: object` A point in the browser viewport, in viewport pixels (the same frame as a full-viewport screenshot). - `type: "coordinate"` - `x: number` Pixels from the left edge of the viewport. minimum: 0 - `y: number` Pixels from the top edge of the viewport. minimum: 0 - `beta_browser_ref_target: object` An element on the page, identified by a reference from a prior `read_page` or `find` result. References are scoped to the tab that produced them and become stale after navigation or a major re-render. - `type: "ref"` - `ref: string` An element reference (e.g. "ref_7") returned by a prior `read_page` or `find` result. - `tab_id: optional string` Tab to act on. Defaults to the active tab when omitted. ### Beta Browser Hover Tool Use Block - `beta_browser_hover_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Move the cursor to a coordinate or element without clicking. - `target: BetaBrowserCoordinateTarget or BetaBrowserRefTarget` Where to act: either a viewport coordinate or an element reference. - `beta_browser_coordinate_target: object` A point in the browser viewport, in viewport pixels (the same frame as a full-viewport screenshot). - `type: "coordinate"` - `x: number` Pixels from the left edge of the viewport. minimum: 0 - `y: number` Pixels from the top edge of the viewport. minimum: 0 - `beta_browser_ref_target: object` An element on the page, identified by a reference from a prior `read_page` or `find` result. References are scoped to the tab that produced them and become stale after navigation or a major re-render. - `type: "ref"` - `ref: string` An element reference (e.g. "ref_7") returned by a prior `read_page` or `find` result. - `tab_id: optional string` Tab to act on. Defaults to the active tab when omitted. - `name: "hover"` - `toolset_name: "browser"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `type: "direct"` - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `type: "code_execution_20250825"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `beta_server_tool_caller_20260120: object` - `type: "code_execution_20260120"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ ### Beta Browser Javascript Exec Config - `beta_browser_javascript_exec_config: object` `javascript_exec`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. ### Beta Browser Javascript Exec Input - `beta_browser_javascript_exec_input: object` Execute JavaScript in the page context and return the value of the last expression. The code runs with access to the DOM, `window`, and page variables. Write the expression you want evaluated — do NOT use `return`. - `text: string` JavaScript to execute in the page context. - `tab_id: optional string` Tab to act on. Defaults to the active tab when omitted. ### Beta Browser Javascript Exec Tool Use Block - `beta_browser_javascript_exec_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Execute JavaScript in the page context and return the value of the last expression. The code runs with access to the DOM, `window`, and page variables. Write the expression you want evaluated — do NOT use `return`. - `text: string` JavaScript to execute in the page context. - `tab_id: optional string` Tab to act on. Defaults to the active tab when omitted. - `name: "javascript_exec"` - `toolset_name: "browser"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `type: "direct"` - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `type: "code_execution_20250825"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `beta_server_tool_caller_20260120: object` - `type: "code_execution_20260120"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ ### Beta Browser Key Config - `beta_browser_key_config: object` `key`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. ### Beta Browser Key Input - `beta_browser_key_input: object` Press a key or key chord. Use "+" to combine modifiers with a key (e.g. "ctrl+a", "cmd+shift+p") and space to sequence presses (e.g. "Backspace Backspace Delete"). Common names like "Return", "Tab", "Escape", "BackSpace" are supported. - `text: string` The key, chord, or space-separated sequence to press. - `repeat: optional number` Number of times to repeat. Default 1. minimum: 1, maximum: 100 - `tab_id: optional string` Tab to act on. Defaults to the active tab when omitted. ### Beta Browser Key Tool Use Block - `beta_browser_key_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Press a key or key chord. Use "+" to combine modifiers with a key (e.g. "ctrl+a", "cmd+shift+p") and space to sequence presses (e.g. "Backspace Backspace Delete"). Common names like "Return", "Tab", "Escape", "BackSpace" are supported. - `text: string` The key, chord, or space-separated sequence to press. - `repeat: optional number` Number of times to repeat. Default 1. minimum: 1, maximum: 100 - `tab_id: optional string` Tab to act on. Defaults to the active tab when omitted. - `name: "key"` - `toolset_name: "browser"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `type: "direct"` - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `type: "code_execution_20250825"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `beta_server_tool_caller_20260120: object` - `type: "code_execution_20260120"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ ### Beta Browser Left Click Config - `beta_browser_left_click_config: object` `left_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. ### Beta Browser Left Click Drag Config - `beta_browser_left_click_drag_config: object` `left_click_drag`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. ### Beta Browser Left Click Drag Input - `beta_browser_left_click_drag_input: object` Press at `from`, drag to `target`, release. Both must be coordinate targets. - `from: object` A point in the browser viewport, in viewport pixels (the same frame as a full-viewport screenshot). - `type: "coordinate"` - `x: number` Pixels from the left edge of the viewport. minimum: 0 - `y: number` Pixels from the top edge of the viewport. minimum: 0 - `target: object` A point in the browser viewport, in viewport pixels (the same frame as a full-viewport screenshot). - `type: "coordinate"` - `x: number` Pixels from the left edge of the viewport. minimum: 0 - `y: number` Pixels from the top edge of the viewport. minimum: 0 - `tab_id: optional string` Tab to act on. Defaults to the active tab when omitted. ### Beta Browser Left Click Drag Tool Use Block - `beta_browser_left_click_drag_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Press at `from`, drag to `target`, release. Both must be coordinate targets. - `from: object` A point in the browser viewport, in viewport pixels (the same frame as a full-viewport screenshot). - `type: "coordinate"` - `x: number` Pixels from the left edge of the viewport. minimum: 0 - `y: number` Pixels from the top edge of the viewport. minimum: 0 - `target: object` A point in the browser viewport, in viewport pixels (the same frame as a full-viewport screenshot). - `type: "coordinate"` - `x: number` Pixels from the left edge of the viewport. minimum: 0 - `y: number` Pixels from the top edge of the viewport. minimum: 0 - `tab_id: optional string` Tab to act on. Defaults to the active tab when omitted. - `name: "left_click_drag"` - `toolset_name: "browser"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `type: "direct"` - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `type: "code_execution_20250825"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `beta_server_tool_caller_20260120: object` - `type: "code_execution_20260120"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ ### Beta Browser Left Click Input - `beta_browser_left_click_input: object` Left-click at a viewport coordinate or on an element by reference. - `target: BetaBrowserCoordinateTarget or BetaBrowserRefTarget` Where to act: either a viewport coordinate or an element reference. - `beta_browser_coordinate_target: object` A point in the browser viewport, in viewport pixels (the same frame as a full-viewport screenshot). - `type: "coordinate"` - `x: number` Pixels from the left edge of the viewport. minimum: 0 - `y: number` Pixels from the top edge of the viewport. minimum: 0 - `beta_browser_ref_target: object` An element on the page, identified by a reference from a prior `read_page` or `find` result. References are scoped to the tab that produced them and become stale after navigation or a major re-render. - `type: "ref"` - `ref: string` An element reference (e.g. "ref_7") returned by a prior `read_page` or `find` result. - `modifiers: optional string` Optional modifier key chord to hold for the duration of this action (e.g. "shift", "ctrl+shift", "cmd+alt"). - `tab_id: optional string` Tab to act on. Defaults to the active tab when omitted. ### Beta Browser Left Click Tool Use Block - `beta_browser_left_click_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Left-click at a viewport coordinate or on an element by reference. - `target: BetaBrowserCoordinateTarget or BetaBrowserRefTarget` Where to act: either a viewport coordinate or an element reference. - `beta_browser_coordinate_target: object` A point in the browser viewport, in viewport pixels (the same frame as a full-viewport screenshot). - `type: "coordinate"` - `x: number` Pixels from the left edge of the viewport. minimum: 0 - `y: number` Pixels from the top edge of the viewport. minimum: 0 - `beta_browser_ref_target: object` An element on the page, identified by a reference from a prior `read_page` or `find` result. References are scoped to the tab that produced them and become stale after navigation or a major re-render. - `type: "ref"` - `ref: string` An element reference (e.g. "ref_7") returned by a prior `read_page` or `find` result. - `modifiers: optional string` Optional modifier key chord to hold for the duration of this action (e.g. "shift", "ctrl+shift", "cmd+alt"). - `tab_id: optional string` Tab to act on. Defaults to the active tab when omitted. - `name: "left_click"` - `toolset_name: "browser"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `type: "direct"` - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `type: "code_execution_20250825"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `beta_server_tool_caller_20260120: object` - `type: "code_execution_20260120"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ ### Beta Browser Left Mouse Down Config - `beta_browser_left_mouse_down_config: object` `left_mouse_down`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. ### Beta Browser Left Mouse Down Input - `beta_browser_left_mouse_down_input: object` Press and hold the left mouse button at a viewport coordinate. Pair with left_mouse_up to perform a custom drag. - `target: object` A point in the browser viewport, in viewport pixels (the same frame as a full-viewport screenshot). - `type: "coordinate"` - `x: number` Pixels from the left edge of the viewport. minimum: 0 - `y: number` Pixels from the top edge of the viewport. minimum: 0 - `tab_id: optional string` Tab to act on. Defaults to the active tab when omitted. ### Beta Browser Left Mouse Down Tool Use Block - `beta_browser_left_mouse_down_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Press and hold the left mouse button at a viewport coordinate. Pair with left_mouse_up to perform a custom drag. - `target: object` A point in the browser viewport, in viewport pixels (the same frame as a full-viewport screenshot). - `type: "coordinate"` - `x: number` Pixels from the left edge of the viewport. minimum: 0 - `y: number` Pixels from the top edge of the viewport. minimum: 0 - `tab_id: optional string` Tab to act on. Defaults to the active tab when omitted. - `name: "left_mouse_down"` - `toolset_name: "browser"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `type: "direct"` - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `type: "code_execution_20250825"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `beta_server_tool_caller_20260120: object` - `type: "code_execution_20260120"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ ### Beta Browser Left Mouse Up Config - `beta_browser_left_mouse_up_config: object` `left_mouse_up`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. ### Beta Browser Left Mouse Up Input - `beta_browser_left_mouse_up_input: object` Release the left mouse button at a viewport coordinate. - `target: object` A point in the browser viewport, in viewport pixels (the same frame as a full-viewport screenshot). - `type: "coordinate"` - `x: number` Pixels from the left edge of the viewport. minimum: 0 - `y: number` Pixels from the top edge of the viewport. minimum: 0 - `tab_id: optional string` Tab to act on. Defaults to the active tab when omitted. ### Beta Browser Left Mouse Up Tool Use Block - `beta_browser_left_mouse_up_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Release the left mouse button at a viewport coordinate. - `target: object` A point in the browser viewport, in viewport pixels (the same frame as a full-viewport screenshot). - `type: "coordinate"` - `x: number` Pixels from the left edge of the viewport. minimum: 0 - `y: number` Pixels from the top edge of the viewport. minimum: 0 - `tab_id: optional string` Tab to act on. Defaults to the active tab when omitted. - `name: "left_mouse_up"` - `toolset_name: "browser"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `type: "direct"` - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `type: "code_execution_20250825"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `beta_server_tool_caller_20260120: object` - `type: "code_execution_20260120"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ ### Beta Browser List Tabs Config - `beta_browser_list_tabs_config: object` `list_tabs`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. ### Beta Browser List Tabs Input - `beta_browser_list_tabs_input: object` List all open tabs with each tab's tab_id, title, and URL. ### Beta Browser List Tabs Tool Use Block - `beta_browser_list_tabs_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` List all open tabs with each tab's tab_id, title, and URL. - `name: "list_tabs"` - `toolset_name: "browser"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `type: "direct"` - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `type: "code_execution_20250825"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `beta_server_tool_caller_20260120: object` - `type: "code_execution_20260120"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ ### Beta Browser Middle Click Config - `beta_browser_middle_click_config: object` `middle_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. ### Beta Browser Middle Click Input - `beta_browser_middle_click_input: object` Middle-click at a viewport coordinate or on an element by reference. - `target: BetaBrowserCoordinateTarget or BetaBrowserRefTarget` Where to act: either a viewport coordinate or an element reference. - `beta_browser_coordinate_target: object` A point in the browser viewport, in viewport pixels (the same frame as a full-viewport screenshot). - `type: "coordinate"` - `x: number` Pixels from the left edge of the viewport. minimum: 0 - `y: number` Pixels from the top edge of the viewport. minimum: 0 - `beta_browser_ref_target: object` An element on the page, identified by a reference from a prior `read_page` or `find` result. References are scoped to the tab that produced them and become stale after navigation or a major re-render. - `type: "ref"` - `ref: string` An element reference (e.g. "ref_7") returned by a prior `read_page` or `find` result. - `modifiers: optional string` Optional modifier key chord to hold for the duration of this action (e.g. "shift", "ctrl+shift", "cmd+alt"). - `tab_id: optional string` Tab to act on. Defaults to the active tab when omitted. ### Beta Browser Middle Click Tool Use Block - `beta_browser_middle_click_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Middle-click at a viewport coordinate or on an element by reference. - `target: BetaBrowserCoordinateTarget or BetaBrowserRefTarget` Where to act: either a viewport coordinate or an element reference. - `beta_browser_coordinate_target: object` A point in the browser viewport, in viewport pixels (the same frame as a full-viewport screenshot). - `type: "coordinate"` - `x: number` Pixels from the left edge of the viewport. minimum: 0 - `y: number` Pixels from the top edge of the viewport. minimum: 0 - `beta_browser_ref_target: object` An element on the page, identified by a reference from a prior `read_page` or `find` result. References are scoped to the tab that produced them and become stale after navigation or a major re-render. - `type: "ref"` - `ref: string` An element reference (e.g. "ref_7") returned by a prior `read_page` or `find` result. - `modifiers: optional string` Optional modifier key chord to hold for the duration of this action (e.g. "shift", "ctrl+shift", "cmd+alt"). - `tab_id: optional string` Tab to act on. Defaults to the active tab when omitted. - `name: "middle_click"` - `toolset_name: "browser"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `type: "direct"` - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `type: "code_execution_20250825"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `beta_server_tool_caller_20260120: object` - `type: "code_execution_20260120"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ ### Beta Browser Mouse Move Config - `beta_browser_mouse_move_config: object` `mouse_move`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. ### Beta Browser Mouse Move Input - `beta_browser_mouse_move_input: object` Move the pointer to a viewport coordinate without clicking. - `target: object` A point in the browser viewport, in viewport pixels (the same frame as a full-viewport screenshot). - `type: "coordinate"` - `x: number` Pixels from the left edge of the viewport. minimum: 0 - `y: number` Pixels from the top edge of the viewport. minimum: 0 - `tab_id: optional string` Tab to act on. Defaults to the active tab when omitted. ### Beta Browser Mouse Move Tool Use Block - `beta_browser_mouse_move_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Move the pointer to a viewport coordinate without clicking. - `target: object` A point in the browser viewport, in viewport pixels (the same frame as a full-viewport screenshot). - `type: "coordinate"` - `x: number` Pixels from the left edge of the viewport. minimum: 0 - `y: number` Pixels from the top edge of the viewport. minimum: 0 - `tab_id: optional string` Tab to act on. Defaults to the active tab when omitted. - `name: "mouse_move"` - `toolset_name: "browser"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `type: "direct"` - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `type: "code_execution_20250825"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `beta_server_tool_caller_20260120: object` - `type: "code_execution_20260120"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ ### Beta Browser Navigate Config - `beta_browser_navigate_config: object` `navigate`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. ### Beta Browser Navigate Input - `beta_browser_navigate_input: object` Navigate to a URL, or go back/forward/reload in history. The protocol may be omitted (defaults to https://). - `url: string` The URL to navigate to, or "back" / "forward" / "reload" for history navigation. - `tab_id: optional string` Tab to act on. Defaults to the active tab when omitted. ### Beta Browser Navigate Tool Use Block - `beta_browser_navigate_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Navigate to a URL, or go back/forward/reload in history. The protocol may be omitted (defaults to https://). - `url: string` The URL to navigate to, or "back" / "forward" / "reload" for history navigation. - `tab_id: optional string` Tab to act on. Defaults to the active tab when omitted. - `name: "navigate"` - `toolset_name: "browser"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `type: "direct"` - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `type: "code_execution_20250825"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `beta_server_tool_caller_20260120: object` - `type: "code_execution_20260120"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ ### Beta Browser New Tab Config - `beta_browser_new_tab_config: object` `new_tab`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. ### Beta Browser New Tab Input - `beta_browser_new_tab_input: object` Open a new empty tab and return its tab_id. ### Beta Browser New Tab Tool Use Block - `beta_browser_new_tab_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Open a new empty tab and return its tab_id. - `name: "new_tab"` - `toolset_name: "browser"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `type: "direct"` - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `type: "code_execution_20250825"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `beta_server_tool_caller_20260120: object` - `type: "code_execution_20260120"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ ### Beta Browser Read Console Config - `beta_browser_read_console_config: object` `read_console`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. ### Beta Browser Read Console Input - `beta_browser_read_console_input: object` Return console output (log entries, errors, warnings) accumulated since the driver attached to the tab and since the last read, one line per entry. An empty result does not mean no traffic for a tab that predates attach. - `tab_id: optional string` Tab to act on. Defaults to the active tab when omitted. ### Beta Browser Read Console Tool Use Block - `beta_browser_read_console_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Return console output (log entries, errors, warnings) accumulated since the driver attached to the tab and since the last read, one line per entry. An empty result does not mean no traffic for a tab that predates attach. - `tab_id: optional string` Tab to act on. Defaults to the active tab when omitted. - `name: "read_console"` - `toolset_name: "browser"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `type: "direct"` - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `type: "code_execution_20250825"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `beta_server_tool_caller_20260120: object` - `type: "code_execution_20260120"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ ### Beta Browser Read Network Config - `beta_browser_read_network_config: object` `read_network`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. ### Beta Browser Read Network Input - `beta_browser_read_network_input: object` Return the network requests (method, URL, status, MIME type, timing) recorded since the driver attached to the tab and since the last read, one line per entry. An empty result does not mean no traffic for a tab that predates attach. - `tab_id: optional string` Tab to act on. Defaults to the active tab when omitted. ### Beta Browser Read Network Tool Use Block - `beta_browser_read_network_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Return the network requests (method, URL, status, MIME type, timing) recorded since the driver attached to the tab and since the last read, one line per entry. An empty result does not mean no traffic for a tab that predates attach. - `tab_id: optional string` Tab to act on. Defaults to the active tab when omitted. - `name: "read_network"` - `toolset_name: "browser"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `type: "direct"` - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `type: "code_execution_20250825"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `beta_server_tool_caller_20260120: object` - `type: "code_execution_20260120"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ ### Beta Browser Read Page Config - `beta_browser_read_page_config: object` `read_page`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. ### Beta Browser Read Page Filter - `beta_browser_read_page_filter: "all" or "interactive"` - `"all"` - `"interactive"` ### Beta Browser Read Page Input - `beta_browser_read_page_input: object` Return a structured accessibility tree of the page (or the subtree rooted at `ref`), with element references like [ref_7] that can be used as targets on later actions. Output is capped at 50,000 characters — narrow with `ref` or a smaller `depth` when exceeded. - `depth: optional number` Maximum tree depth. Default 15. minimum: 1 - `filter: optional "all" or "interactive"` Which elements to include. Omitted: every visible element. "interactive": interactive elements only. "all": additionally includes off-viewport elements. - `"all"` - `"interactive"` - `ref: optional string` Element reference to read a subtree from. Omit to read from the page root. - `tab_id: optional string` Tab to act on. Defaults to the active tab when omitted. ### Beta Browser Read Page Tool Use Block - `beta_browser_read_page_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Return a structured accessibility tree of the page (or the subtree rooted at `ref`), with element references like [ref_7] that can be used as targets on later actions. Output is capped at 50,000 characters — narrow with `ref` or a smaller `depth` when exceeded. - `depth: optional number` Maximum tree depth. Default 15. minimum: 1 - `filter: optional "all" or "interactive"` Which elements to include. Omitted: every visible element. "interactive": interactive elements only. "all": additionally includes off-viewport elements. - `"all"` - `"interactive"` - `ref: optional string` Element reference to read a subtree from. Omit to read from the page root. - `tab_id: optional string` Tab to act on. Defaults to the active tab when omitted. - `name: "read_page"` - `toolset_name: "browser"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `type: "direct"` - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `type: "code_execution_20250825"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `beta_server_tool_caller_20260120: object` - `type: "code_execution_20260120"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ ### Beta Browser Ref Target - `beta_browser_ref_target: object` An element on the page, identified by a reference from a prior `read_page` or `find` result. References are scoped to the tab that produced them and become stale after navigation or a major re-render. - `type: "ref"` - `ref: string` An element reference (e.g. "ref_7") returned by a prior `read_page` or `find` result. ### Beta Browser Right Click Config - `beta_browser_right_click_config: object` `right_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. ### Beta Browser Right Click Input - `beta_browser_right_click_input: object` Right-click at a viewport coordinate or on an element by reference. - `target: BetaBrowserCoordinateTarget or BetaBrowserRefTarget` Where to act: either a viewport coordinate or an element reference. - `beta_browser_coordinate_target: object` A point in the browser viewport, in viewport pixels (the same frame as a full-viewport screenshot). - `type: "coordinate"` - `x: number` Pixels from the left edge of the viewport. minimum: 0 - `y: number` Pixels from the top edge of the viewport. minimum: 0 - `beta_browser_ref_target: object` An element on the page, identified by a reference from a prior `read_page` or `find` result. References are scoped to the tab that produced them and become stale after navigation or a major re-render. - `type: "ref"` - `ref: string` An element reference (e.g. "ref_7") returned by a prior `read_page` or `find` result. - `modifiers: optional string` Optional modifier key chord to hold for the duration of this action (e.g. "shift", "ctrl+shift", "cmd+alt"). - `tab_id: optional string` Tab to act on. Defaults to the active tab when omitted. ### Beta Browser Right Click Tool Use Block - `beta_browser_right_click_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Right-click at a viewport coordinate or on an element by reference. - `target: BetaBrowserCoordinateTarget or BetaBrowserRefTarget` Where to act: either a viewport coordinate or an element reference. - `beta_browser_coordinate_target: object` A point in the browser viewport, in viewport pixels (the same frame as a full-viewport screenshot). - `type: "coordinate"` - `x: number` Pixels from the left edge of the viewport. minimum: 0 - `y: number` Pixels from the top edge of the viewport. minimum: 0 - `beta_browser_ref_target: object` An element on the page, identified by a reference from a prior `read_page` or `find` result. References are scoped to the tab that produced them and become stale after navigation or a major re-render. - `type: "ref"` - `ref: string` An element reference (e.g. "ref_7") returned by a prior `read_page` or `find` result. - `modifiers: optional string` Optional modifier key chord to hold for the duration of this action (e.g. "shift", "ctrl+shift", "cmd+alt"). - `tab_id: optional string` Tab to act on. Defaults to the active tab when omitted. - `name: "right_click"` - `toolset_name: "browser"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `type: "direct"` - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `type: "code_execution_20250825"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `beta_server_tool_caller_20260120: object` - `type: "code_execution_20260120"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ ### Beta Browser Screenshot Config - `beta_browser_screenshot_config: object` `screenshot`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. ### Beta Browser Screenshot Input - `beta_browser_screenshot_input: object` Capture the current browser viewport. - `tab_id: optional string` Tab to act on. Defaults to the active tab when omitted. ### Beta Browser Screenshot Tool Use Block - `beta_browser_screenshot_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Capture the current browser viewport. - `tab_id: optional string` Tab to act on. Defaults to the active tab when omitted. - `name: "screenshot"` - `toolset_name: "browser"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `type: "direct"` - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `type: "code_execution_20250825"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `beta_server_tool_caller_20260120: object` - `type: "code_execution_20260120"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ ### Beta Browser Scroll Config - `beta_browser_scroll_config: object` `scroll`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. ### Beta Browser Scroll Direction - `beta_browser_scroll_direction: "up" or "down" or "left" or "right"` - `"up"` - `"down"` - `"left"` - `"right"` ### Beta Browser Scroll Input - `beta_browser_scroll_input: object` Scroll at a viewport position. `target` must be a coordinate target. - `scroll_direction: "up" or "down" or "left" or "right"` - `"up"` - `"down"` - `"left"` - `"right"` - `target: object` A point in the browser viewport, in viewport pixels (the same frame as a full-viewport screenshot). - `type: "coordinate"` - `x: number` Pixels from the left edge of the viewport. minimum: 0 - `y: number` Pixels from the top edge of the viewport. minimum: 0 - `scroll_amount: optional number` Scroll-wheel notches (1–10). Default 3. minimum: 1, maximum: 10 - `tab_id: optional string` Tab to act on. Defaults to the active tab when omitted. ### Beta Browser Scroll To Config - `beta_browser_scroll_to_config: object` `scroll_to`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. ### Beta Browser Scroll To Input - `beta_browser_scroll_to_input: object` Scroll an element into view. - `target: object` An element on the page, identified by a reference from a prior `read_page` or `find` result. References are scoped to the tab that produced them and become stale after navigation or a major re-render. - `type: "ref"` - `ref: string` An element reference (e.g. "ref_7") returned by a prior `read_page` or `find` result. - `tab_id: optional string` Tab to act on. Defaults to the active tab when omitted. ### Beta Browser Scroll To Tool Use Block - `beta_browser_scroll_to_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Scroll an element into view. - `target: object` An element on the page, identified by a reference from a prior `read_page` or `find` result. References are scoped to the tab that produced them and become stale after navigation or a major re-render. - `type: "ref"` - `ref: string` An element reference (e.g. "ref_7") returned by a prior `read_page` or `find` result. - `tab_id: optional string` Tab to act on. Defaults to the active tab when omitted. - `name: "scroll_to"` - `toolset_name: "browser"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `type: "direct"` - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `type: "code_execution_20250825"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `beta_server_tool_caller_20260120: object` - `type: "code_execution_20260120"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ ### Beta Browser Scroll Tool Use Block - `beta_browser_scroll_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Scroll at a viewport position. `target` must be a coordinate target. - `scroll_direction: "up" or "down" or "left" or "right"` - `"up"` - `"down"` - `"left"` - `"right"` - `target: object` A point in the browser viewport, in viewport pixels (the same frame as a full-viewport screenshot). - `type: "coordinate"` - `x: number` Pixels from the left edge of the viewport. minimum: 0 - `y: number` Pixels from the top edge of the viewport. minimum: 0 - `scroll_amount: optional number` Scroll-wheel notches (1–10). Default 3. minimum: 1, maximum: 10 - `tab_id: optional string` Tab to act on. Defaults to the active tab when omitted. - `name: "scroll"` - `toolset_name: "browser"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `type: "direct"` - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `type: "code_execution_20250825"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `beta_server_tool_caller_20260120: object` - `type: "code_execution_20260120"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ ### Beta Browser State Block Param - `beta_browser_state_block_param: object` The caller's browser state after a browser toolset member call — the full inventory of open tabs, which tab is active, and any side effects (tabs opened, download state changes) the call produced. At most one per `tool_result`, only on a non-error result answering a browser toolset member `tool_use`. The server renders the model-visible text from it; the model never sees the raw fields. - `type: "browser_state"` - `tabs: array of BetaBrowserStateTabEntry` All tabs open in the browser after this call — the full inventory, not a delta. May be empty. Whenever non-empty, exactly one entry carries `active: true`. maxItems: 100 - `tab_id: string` The caller-assigned identifier for this tab, unique within the inventory. minLength: 1, maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `title: string` The title of the page the tab is showing. May be empty. maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `url: string` The URL of the page the tab is showing. May be empty. maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `active: optional boolean` Whether this tab is the active tab after this call. Whenever `tabs` is non-empty, exactly one entry is marked `active: true`. - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `"5m"` - `"1h"` - `state_changes: optional array of BetaBrowserStateChange` Tabs opened and download state changes during this call. "Nothing to report" is expressed by omitting the field, never by an empty list. minItems: 1, maxItems: 200 - `beta_browser_state_change_tab_opened: object` A tab this call's execution opened that remains open at its end — the creation delta of the `tabs` inventory, not an event log. Carries only the `tab_id`; the tab's `title` and `url` live on its `tabs` entry, which must include the same `tab_id`. A tab opened during a failed call gets no deferred `tab_opened`; it simply appears in the next result's `tabs` inventory. - `type: "tab_opened"` - `tab_id: string` The `tab_id` of the opened tab, present in `tabs`. minLength: 1, maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `beta_browser_state_change_download_started: object` A file download that started during this call. - `type: "download_started"` - `download_id: string` The caller-assigned identifier for this download, stable across the state changes reporting it. minLength: 1, maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `url: string` The final post-redirect URL the download was served from. maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `beta_browser_state_change_download_completed: object` A file download that finished during this call, reported with the same `download_id` as its `download_started` — or without a prior `download_started`, when the download finished during the call that started it (at most one state change per `download_id` per result). - `type: "download_completed"` - `download_id: string` The caller-assigned identifier for this download, stable across the state changes reporting it. minLength: 1, maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `url: string` The final post-redirect URL the download was served from. maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `path: optional string` Where the executor saved the file, on the executor's filesystem. Only included when another tool in the same environment can read the file at that path. maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `size_bytes: optional number` The completed download's size. minimum: 0 - `beta_browser_state_change_download_failed: object` A file download that failed — or was cancelled — during this call. - `type: "download_failed"` - `download_id: string` The caller-assigned identifier for this download, stable across the state changes reporting it. minLength: 1, maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `url: string` The final post-redirect URL the download was served from. maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `error: optional string` The failure or cancellation detail, when known. maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ ### Beta Browser State Change - `beta_browser_state_change: BetaBrowserStateChangeTabOpened or BetaBrowserStateChangeDownloadStarted or BetaBrowserStateChangeDownloadCompleted or BetaBrowserStateChangeDownloadFailed` - `beta_browser_state_change_tab_opened: object` A tab this call's execution opened that remains open at its end — the creation delta of the `tabs` inventory, not an event log. Carries only the `tab_id`; the tab's `title` and `url` live on its `tabs` entry, which must include the same `tab_id`. A tab opened during a failed call gets no deferred `tab_opened`; it simply appears in the next result's `tabs` inventory. - `type: "tab_opened"` - `tab_id: string` The `tab_id` of the opened tab, present in `tabs`. minLength: 1, maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `beta_browser_state_change_download_started: object` A file download that started during this call. - `type: "download_started"` - `download_id: string` The caller-assigned identifier for this download, stable across the state changes reporting it. minLength: 1, maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `url: string` The final post-redirect URL the download was served from. maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `beta_browser_state_change_download_completed: object` A file download that finished during this call, reported with the same `download_id` as its `download_started` — or without a prior `download_started`, when the download finished during the call that started it (at most one state change per `download_id` per result). - `type: "download_completed"` - `download_id: string` The caller-assigned identifier for this download, stable across the state changes reporting it. minLength: 1, maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `url: string` The final post-redirect URL the download was served from. maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `path: optional string` Where the executor saved the file, on the executor's filesystem. Only included when another tool in the same environment can read the file at that path. maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `size_bytes: optional number` The completed download's size. minimum: 0 - `beta_browser_state_change_download_failed: object` A file download that failed — or was cancelled — during this call. - `type: "download_failed"` - `download_id: string` The caller-assigned identifier for this download, stable across the state changes reporting it. minLength: 1, maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `url: string` The final post-redirect URL the download was served from. maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `error: optional string` The failure or cancellation detail, when known. maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ ### Beta Browser State Change Download Completed - `beta_browser_state_change_download_completed: object` A file download that finished during this call, reported with the same `download_id` as its `download_started` — or without a prior `download_started`, when the download finished during the call that started it (at most one state change per `download_id` per result). - `type: "download_completed"` - `download_id: string` The caller-assigned identifier for this download, stable across the state changes reporting it. minLength: 1, maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `url: string` The final post-redirect URL the download was served from. maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `path: optional string` Where the executor saved the file, on the executor's filesystem. Only included when another tool in the same environment can read the file at that path. maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `size_bytes: optional number` The completed download's size. minimum: 0 ### Beta Browser State Change Download Failed - `beta_browser_state_change_download_failed: object` A file download that failed — or was cancelled — during this call. - `type: "download_failed"` - `download_id: string` The caller-assigned identifier for this download, stable across the state changes reporting it. minLength: 1, maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `url: string` The final post-redirect URL the download was served from. maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `error: optional string` The failure or cancellation detail, when known. maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ ### Beta Browser State Change Download Started - `beta_browser_state_change_download_started: object` A file download that started during this call. - `type: "download_started"` - `download_id: string` The caller-assigned identifier for this download, stable across the state changes reporting it. minLength: 1, maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `url: string` The final post-redirect URL the download was served from. maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ ### Beta Browser State Change Tab Opened - `beta_browser_state_change_tab_opened: object` A tab this call's execution opened that remains open at its end — the creation delta of the `tabs` inventory, not an event log. Carries only the `tab_id`; the tab's `title` and `url` live on its `tabs` entry, which must include the same `tab_id`. A tab opened during a failed call gets no deferred `tab_opened`; it simply appears in the next result's `tabs` inventory. - `type: "tab_opened"` - `tab_id: string` The `tab_id` of the opened tab, present in `tabs`. minLength: 1, maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ ### Beta Browser State Tab Entry - `beta_browser_state_tab_entry: object` One open browser tab reported in a `browser_state` block's `tabs` inventory. `tab_id` is the caller-assigned identifier for the tab; `title` and `url` describe the page the tab is currently showing and may be empty strings (a blank tab legitimately has both empty). `active` marks the tab that is active after this call; whenever `tabs` is non-empty, exactly one entry is marked. - `tab_id: string` The caller-assigned identifier for this tab, unique within the inventory. minLength: 1, maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `title: string` The title of the page the tab is showing. May be empty. maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `url: string` The URL of the page the tab is showing. May be empty. maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `active: optional boolean` Whether this tab is the active tab after this call. Whenever `tabs` is non-empty, exactly one entry is marked `active: true`. ### Beta Browser Switch Tab Config - `beta_browser_switch_tab_config: object` `switch_tab`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. ### Beta Browser Switch Tab Input - `beta_browser_switch_tab_input: object` Make the tab with the given tab_id the active tab — the tab that actions without a tab_id apply to. - `tab_id: string` The tab to switch to. ### Beta Browser Switch Tab Tool Use Block - `beta_browser_switch_tab_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Make the tab with the given tab_id the active tab — the tab that actions without a tab_id apply to. - `tab_id: string` The tab to switch to. - `name: "switch_tab"` - `toolset_name: "browser"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `type: "direct"` - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `type: "code_execution_20250825"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `beta_server_tool_caller_20260120: object` - `type: "code_execution_20260120"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ ### Beta Browser Tool Use Block - `beta_browser_tool_use_block: BetaBrowserNavigateToolUseBlock or BetaBrowserListTabsToolUseBlock or BetaBrowserNewTabToolUseBlock or 28 more` - `beta_browser_navigate_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Navigate to a URL, or go back/forward/reload in history. The protocol may be omitted (defaults to https://). - `url: string` The URL to navigate to, or "back" / "forward" / "reload" for history navigation. - `tab_id: optional string` Tab to act on. Defaults to the active tab when omitted. - `name: "navigate"` - `toolset_name: "browser"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `type: "direct"` - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `type: "code_execution_20250825"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `beta_server_tool_caller_20260120: object` - `type: "code_execution_20260120"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `beta_browser_list_tabs_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` List all open tabs with each tab's tab_id, title, and URL. - `name: "list_tabs"` - `toolset_name: "browser"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `beta_server_tool_caller_20260120: object` - `beta_browser_new_tab_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Open a new empty tab and return its tab_id. - `name: "new_tab"` - `toolset_name: "browser"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `beta_server_tool_caller_20260120: object` - `beta_browser_switch_tab_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Make the tab with the given tab_id the active tab — the tab that actions without a tab_id apply to. - `tab_id: string` The tab to switch to. - `name: "switch_tab"` - `toolset_name: "browser"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `beta_server_tool_caller_20260120: object` - `beta_browser_close_tab_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Close the tab with the given tab_id. - `tab_id: string` The tab to close. - `name: "close_tab"` - `toolset_name: "browser"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `beta_server_tool_caller_20260120: object` - `beta_browser_read_page_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Return a structured accessibility tree of the page (or the subtree rooted at `ref`), with element references like [ref_7] that can be used as targets on later actions. Output is capped at 50,000 characters — narrow with `ref` or a smaller `depth` when exceeded. - `depth: optional number` Maximum tree depth. Default 15. minimum: 1 - `filter: optional "all" or "interactive"` Which elements to include. Omitted: every visible element. "interactive": interactive elements only. "all": additionally includes off-viewport elements. - `"all"` - `"interactive"` - `ref: optional string` Element reference to read a subtree from. Omit to read from the page root. - `tab_id: optional string` Tab to act on. Defaults to the active tab when omitted. - `name: "read_page"` - `toolset_name: "browser"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `beta_server_tool_caller_20260120: object` - `beta_browser_get_page_text_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Return the page's visible text content as plain text, prioritizing article content. Suited to articles, documentation, and other text-heavy pages. - `tab_id: optional string` Tab to act on. Defaults to the active tab when omitted. - `name: "get_page_text"` - `toolset_name: "browser"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `beta_server_tool_caller_20260120: object` - `beta_browser_read_console_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Return console output (log entries, errors, warnings) accumulated since the driver attached to the tab and since the last read, one line per entry. An empty result does not mean no traffic for a tab that predates attach. - `tab_id: optional string` Tab to act on. Defaults to the active tab when omitted. - `name: "read_console"` - `toolset_name: "browser"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `beta_server_tool_caller_20260120: object` - `beta_browser_read_network_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Return the network requests (method, URL, status, MIME type, timing) recorded since the driver attached to the tab and since the last read, one line per entry. An empty result does not mean no traffic for a tab that predates attach. - `tab_id: optional string` Tab to act on. Defaults to the active tab when omitted. - `name: "read_network"` - `toolset_name: "browser"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `beta_server_tool_caller_20260120: object` - `beta_browser_find_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Find elements matching a natural-language description (e.g. "search bar", "add to cart button") and return up to 20 matches with element references. - `query: string` Natural-language description of the element(s) to find. - `tab_id: optional string` Tab to act on. Defaults to the active tab when omitted. - `name: "find"` - `toolset_name: "browser"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `beta_server_tool_caller_20260120: object` - `beta_browser_form_input_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Set the value of a form element (input, textarea, select, checkbox). Use a boolean for checkboxes, an option value or text for selects. - `target: object` An element on the page, identified by a reference from a prior `read_page` or `find` result. References are scoped to the tab that produced them and become stale after navigation or a major re-render. - `type: "ref"` - `ref: string` An element reference (e.g. "ref_7") returned by a prior `read_page` or `find` result. - `value: string or number or boolean` The value to set. - `union_member_0: string` - `union_member_1: number` - `union_member_2: boolean` - `tab_id: optional string` Tab to act on. Defaults to the active tab when omitted. - `name: "form_input"` - `toolset_name: "browser"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `beta_server_tool_caller_20260120: object` - `beta_browser_file_upload_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Set the value of a file-input element to one or more files. The target must be an element reference; at least one of paths or document_ids is required. - `target: object` An element on the page, identified by a reference from a prior `read_page` or `find` result. References are scoped to the tab that produced them and become stale after navigation or a major re-render. - `type: "ref"` - `ref: string` An element reference (e.g. "ref_7") returned by a prior `read_page` or `find` result. - `document_ids: optional array of string` References to files the harness has staged, for deployments where the browser executor cannot read the caller's filesystem. minItems: 1 - `paths: optional array of string` File paths on the browser executor's filesystem. minItems: 1 - `tab_id: optional string` Tab to act on. Defaults to the active tab when omitted. - `name: "file_upload"` - `toolset_name: "browser"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `beta_server_tool_caller_20260120: object` - `beta_browser_scroll_to_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Scroll an element into view. - `target: object` An element on the page, identified by a reference from a prior `read_page` or `find` result. References are scoped to the tab that produced them and become stale after navigation or a major re-render. - `type: "ref"` - `ref: string` An element reference (e.g. "ref_7") returned by a prior `read_page` or `find` result. - `tab_id: optional string` Tab to act on. Defaults to the active tab when omitted. - `name: "scroll_to"` - `toolset_name: "browser"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `beta_server_tool_caller_20260120: object` - `beta_browser_screenshot_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Capture the current browser viewport. - `tab_id: optional string` Tab to act on. Defaults to the active tab when omitted. - `name: "screenshot"` - `toolset_name: "browser"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `beta_server_tool_caller_20260120: object` - `beta_browser_zoom_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Return a cropped screenshot of the given viewport region, scaled up for closer inspection — useful for small icons, buttons, or text. Coordinates are in the same viewport-pixel space as a full screenshot. - `region: array of number` [x0, y0, x1, y1] in viewport pixels. minItems: 4, maxItems: 4 - `tab_id: optional string` Tab to act on. Defaults to the active tab when omitted. - `name: "zoom"` - `toolset_name: "browser"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `beta_server_tool_caller_20260120: object` - `beta_browser_left_click_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Left-click at a viewport coordinate or on an element by reference. - `target: BetaBrowserCoordinateTarget or BetaBrowserRefTarget` Where to act: either a viewport coordinate or an element reference. - `beta_browser_coordinate_target: object` A point in the browser viewport, in viewport pixels (the same frame as a full-viewport screenshot). - `type: "coordinate"` - `x: number` Pixels from the left edge of the viewport. minimum: 0 - `y: number` Pixels from the top edge of the viewport. minimum: 0 - `beta_browser_ref_target: object` An element on the page, identified by a reference from a prior `read_page` or `find` result. References are scoped to the tab that produced them and become stale after navigation or a major re-render. - `type: "ref"` - `ref: string` An element reference (e.g. "ref_7") returned by a prior `read_page` or `find` result. - `modifiers: optional string` Optional modifier key chord to hold for the duration of this action (e.g. "shift", "ctrl+shift", "cmd+alt"). - `tab_id: optional string` Tab to act on. Defaults to the active tab when omitted. - `name: "left_click"` - `toolset_name: "browser"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `beta_server_tool_caller_20260120: object` - `beta_browser_right_click_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Right-click at a viewport coordinate or on an element by reference. - `target: BetaBrowserCoordinateTarget or BetaBrowserRefTarget` Where to act: either a viewport coordinate or an element reference. - `beta_browser_coordinate_target: object` A point in the browser viewport, in viewport pixels (the same frame as a full-viewport screenshot). - `beta_browser_ref_target: object` An element on the page, identified by a reference from a prior `read_page` or `find` result. References are scoped to the tab that produced them and become stale after navigation or a major re-render. - `modifiers: optional string` Optional modifier key chord to hold for the duration of this action (e.g. "shift", "ctrl+shift", "cmd+alt"). - `tab_id: optional string` Tab to act on. Defaults to the active tab when omitted. - `name: "right_click"` - `toolset_name: "browser"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `beta_server_tool_caller_20260120: object` - `beta_browser_middle_click_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Middle-click at a viewport coordinate or on an element by reference. - `target: BetaBrowserCoordinateTarget or BetaBrowserRefTarget` Where to act: either a viewport coordinate or an element reference. - `beta_browser_coordinate_target: object` A point in the browser viewport, in viewport pixels (the same frame as a full-viewport screenshot). - `beta_browser_ref_target: object` An element on the page, identified by a reference from a prior `read_page` or `find` result. References are scoped to the tab that produced them and become stale after navigation or a major re-render. - `modifiers: optional string` Optional modifier key chord to hold for the duration of this action (e.g. "shift", "ctrl+shift", "cmd+alt"). - `tab_id: optional string` Tab to act on. Defaults to the active tab when omitted. - `name: "middle_click"` - `toolset_name: "browser"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `beta_server_tool_caller_20260120: object` - `beta_browser_double_click_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Double left-click at a viewport coordinate or on an element by reference. - `target: BetaBrowserCoordinateTarget or BetaBrowserRefTarget` Where to act: either a viewport coordinate or an element reference. - `beta_browser_coordinate_target: object` A point in the browser viewport, in viewport pixels (the same frame as a full-viewport screenshot). - `beta_browser_ref_target: object` An element on the page, identified by a reference from a prior `read_page` or `find` result. References are scoped to the tab that produced them and become stale after navigation or a major re-render. - `modifiers: optional string` Optional modifier key chord to hold for the duration of this action (e.g. "shift", "ctrl+shift", "cmd+alt"). - `tab_id: optional string` Tab to act on. Defaults to the active tab when omitted. - `name: "double_click"` - `toolset_name: "browser"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `beta_server_tool_caller_20260120: object` - `beta_browser_triple_click_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Triple left-click at a viewport coordinate or on an element by reference (typically selects a line or paragraph). - `target: BetaBrowserCoordinateTarget or BetaBrowserRefTarget` Where to act: either a viewport coordinate or an element reference. - `beta_browser_coordinate_target: object` A point in the browser viewport, in viewport pixels (the same frame as a full-viewport screenshot). - `beta_browser_ref_target: object` An element on the page, identified by a reference from a prior `read_page` or `find` result. References are scoped to the tab that produced them and become stale after navigation or a major re-render. - `modifiers: optional string` Optional modifier key chord to hold for the duration of this action (e.g. "shift", "ctrl+shift", "cmd+alt"). - `tab_id: optional string` Tab to act on. Defaults to the active tab when omitted. - `name: "triple_click"` - `toolset_name: "browser"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `beta_server_tool_caller_20260120: object` - `beta_browser_hover_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Move the cursor to a coordinate or element without clicking. - `target: BetaBrowserCoordinateTarget or BetaBrowserRefTarget` Where to act: either a viewport coordinate or an element reference. - `beta_browser_coordinate_target: object` A point in the browser viewport, in viewport pixels (the same frame as a full-viewport screenshot). - `beta_browser_ref_target: object` An element on the page, identified by a reference from a prior `read_page` or `find` result. References are scoped to the tab that produced them and become stale after navigation or a major re-render. - `tab_id: optional string` Tab to act on. Defaults to the active tab when omitted. - `name: "hover"` - `toolset_name: "browser"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `beta_server_tool_caller_20260120: object` - `beta_browser_left_click_drag_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Press at `from`, drag to `target`, release. Both must be coordinate targets. - `from: object` A point in the browser viewport, in viewport pixels (the same frame as a full-viewport screenshot). - `type: "coordinate"` - `x: number` Pixels from the left edge of the viewport. minimum: 0 - `y: number` Pixels from the top edge of the viewport. minimum: 0 - `target: object` A point in the browser viewport, in viewport pixels (the same frame as a full-viewport screenshot). - `type: "coordinate"` - `x: number` Pixels from the left edge of the viewport. minimum: 0 - `y: number` Pixels from the top edge of the viewport. minimum: 0 - `tab_id: optional string` Tab to act on. Defaults to the active tab when omitted. - `name: "left_click_drag"` - `toolset_name: "browser"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `beta_server_tool_caller_20260120: object` - `beta_browser_left_mouse_down_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Press and hold the left mouse button at a viewport coordinate. Pair with left_mouse_up to perform a custom drag. - `target: object` A point in the browser viewport, in viewport pixels (the same frame as a full-viewport screenshot). - `type: "coordinate"` - `x: number` Pixels from the left edge of the viewport. minimum: 0 - `y: number` Pixels from the top edge of the viewport. minimum: 0 - `tab_id: optional string` Tab to act on. Defaults to the active tab when omitted. - `name: "left_mouse_down"` - `toolset_name: "browser"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `beta_server_tool_caller_20260120: object` - `beta_browser_left_mouse_up_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Release the left mouse button at a viewport coordinate. - `target: object` A point in the browser viewport, in viewport pixels (the same frame as a full-viewport screenshot). - `type: "coordinate"` - `x: number` Pixels from the left edge of the viewport. minimum: 0 - `y: number` Pixels from the top edge of the viewport. minimum: 0 - `tab_id: optional string` Tab to act on. Defaults to the active tab when omitted. - `name: "left_mouse_up"` - `toolset_name: "browser"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `beta_server_tool_caller_20260120: object` - `beta_browser_mouse_move_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Move the pointer to a viewport coordinate without clicking. - `target: object` A point in the browser viewport, in viewport pixels (the same frame as a full-viewport screenshot). - `type: "coordinate"` - `x: number` Pixels from the left edge of the viewport. minimum: 0 - `y: number` Pixels from the top edge of the viewport. minimum: 0 - `tab_id: optional string` Tab to act on. Defaults to the active tab when omitted. - `name: "mouse_move"` - `toolset_name: "browser"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `beta_server_tool_caller_20260120: object` - `beta_browser_scroll_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Scroll at a viewport position. `target` must be a coordinate target. - `scroll_direction: "up" or "down" or "left" or "right"` - `"up"` - `"down"` - `"left"` - `"right"` - `target: object` A point in the browser viewport, in viewport pixels (the same frame as a full-viewport screenshot). - `type: "coordinate"` - `x: number` Pixels from the left edge of the viewport. minimum: 0 - `y: number` Pixels from the top edge of the viewport. minimum: 0 - `scroll_amount: optional number` Scroll-wheel notches (1–10). Default 3. minimum: 1, maximum: 10 - `tab_id: optional string` Tab to act on. Defaults to the active tab when omitted. - `name: "scroll"` - `toolset_name: "browser"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `beta_server_tool_caller_20260120: object` - `beta_browser_type_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Type a literal string at the current focus. - `text: string` The text to type. - `tab_id: optional string` Tab to act on. Defaults to the active tab when omitted. - `name: "type"` - `toolset_name: "browser"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `beta_server_tool_caller_20260120: object` - `beta_browser_key_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Press a key or key chord. Use "+" to combine modifiers with a key (e.g. "ctrl+a", "cmd+shift+p") and space to sequence presses (e.g. "Backspace Backspace Delete"). Common names like "Return", "Tab", "Escape", "BackSpace" are supported. - `text: string` The key, chord, or space-separated sequence to press. - `repeat: optional number` Number of times to repeat. Default 1. minimum: 1, maximum: 100 - `tab_id: optional string` Tab to act on. Defaults to the active tab when omitted. - `name: "key"` - `toolset_name: "browser"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `beta_server_tool_caller_20260120: object` - `beta_browser_hold_key_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Hold a key or key chord down for a duration, then release it. Uses the same key names and "+" chord syntax as the key action. - `duration: number` Seconds to hold the key down (maximum 30). minimum: 0, maximum: 30 - `text: string` The key or chord to hold. - `tab_id: optional string` Tab to act on. Defaults to the active tab when omitted. - `name: "hold_key"` - `toolset_name: "browser"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `beta_server_tool_caller_20260120: object` - `beta_browser_wait_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Pause for the given duration. - `duration: number` Seconds to wait (maximum 30). minimum: 0, maximum: 30 - `tab_id: optional string` Tab to act on. Defaults to the active tab when omitted. - `name: "wait"` - `toolset_name: "browser"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `beta_server_tool_caller_20260120: object` - `beta_browser_javascript_exec_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Execute JavaScript in the page context and return the value of the last expression. The code runs with access to the DOM, `window`, and page variables. Write the expression you want evaluated — do NOT use `return`. - `text: string` JavaScript to execute in the page context. - `tab_id: optional string` Tab to act on. Defaults to the active tab when omitted. - `name: "javascript_exec"` - `toolset_name: "browser"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `beta_server_tool_caller_20260120: object` ### Beta Browser Toolset 20260801 - `beta_browser_toolset_20260801: object` The browser toolset: a single `tools[]` entry (carrying no `name`) that declares the browser tool family. The model is served the family's tool with any members disabled via `configs` removed from its schema. - `type: "browser_toolset_20260801"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `"5m"` - `"1h"` - `configs: optional object` Sparse per-member overrides, keyed by member name. Absent, null, and {} are equivalent; a member's defaults apply wherever its key is absent. - `type: optional object` `type`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `close_tab: optional object` `close_tab`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `double_click: optional object` `double_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `file_upload: optional object` `file_upload`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `find: optional object` `find`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `form_input: optional object` `form_input`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `get_page_text: optional object` `get_page_text`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `hold_key: optional object` `hold_key`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `hover: optional object` `hover`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `javascript_exec: optional object` `javascript_exec`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `key: optional object` `key`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_click: optional object` `left_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_click_drag: optional object` `left_click_drag`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_mouse_down: optional object` `left_mouse_down`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_mouse_up: optional object` `left_mouse_up`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `list_tabs: optional object` `list_tabs`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `middle_click: optional object` `middle_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `mouse_move: optional object` `mouse_move`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `navigate: optional object` `navigate`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `new_tab: optional object` `new_tab`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `read_console: optional object` `read_console`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `read_network: optional object` `read_network`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `read_page: optional object` `read_page`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `right_click: optional object` `right_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `screenshot: optional object` `screenshot`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `scroll: optional object` `scroll`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `scroll_to: optional object` `scroll_to`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `switch_tab: optional object` `switch_tab`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `triple_click: optional object` `triple_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `wait: optional object` `wait`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `zoom: optional object` `zoom`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. ### Beta Browser Toolset Configs - `beta_browser_toolset_configs: object` Per-member configuration for `browser_toolset_20260801`: one optional field per member tool, keyed by the member name — the same name the member's `tool_use` blocks carry. Every member is an accepted key, and a member's defaults apply wherever its key is absent. Unknown keys are rejected: the field set is this toolset version's complete member set. - `type: optional object` `type`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `close_tab: optional object` `close_tab`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `double_click: optional object` `double_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `file_upload: optional object` `file_upload`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `find: optional object` `find`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `form_input: optional object` `form_input`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `get_page_text: optional object` `get_page_text`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `hold_key: optional object` `hold_key`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `hover: optional object` `hover`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `javascript_exec: optional object` `javascript_exec`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `key: optional object` `key`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_click: optional object` `left_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_click_drag: optional object` `left_click_drag`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_mouse_down: optional object` `left_mouse_down`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_mouse_up: optional object` `left_mouse_up`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `list_tabs: optional object` `list_tabs`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `middle_click: optional object` `middle_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `mouse_move: optional object` `mouse_move`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `navigate: optional object` `navigate`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `new_tab: optional object` `new_tab`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `read_console: optional object` `read_console`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `read_network: optional object` `read_network`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `read_page: optional object` `read_page`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `right_click: optional object` `right_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `screenshot: optional object` `screenshot`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `scroll: optional object` `scroll`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `scroll_to: optional object` `scroll_to`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `switch_tab: optional object` `switch_tab`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `triple_click: optional object` `triple_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `wait: optional object` `wait`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `zoom: optional object` `zoom`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. ### Beta Browser Triple Click Config - `beta_browser_triple_click_config: object` `triple_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. ### Beta Browser Triple Click Input - `beta_browser_triple_click_input: object` Triple left-click at a viewport coordinate or on an element by reference (typically selects a line or paragraph). - `target: BetaBrowserCoordinateTarget or BetaBrowserRefTarget` Where to act: either a viewport coordinate or an element reference. - `beta_browser_coordinate_target: object` A point in the browser viewport, in viewport pixels (the same frame as a full-viewport screenshot). - `type: "coordinate"` - `x: number` Pixels from the left edge of the viewport. minimum: 0 - `y: number` Pixels from the top edge of the viewport. minimum: 0 - `beta_browser_ref_target: object` An element on the page, identified by a reference from a prior `read_page` or `find` result. References are scoped to the tab that produced them and become stale after navigation or a major re-render. - `type: "ref"` - `ref: string` An element reference (e.g. "ref_7") returned by a prior `read_page` or `find` result. - `modifiers: optional string` Optional modifier key chord to hold for the duration of this action (e.g. "shift", "ctrl+shift", "cmd+alt"). - `tab_id: optional string` Tab to act on. Defaults to the active tab when omitted. ### Beta Browser Triple Click Tool Use Block - `beta_browser_triple_click_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Triple left-click at a viewport coordinate or on an element by reference (typically selects a line or paragraph). - `target: BetaBrowserCoordinateTarget or BetaBrowserRefTarget` Where to act: either a viewport coordinate or an element reference. - `beta_browser_coordinate_target: object` A point in the browser viewport, in viewport pixels (the same frame as a full-viewport screenshot). - `type: "coordinate"` - `x: number` Pixels from the left edge of the viewport. minimum: 0 - `y: number` Pixels from the top edge of the viewport. minimum: 0 - `beta_browser_ref_target: object` An element on the page, identified by a reference from a prior `read_page` or `find` result. References are scoped to the tab that produced them and become stale after navigation or a major re-render. - `type: "ref"` - `ref: string` An element reference (e.g. "ref_7") returned by a prior `read_page` or `find` result. - `modifiers: optional string` Optional modifier key chord to hold for the duration of this action (e.g. "shift", "ctrl+shift", "cmd+alt"). - `tab_id: optional string` Tab to act on. Defaults to the active tab when omitted. - `name: "triple_click"` - `toolset_name: "browser"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `type: "direct"` - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `type: "code_execution_20250825"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `beta_server_tool_caller_20260120: object` - `type: "code_execution_20260120"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ ### Beta Browser Type Config - `beta_browser_type_config: object` `type`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. ### Beta Browser Type Input - `beta_browser_type_input: object` Type a literal string at the current focus. - `text: string` The text to type. - `tab_id: optional string` Tab to act on. Defaults to the active tab when omitted. ### Beta Browser Type Tool Use Block - `beta_browser_type_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Type a literal string at the current focus. - `text: string` The text to type. - `tab_id: optional string` Tab to act on. Defaults to the active tab when omitted. - `name: "type"` - `toolset_name: "browser"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `type: "direct"` - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `type: "code_execution_20250825"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `beta_server_tool_caller_20260120: object` - `type: "code_execution_20260120"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ ### Beta Browser Wait Config - `beta_browser_wait_config: object` `wait`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. ### Beta Browser Wait Input - `beta_browser_wait_input: object` Pause for the given duration. - `duration: number` Seconds to wait (maximum 30). minimum: 0, maximum: 30 - `tab_id: optional string` Tab to act on. Defaults to the active tab when omitted. ### Beta Browser Wait Tool Use Block - `beta_browser_wait_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Pause for the given duration. - `duration: number` Seconds to wait (maximum 30). minimum: 0, maximum: 30 - `tab_id: optional string` Tab to act on. Defaults to the active tab when omitted. - `name: "wait"` - `toolset_name: "browser"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `type: "direct"` - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `type: "code_execution_20250825"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `beta_server_tool_caller_20260120: object` - `type: "code_execution_20260120"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ ### Beta Browser Zoom Config - `beta_browser_zoom_config: object` `zoom`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. ### Beta Browser Zoom Input - `beta_browser_zoom_input: object` Return a cropped screenshot of the given viewport region, scaled up for closer inspection — useful for small icons, buttons, or text. Coordinates are in the same viewport-pixel space as a full screenshot. - `region: array of number` [x0, y0, x1, y1] in viewport pixels. minItems: 4, maxItems: 4 - `tab_id: optional string` Tab to act on. Defaults to the active tab when omitted. ### Beta Browser Zoom Tool Use Block - `beta_browser_zoom_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Return a cropped screenshot of the given viewport region, scaled up for closer inspection — useful for small icons, buttons, or text. Coordinates are in the same viewport-pixel space as a full screenshot. - `region: array of number` [x0, y0, x1, y1] in viewport pixels. minItems: 4, maxItems: 4 - `tab_id: optional string` Tab to act on. Defaults to the active tab when omitted. - `name: "zoom"` - `toolset_name: "browser"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `type: "direct"` - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `type: "code_execution_20250825"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `beta_server_tool_caller_20260120: object` - `type: "code_execution_20260120"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ ### Beta Cache Control Ephemeral - `beta_cache_control_ephemeral: object` - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `"5m"` - `"1h"` ### Beta Cache Creation - `beta_cache_creation: object` - `ephemeral_1h_input_tokens: number` The number of input tokens used to create the 1 hour cache entry. minimum: 0 - `ephemeral_5m_input_tokens: number` The number of input tokens used to create the 5 minute cache entry. minimum: 0 ### Beta Cache Miss Messages Changed - `beta_cache_miss_messages_changed: object` - `type: "messages_changed"` - `cache_missed_input_tokens: number` Approximate number of input tokens that would have been read from cache had the prefix matched the previous request. ### Beta Cache Miss Model Changed - `beta_cache_miss_model_changed: object` - `type: "model_changed"` - `cache_missed_input_tokens: number` Approximate number of input tokens that would have been read from cache had the prefix matched the previous request. ### Beta Cache Miss Previous Message Not Found - `beta_cache_miss_previous_message_not_found: object` - `type: "previous_message_not_found"` ### Beta Cache Miss Reason - `beta_cache_miss_reason: BetaCacheMissModelChanged or BetaCacheMissSystemChanged or BetaCacheMissToolsChanged or 3 more` - `beta_cache_miss_model_changed: object` - `type: "model_changed"` - `cache_missed_input_tokens: number` Approximate number of input tokens that would have been read from cache had the prefix matched the previous request. - `beta_cache_miss_system_changed: object` - `type: "system_changed"` - `cache_missed_input_tokens: number` Approximate number of input tokens that would have been read from cache had the prefix matched the previous request. - `beta_cache_miss_tools_changed: object` - `type: "tools_changed"` - `cache_missed_input_tokens: number` Approximate number of input tokens that would have been read from cache had the prefix matched the previous request. - `beta_cache_miss_messages_changed: object` - `type: "messages_changed"` - `cache_missed_input_tokens: number` Approximate number of input tokens that would have been read from cache had the prefix matched the previous request. - `beta_cache_miss_previous_message_not_found: object` - `type: "previous_message_not_found"` - `beta_cache_miss_unavailable: object` - `type: "unavailable"` ### Beta Cache Miss System Changed - `beta_cache_miss_system_changed: object` - `type: "system_changed"` - `cache_missed_input_tokens: number` Approximate number of input tokens that would have been read from cache had the prefix matched the previous request. ### Beta Cache Miss Tools Changed - `beta_cache_miss_tools_changed: object` - `type: "tools_changed"` - `cache_missed_input_tokens: number` Approximate number of input tokens that would have been read from cache had the prefix matched the previous request. ### Beta Cache Miss Unavailable - `beta_cache_miss_unavailable: object` - `type: "unavailable"` ### Beta Citation Char Location - `beta_citation_char_location: object` - `type: "char_location"` - `cited_text: string` - `document_index: number` minimum: 0 - `document_title: string` - `end_char_index: number` - `file_id: string` - `start_char_index: number` minimum: 0 ### Beta Citation Char Location Param - `beta_citation_char_location_param: object` - `type: "char_location"` - `cited_text: string` - `document_index: number` minimum: 0 - `document_title: string` minLength: 1, maxLength: 500 - `end_char_index: number` - `start_char_index: number` minimum: 0 ### Beta Citation Config - `beta_citation_config: object` - `enabled: boolean` ### Beta Citation Content Block Location - `beta_citation_content_block_location: object` - `type: "content_block_location"` - `cited_text: string` The full text of the cited block range, concatenated. Always equals the contents of `content[start_block_index:end_block_index]` joined together. The text block is the minimal citable unit; this field is never a substring of a single block. Not counted toward output tokens, and not counted toward input tokens when sent back in subsequent turns. - `document_index: number` minimum: 0 - `document_title: string` - `end_block_index: number` Exclusive 0-based end index of the cited block range in the source's `content` array. Always greater than `start_block_index`; a single-block citation has `end_block_index = start_block_index + 1`. - `file_id: string` - `start_block_index: number` 0-based index of the first cited block in the source's `content` array. minimum: 0 ### Beta Citation Content Block Location Param - `beta_citation_content_block_location_param: object` - `type: "content_block_location"` - `cited_text: string` The full text of the cited block range, concatenated. Always equals the contents of `content[start_block_index:end_block_index]` joined together. The text block is the minimal citable unit; this field is never a substring of a single block. Not counted toward output tokens, and not counted toward input tokens when sent back in subsequent turns. - `document_index: number` minimum: 0 - `document_title: string` minLength: 1, maxLength: 500 - `end_block_index: number` Exclusive 0-based end index of the cited block range in the source's `content` array. Always greater than `start_block_index`; a single-block citation has `end_block_index = start_block_index + 1`. - `start_block_index: number` 0-based index of the first cited block in the source's `content` array. minimum: 0 ### Beta Citation Page Location - `beta_citation_page_location: object` - `type: "page_location"` - `cited_text: string` - `document_index: number` minimum: 0 - `document_title: string` - `end_page_number: number` - `file_id: string` - `start_page_number: number` minimum: 1 ### Beta Citation Page Location Param - `beta_citation_page_location_param: object` - `type: "page_location"` - `cited_text: string` - `document_index: number` minimum: 0 - `document_title: string` minLength: 1, maxLength: 500 - `end_page_number: number` - `start_page_number: number` minimum: 1 ### Beta Citation Search Result Location - `beta_citation_search_result_location: object` - `type: "search_result_location"` - `cited_text: string` The full text of the cited block range, concatenated. Always equals the contents of `content[start_block_index:end_block_index]` joined together. The text block is the minimal citable unit; this field is never a substring of a single block. Not counted toward output tokens, and not counted toward input tokens when sent back in subsequent turns. - `end_block_index: number` Exclusive 0-based end index of the cited block range in the source's `content` array. Always greater than `start_block_index`; a single-block citation has `end_block_index = start_block_index + 1`. - `search_result_index: number` 0-based index of the cited search result among all `search_result` content blocks in the request, in the order they appear across messages and tool results. Counted separately from `document_index`; server-side web search results are not included in this count. minimum: 0 - `source: string` - `start_block_index: number` 0-based index of the first cited block in the source's `content` array. minimum: 0 - `title: string` ### Beta Citation Search Result Location Param - `beta_citation_search_result_location_param: object` - `type: "search_result_location"` - `cited_text: string` The full text of the cited block range, concatenated. Always equals the contents of `content[start_block_index:end_block_index]` joined together. The text block is the minimal citable unit; this field is never a substring of a single block. Not counted toward output tokens, and not counted toward input tokens when sent back in subsequent turns. - `end_block_index: number` Exclusive 0-based end index of the cited block range in the source's `content` array. Always greater than `start_block_index`; a single-block citation has `end_block_index = start_block_index + 1`. - `search_result_index: number` 0-based index of the cited search result among all `search_result` content blocks in the request, in the order they appear across messages and tool results. Counted separately from `document_index`; server-side web search results are not included in this count. minimum: 0 - `source: string` - `start_block_index: number` 0-based index of the first cited block in the source's `content` array. minimum: 0 - `title: string` ### Beta Citation Web Search Result Location Param - `beta_citation_web_search_result_location_param: object` - `type: "web_search_result_location"` - `cited_text: string` - `encrypted_index: string` - `title: string` minLength: 1, maxLength: 512 - `url: string` minLength: 1 ### Beta Citations Config Param - `beta_citations_config_param: object` - `enabled: optional boolean` ### Beta Citations Delta - `beta_citations_delta: object` - `type: "citations_delta"` - `citation: BetaCitationCharLocation or BetaCitationPageLocation or BetaCitationContentBlockLocation or 2 more` - `beta_citation_char_location: object` - `type: "char_location"` - `cited_text: string` - `document_index: number` minimum: 0 - `document_title: string` - `end_char_index: number` - `file_id: string` - `start_char_index: number` minimum: 0 - `beta_citation_page_location: object` - `type: "page_location"` - `cited_text: string` - `document_index: number` minimum: 0 - `document_title: string` - `end_page_number: number` - `file_id: string` - `start_page_number: number` minimum: 1 - `beta_citation_content_block_location: object` - `type: "content_block_location"` - `cited_text: string` The full text of the cited block range, concatenated. Always equals the contents of `content[start_block_index:end_block_index]` joined together. The text block is the minimal citable unit; this field is never a substring of a single block. Not counted toward output tokens, and not counted toward input tokens when sent back in subsequent turns. - `document_index: number` minimum: 0 - `document_title: string` - `end_block_index: number` Exclusive 0-based end index of the cited block range in the source's `content` array. Always greater than `start_block_index`; a single-block citation has `end_block_index = start_block_index + 1`. - `file_id: string` - `start_block_index: number` 0-based index of the first cited block in the source's `content` array. minimum: 0 - `beta_citations_web_search_result_location: object` - `type: "web_search_result_location"` - `cited_text: string` - `encrypted_index: string` - `title: string` maxLength: 512 - `url: string` - `beta_citation_search_result_location: object` - `type: "search_result_location"` - `cited_text: string` The full text of the cited block range, concatenated. Always equals the contents of `content[start_block_index:end_block_index]` joined together. The text block is the minimal citable unit; this field is never a substring of a single block. Not counted toward output tokens, and not counted toward input tokens when sent back in subsequent turns. - `end_block_index: number` Exclusive 0-based end index of the cited block range in the source's `content` array. Always greater than `start_block_index`; a single-block citation has `end_block_index = start_block_index + 1`. - `search_result_index: number` 0-based index of the cited search result among all `search_result` content blocks in the request, in the order they appear across messages and tool results. Counted separately from `document_index`; server-side web search results are not included in this count. minimum: 0 - `source: string` - `start_block_index: number` 0-based index of the first cited block in the source's `content` array. minimum: 0 - `title: string` ### Beta Citations Web Search Result Location - `beta_citations_web_search_result_location: object` - `type: "web_search_result_location"` - `cited_text: string` - `encrypted_index: string` - `title: string` maxLength: 512 - `url: string` ### Beta Clear Thinking 20251015 Edit - `beta_clear_thinking_20251015_edit: object` - `type: "clear_thinking_20251015"` - `keep: optional BetaThinkingTurns or BetaAllThinkingTurns or "all"` Number of most recent assistant turns to keep thinking blocks for. Older turns will have their thinking blocks removed. - `beta_thinking_turns: object` - `type: "thinking_turns"` - `value: number` minimum: 1 - `beta_all_thinking_turns: object` - `type: "all"` - `union_member_2: "all"` ### Beta Clear Thinking 20251015 Edit Response - `beta_clear_thinking_20251015_edit_response: object` - `type: "clear_thinking_20251015"` The type of context management edit applied. - `cleared_input_tokens: number` Number of input tokens cleared by this edit. minimum: 0 - `cleared_thinking_turns: number` Number of thinking turns that were cleared. minimum: 0 ### Beta Clear Tool Uses 20250919 Edit - `beta_clear_tool_uses_20250919_edit: object` - `type: "clear_tool_uses_20250919"` - `clear_at_least: optional object` Minimum number of tokens that must be cleared when triggered. Context will only be modified if at least this many tokens can be removed. - `type: "input_tokens"` - `value: number` minimum: 0 - `clear_tool_inputs: optional boolean or array of string` Whether to clear all tool inputs (bool) or specific tool inputs to clear (list) - `union_member_0: boolean` - `union_member_1: array of string` - `exclude_tools: optional array of string` Tool names whose uses are preserved from clearing - `keep: optional object` Number of tool uses to retain in the conversation - `type: "tool_uses"` - `value: number` minimum: 0 - `trigger: optional BetaInputTokensTrigger or BetaToolUsesTrigger` Condition that triggers the context management strategy - `beta_input_tokens_trigger: object` - `type: "input_tokens"` - `value: number` minimum: 1 - `beta_tool_uses_trigger: object` - `type: "tool_uses"` - `value: number` minimum: 1 ### Beta Clear Tool Uses 20250919 Edit Response - `beta_clear_tool_uses_20250919_edit_response: object` - `type: "clear_tool_uses_20250919"` The type of context management edit applied. - `cleared_input_tokens: number` Number of input tokens cleared by this edit. minimum: 0 - `cleared_tool_uses: number` Number of tool uses that were cleared. minimum: 0 ### Beta Code Execution Output Block - `beta_code_execution_output_block: object` - `type: "code_execution_output"` - `file_id: string` ### Beta Code Execution Output Block Param - `beta_code_execution_output_block_param: object` - `type: "code_execution_output"` - `file_id: string` ### Beta Code Execution Result Block - `beta_code_execution_result_block: object` - `type: "code_execution_result"` - `content: array of BetaCodeExecutionOutputBlock` - `type: "code_execution_output"` - `file_id: string` - `return_code: number` - `stderr: string` - `stdout: string` ### Beta Code Execution Result Block Param - `beta_code_execution_result_block_param: object` - `type: "code_execution_result"` - `content: array of BetaCodeExecutionOutputBlockParam` - `type: "code_execution_output"` - `file_id: string` - `return_code: number` - `stderr: string` - `stdout: string` ### Beta Code Execution Tool 20250522 - `beta_code_execution_tool_20250522: object` - `type: "code_execution_20250522"` - `name: "code_execution"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `"5m"` - `"1h"` - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs ### Beta Code Execution Tool 20250825 - `beta_code_execution_tool_20250825: object` - `type: "code_execution_20250825"` - `name: "code_execution"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `"5m"` - `"1h"` - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs ### Beta Code Execution Tool 20260120 - `beta_code_execution_tool_20260120: object` Code execution tool with REPL state persistence (daemon mode + gVisor checkpoint). - `type: "code_execution_20260120"` - `name: "code_execution"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `"5m"` - `"1h"` - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs ### Beta Code Execution Tool 20260521 - `beta_code_execution_tool_20260521: object` Code execution tool with REPL state persistence. - `type: "code_execution_20260521"` - `name: "code_execution"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `"5m"` - `"1h"` - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs ### Beta Code Execution Tool Result Block - `beta_code_execution_tool_result_block: object` - `type: "code_execution_tool_result"` - `content: BetaCodeExecutionToolResultError or BetaCodeExecutionResultBlock or BetaEncryptedCodeExecutionResultBlock` - `beta_code_execution_tool_result_error: object` - `type: "code_execution_tool_result_error"` - `error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or "execution_time_exceeded"` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `beta_code_execution_result_block: object` - `type: "code_execution_result"` - `content: array of BetaCodeExecutionOutputBlock` - `type: "code_execution_output"` - `file_id: string` - `return_code: number` - `stderr: string` - `stdout: string` - `beta_encrypted_code_execution_result_block: object` Code execution result with encrypted stdout for PFC + web_search results. - `type: "encrypted_code_execution_result"` - `content: array of BetaCodeExecutionOutputBlock` - `type: "code_execution_output"` - `file_id: string` - `encrypted_stdout: string` - `return_code: number` - `stderr: string` - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ ### Beta Code Execution Tool Result Block Content - `beta_code_execution_tool_result_block_content: BetaCodeExecutionToolResultError or BetaCodeExecutionResultBlock or BetaEncryptedCodeExecutionResultBlock` - `beta_code_execution_tool_result_error: object` - `type: "code_execution_tool_result_error"` - `error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or "execution_time_exceeded"` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `beta_code_execution_result_block: object` - `type: "code_execution_result"` - `content: array of BetaCodeExecutionOutputBlock` - `type: "code_execution_output"` - `file_id: string` - `return_code: number` - `stderr: string` - `stdout: string` - `beta_encrypted_code_execution_result_block: object` Code execution result with encrypted stdout for PFC + web_search results. - `type: "encrypted_code_execution_result"` - `content: array of BetaCodeExecutionOutputBlock` - `type: "code_execution_output"` - `file_id: string` - `encrypted_stdout: string` - `return_code: number` - `stderr: string` ### Beta Code Execution Tool Result Block Param - `beta_code_execution_tool_result_block_param: object` - `type: "code_execution_tool_result"` - `content: BetaCodeExecutionToolResultErrorParam or BetaCodeExecutionResultBlockParam or BetaEncryptedCodeExecutionResultBlockParam` - `beta_code_execution_tool_result_error_param: object` - `type: "code_execution_tool_result_error"` - `error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or "execution_time_exceeded"` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `beta_code_execution_result_block_param: object` - `type: "code_execution_result"` - `content: array of BetaCodeExecutionOutputBlockParam` - `type: "code_execution_output"` - `file_id: string` - `return_code: number` - `stderr: string` - `stdout: string` - `beta_encrypted_code_execution_result_block_param: object` Code execution result with encrypted stdout for PFC + web_search results. - `type: "encrypted_code_execution_result"` - `content: array of BetaCodeExecutionOutputBlockParam` - `type: "code_execution_output"` - `file_id: string` - `encrypted_stdout: string` - `return_code: number` - `stderr: string` - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `"5m"` - `"1h"` ### Beta Code Execution Tool Result Block Param Content - `beta_code_execution_tool_result_block_param_content: BetaCodeExecutionToolResultErrorParam or BetaCodeExecutionResultBlockParam or BetaEncryptedCodeExecutionResultBlockParam` - `beta_code_execution_tool_result_error_param: object` - `type: "code_execution_tool_result_error"` - `error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or "execution_time_exceeded"` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `beta_code_execution_result_block_param: object` - `type: "code_execution_result"` - `content: array of BetaCodeExecutionOutputBlockParam` - `type: "code_execution_output"` - `file_id: string` - `return_code: number` - `stderr: string` - `stdout: string` - `beta_encrypted_code_execution_result_block_param: object` Code execution result with encrypted stdout for PFC + web_search results. - `type: "encrypted_code_execution_result"` - `content: array of BetaCodeExecutionOutputBlockParam` - `type: "code_execution_output"` - `file_id: string` - `encrypted_stdout: string` - `return_code: number` - `stderr: string` ### Beta Code Execution Tool Result Error - `beta_code_execution_tool_result_error: object` - `type: "code_execution_tool_result_error"` - `error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or "execution_time_exceeded"` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` ### Beta Code Execution Tool Result Error Code - `beta_code_execution_tool_result_error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or "execution_time_exceeded"` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` ### Beta Code Execution Tool Result Error Param - `beta_code_execution_tool_result_error_param: object` - `type: "code_execution_tool_result_error"` - `error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or "execution_time_exceeded"` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` ### Beta Compact 20260112 Edit - `beta_compact_20260112_edit: object` Automatically compact older context when reaching the configured trigger threshold. - `type: "compact_20260112"` - `instructions: optional string` Additional instructions for summarization. - `pause_after_compaction: optional boolean` Whether to pause after compaction and return the compaction block to the user. - `trigger: optional object` When to trigger compaction. Defaults to 150000 input tokens. - `type: "input_tokens"` - `value: number` minimum: 1 ### Beta Compaction Block - `beta_compaction_block: object` A compaction block returned when autocompact is triggered. When content is None, it indicates the compaction failed to produce a valid summary (e.g., malformed output from the model). Clients may round-trip compaction blocks with null content; the server treats them as no-ops. - `type: "compaction"` - `content: string` Summary of compacted content, or null if compaction failed - `encrypted_content: string` Opaque metadata from prior compaction, to be round-tripped verbatim - `signature: optional string` Signature over the summary, to be sent back with the block verbatim - `tool_changes: optional array of BetaResponseToolAdditionBlock or BetaResponseToolRemovalBlock` The tool changes of the compacted range: the `tool_addition` and `tool_removal` blocks that take the request's `tools` to the tool set in effect at the end of the range, or `[]` when the range changed no tool. Absent when the server did not compute them. Send the block back unchanged. - `beta_response_tool_addition_block: object` An entry of a `compaction` block's `tool_changes`: a tool the compacted range made available, as a reference to a `tools` entry or MCP toolset, or as the tool definition in effect at the end of the range, by value. Send it back unchanged. - `type: "tool_addition"` - `tool: BetaResponseToolChangeToolReference or BetaResponseToolChangeMCPToolReference or BetaResponseToolChangeMCPToolsetReference or BetaToolChangeToolDefinition` The tool made available: a reference to a `tools` entry or MCP toolset, or a `tool_definition` carrying the definition by value. - `beta_response_tool_change_tool_reference: object` Reference to a single tool, by the name the model uses to call it, as a `compaction` block's `tool_changes` entry reports it: a tool declared in `tools` or defined by an earlier `tool_addition` block. Send it back unchanged with the block. - `type: "tool_reference"` - `name: string` - `beta_response_tool_change_mcp_tool_reference: object` Reference to a single MCP tool, by its server and its name on that server, as a `compaction` block's `tool_changes` entry reports it. Send it back unchanged with the block. - `type: "mcp_tool_reference"` - `name: string` - `server_name: string` - `beta_response_tool_change_mcp_toolset_reference: object` Reference to every tool in the named MCP server's toolset, as a `compaction` block's `tool_changes` entry reports it. Send it back unchanged with the block. - `type: "mcp_toolset_reference"` - `server_name: string` - `beta_tool_change_tool_definition: object` A tool defined by value, as a `compaction` block's `tool_changes` entry reports it: `definition` is the tool's definition as it was sent, in the form of a `tools` entry, without `cache_control`. Send it back unchanged with the block. - `type: "tool_definition"` - `definition: BetaResponseTool or BetaToolBash20241022 or BetaToolBash20250124 or 25 more` - `beta_response_tool: object` A custom tool definition, as sent. - `type: optional "custom"` - `input_schema: object` [JSON schema](https://json-schema.org/draft/2020-12) for this tool's input. This defines the shape of the `input` that your tool accepts and that the model will produce. - `type: "object"` - `properties: optional map[unknown]` - `required: optional array of string` - `name: string` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. minLength: 1, maxLength: 128, pattern: ^[a-zA-Z0-9_-]{1,128}$ - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `description: optional string` Description of what this tool does. Tool descriptions should be as detailed as possible. The more information that the model has about what the tool is and how to use it, the better it will perform. You can use natural language descriptions to reinforce important aspects of the tool input JSON schema. - `eager_input_streaming: optional boolean` Enable eager input streaming for this tool. When true, tool input parameters will be streamed incrementally as they are generated, and types will be inferred on-the-fly rather than buffering the full JSON output. When false, streaming is disabled for this tool even if the fine-grained-tool-streaming beta is active. When null (default), uses the default behavior based on beta headers. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_bash_20241022: object` - `type: "bash_20241022"` - `name: "bash"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `"5m"` - `"1h"` - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_bash_20250124: object` - `type: "bash_20250124"` - `name: "bash"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_code_execution_tool_20250522: object` - `type: "code_execution_20250522"` - `name: "code_execution"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_code_execution_tool_20250825: object` - `type: "code_execution_20250825"` - `name: "code_execution"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_code_execution_tool_20260120: object` Code execution tool with REPL state persistence (daemon mode + gVisor checkpoint). - `type: "code_execution_20260120"` - `name: "code_execution"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_code_execution_tool_20260521: object` Code execution tool with REPL state persistence. - `type: "code_execution_20260521"` - `name: "code_execution"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_browser_toolset_20260801: object` The browser toolset: a single `tools[]` entry (carrying no `name`) that declares the browser tool family. The model is served the family's tool with any members disabled via `configs` removed from its schema. - `type: "browser_toolset_20260801"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `configs: optional object` Sparse per-member overrides, keyed by member name. Absent, null, and {} are equivalent; a member's defaults apply wherever its key is absent. - `type: optional object` `type`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `close_tab: optional object` `close_tab`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `double_click: optional object` `double_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `file_upload: optional object` `file_upload`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `find: optional object` `find`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `form_input: optional object` `form_input`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `get_page_text: optional object` `get_page_text`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `hold_key: optional object` `hold_key`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `hover: optional object` `hover`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `javascript_exec: optional object` `javascript_exec`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `key: optional object` `key`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_click: optional object` `left_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_click_drag: optional object` `left_click_drag`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_mouse_down: optional object` `left_mouse_down`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_mouse_up: optional object` `left_mouse_up`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `list_tabs: optional object` `list_tabs`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `middle_click: optional object` `middle_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `mouse_move: optional object` `mouse_move`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `navigate: optional object` `navigate`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `new_tab: optional object` `new_tab`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `read_console: optional object` `read_console`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `read_network: optional object` `read_network`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `read_page: optional object` `read_page`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `right_click: optional object` `right_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `screenshot: optional object` `screenshot`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `scroll: optional object` `scroll`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `scroll_to: optional object` `scroll_to`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `switch_tab: optional object` `switch_tab`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `triple_click: optional object` `triple_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `wait: optional object` `wait`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `zoom: optional object` `zoom`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `beta_tool_computer_use_20241022: object` - `type: "computer_20241022"` - `display_height_px: number` The height of the display in pixels. minimum: 1 - `display_width_px: number` The width of the display in pixels. minimum: 1 - `name: "computer"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `display_number: optional number` The X11 display number (e.g. 0, 1) for the display. minimum: 0 - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_memory_tool_20250818: object` - `type: "memory_20250818"` - `name: "memory"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_computer_use_20250124: object` - `type: "computer_20250124"` - `display_height_px: number` The height of the display in pixels. minimum: 1 - `display_width_px: number` The width of the display in pixels. minimum: 1 - `name: "computer"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `display_number: optional number` The X11 display number (e.g. 0, 1) for the display. minimum: 0 - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_text_editor_20241022: object` - `type: "text_editor_20241022"` - `name: "str_replace_editor"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_computer_use_20251124: object` - `type: "computer_20251124"` - `display_height_px: number` The height of the display in pixels. minimum: 1 - `display_width_px: number` The width of the display in pixels. minimum: 1 - `name: "computer"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `display_number: optional number` The X11 display number (e.g. 0, 1) for the display. minimum: 0 - `enable_zoom: optional boolean` Whether to enable an action to take a zoomed-in screenshot of the screen. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_computer_toolset_20260801: object` The computer toolset: a single `tools[]` entry (carrying no `name`) that declares the computer tool family. The model is served the family's tool with any members disabled via `configs` removed from its schema. Every member is enabled by default, zoom included. The single-tool options `display_number` and `enable_zoom` are not fields of a toolset entry — it carries only `type`, `configs`, and `cache_control`; zoom is controlled via `configs.zoom.enabled`. - `type: "computer_toolset_20260801"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `configs: optional object` Sparse per-member overrides, keyed by member name. Absent, null, and {} are equivalent; a member's defaults apply wherever its key is absent. - `type: optional object` `type`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `cursor_position: optional object` `cursor_position`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `double_click: optional object` `double_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `hold_key: optional object` `hold_key`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `key: optional object` `key`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_click: optional object` `left_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_click_drag: optional object` `left_click_drag`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_mouse_down: optional object` `left_mouse_down`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_mouse_up: optional object` `left_mouse_up`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `middle_click: optional object` `middle_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `mouse_move: optional object` `mouse_move`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `right_click: optional object` `right_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `screenshot: optional object` `screenshot`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `scroll: optional object` `scroll`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `triple_click: optional object` `triple_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `wait: optional object` `wait`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `zoom: optional object` `zoom`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `beta_tool_text_editor_20250124: object` - `type: "text_editor_20250124"` - `name: "str_replace_editor"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_text_editor_20250429: object` - `type: "text_editor_20250429"` - `name: "str_replace_based_edit_tool"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_text_editor_20250728: object` - `type: "text_editor_20250728"` - `name: "str_replace_based_edit_tool"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: optional array of map[unknown]` - `max_characters: optional number` Maximum number of characters to display when viewing a file. If not specified, defaults to displaying the full file. minimum: 1 - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_web_search_tool_20250305: object` - `type: "web_search_20250305"` - `name: "web_search"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: optional array of string` If provided, only these domains will be included in results. Cannot be used alongside `blocked_domains`. - `blocked_domains: optional array of string` If provided, these domains will never appear in results. Cannot be used alongside `allowed_domains`. - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `user_location: optional object` Parameters for the user's location. Used to provide more relevant search results. - `type: "approximate"` - `city: optional string` The city of the user. minLength: 1, maxLength: 255 - `country: optional string` The two letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1_alpha-2) of the user. minLength: 2, maxLength: 2 - `region: optional string` The region of the user. minLength: 1, maxLength: 255 - `timezone: optional string` The [IANA timezone](https://nodatime.org/TimeZones) of the user. minLength: 1, maxLength: 255 - `beta_web_fetch_tool_20250910: object` - `type: "web_fetch_20250910"` - `name: "web_fetch"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: optional array of string` List of domains to allow fetching from - `blocked_domains: optional array of string` List of domains to block fetching from - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `citations: optional object` Citations configuration for fetched documents. Citations are disabled by default. - `enabled: optional boolean` - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_content_tokens: optional number` Maximum number of tokens used by including web page text content in the context. The limit is approximate and does not apply to binary content such as PDFs. minimum: 1 - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `url_sources: optional object` Which sources contribute to the set of URLs the tool may fetch. Omitted means every source. - `client_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which client tools' results contribute fetchable URLs: "all", "none", or an only or except list of client tool names from tools[]. - `beta_web_fetch_url_source_all: object` The `url_sources` variant under which a source contributes in full: every result of the tool filter's source, or all user input. - `type: "all"` - `beta_web_fetch_url_source_none: object` The `url_sources` variant under which a source contributes nothing: no result of the tool filter's source, or no user input. - `type: "none"` - `beta_web_fetch_url_source_only: object` The tool filter variant under which only the named tools' results contribute. - `type: "only"` - `tools: array of BetaWebFetchURLSourceToolReference` - `type: "tool_reference"` - `name: string` - `beta_web_fetch_url_source_except: object` The tool filter variant under which every result but the named tools' contributes. - `type: "except"` - `tools: array of BetaWebFetchURLSourceToolReference` - `type: "tool_reference"` - `name: string` - `server_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which server tools' results contribute fetchable URLs: "all", "none", or an only or except list of server tool names from tools[]; only web_search and web_fetch results ever contribute. - `beta_web_fetch_url_source_all: object` The `url_sources` variant under which a source contributes in full: every result of the tool filter's source, or all user input. - `beta_web_fetch_url_source_none: object` The `url_sources` variant under which a source contributes nothing: no result of the tool filter's source, or no user input. - `beta_web_fetch_url_source_only: object` The tool filter variant under which only the named tools' results contribute. - `beta_web_fetch_url_source_except: object` The tool filter variant under which every result but the named tools' contributes. - `user_input: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone` Whether URLs in user messages are fetchable: "all" or "none". - `beta_web_fetch_url_source_all: object` The `url_sources` variant under which a source contributes in full: every result of the tool filter's source, or all user input. - `beta_web_fetch_url_source_none: object` The `url_sources` variant under which a source contributes nothing: no result of the tool filter's source, or no user input. - `beta_web_search_tool_20260209: object` - `type: "web_search_20260209"` - `name: "web_search"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: optional array of string` If provided, only these domains will be included in results. Cannot be used alongside `blocked_domains`. - `blocked_domains: optional array of string` If provided, these domains will never appear in results. Cannot be used alongside `allowed_domains`. - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `user_location: optional object` Parameters for the user's location. Used to provide more relevant search results. - `type: "approximate"` - `city: optional string` The city of the user. minLength: 1, maxLength: 255 - `country: optional string` The two letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1_alpha-2) of the user. minLength: 2, maxLength: 2 - `region: optional string` The region of the user. minLength: 1, maxLength: 255 - `timezone: optional string` The [IANA timezone](https://nodatime.org/TimeZones) of the user. minLength: 1, maxLength: 255 - `beta_web_fetch_tool_20260209: object` - `type: "web_fetch_20260209"` - `name: "web_fetch"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: optional array of string` List of domains to allow fetching from - `blocked_domains: optional array of string` List of domains to block fetching from - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `citations: optional object` Citations configuration for fetched documents. Citations are disabled by default. - `enabled: optional boolean` - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_content_tokens: optional number` Maximum number of tokens used by including web page text content in the context. The limit is approximate and does not apply to binary content such as PDFs. minimum: 1 - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `url_sources: optional object` Which sources contribute to the set of URLs the tool may fetch. Omitted means every source. - `client_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which client tools' results contribute fetchable URLs: "all", "none", or an only or except list of client tool names from tools[]. - `server_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which server tools' results contribute fetchable URLs: "all", "none", or an only or except list of server tool names from tools[]; only web_search and web_fetch results ever contribute. - `user_input: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone` Whether URLs in user messages are fetchable: "all" or "none". - `beta_web_fetch_tool_20260309: object` Web fetch tool with use_cache parameter for bypassing cached content. - `type: "web_fetch_20260309"` - `name: "web_fetch"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: optional array of string` List of domains to allow fetching from - `blocked_domains: optional array of string` List of domains to block fetching from - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `citations: optional object` Citations configuration for fetched documents. Citations are disabled by default. - `enabled: optional boolean` - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_content_tokens: optional number` Maximum number of tokens used by including web page text content in the context. The limit is approximate and does not apply to binary content such as PDFs. minimum: 1 - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `url_sources: optional object` Which sources contribute to the set of URLs the tool may fetch. Omitted means every source. - `client_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which client tools' results contribute fetchable URLs: "all", "none", or an only or except list of client tool names from tools[]. - `server_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which server tools' results contribute fetchable URLs: "all", "none", or an only or except list of server tool names from tools[]; only web_search and web_fetch results ever contribute. - `user_input: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone` Whether URLs in user messages are fetchable: "all" or "none". - `use_cache: optional boolean` Whether to use cached content. Set to false to bypass the cache and fetch fresh content. Only set to false when the user explicitly requests fresh content or when fetching rapidly-changing sources. - `beta_web_search_tool_20260318: object` - `type: "web_search_20260318"` - `name: "web_search"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: optional array of string` If provided, only these domains will be included in results. Cannot be used alongside `blocked_domains`. - `blocked_domains: optional array of string` If provided, these domains will never appear in results. Cannot be used alongside `allowed_domains`. - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `response_inclusion: optional "full" or "excluded"` How this tool's result blocks appear in the API response when the result was consumed by a completed code_execution call in the same turn. 'full' returns the complete content (default). 'excluded' drops the nested server_tool_use and result block pair entirely. Results from direct calls, or from code_execution calls that paused before completing, are always returned in full so they can be sent back on the next turn. - `"full"` - `"excluded"` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `user_location: optional object` Parameters for the user's location. Used to provide more relevant search results. - `type: "approximate"` - `city: optional string` The city of the user. minLength: 1, maxLength: 255 - `country: optional string` The two letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1_alpha-2) of the user. minLength: 2, maxLength: 2 - `region: optional string` The region of the user. minLength: 1, maxLength: 255 - `timezone: optional string` The [IANA timezone](https://nodatime.org/TimeZones) of the user. minLength: 1, maxLength: 255 - `beta_web_fetch_tool_20260318: object` - `type: "web_fetch_20260318"` - `name: "web_fetch"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: optional array of string` List of domains to allow fetching from - `blocked_domains: optional array of string` List of domains to block fetching from - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `citations: optional object` Citations configuration for fetched documents. Citations are disabled by default. - `enabled: optional boolean` - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_content_tokens: optional number` Maximum number of tokens used by including web page text content in the context. The limit is approximate and does not apply to binary content such as PDFs. minimum: 1 - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `response_inclusion: optional "full" or "excluded"` How this tool's result blocks appear in the API response when the result was consumed by a completed code_execution call in the same turn. 'full' returns the complete content (default). 'excluded' drops the nested server_tool_use and result block pair entirely. Results from direct calls, or from code_execution calls that paused before completing, are always returned in full so they can be sent back on the next turn. - `"full"` - `"excluded"` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `url_sources: optional object` Which sources contribute to the set of URLs the tool may fetch. Omitted means every source. - `client_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which client tools' results contribute fetchable URLs: "all", "none", or an only or except list of client tool names from tools[]. - `server_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which server tools' results contribute fetchable URLs: "all", "none", or an only or except list of server tool names from tools[]; only web_search and web_fetch results ever contribute. - `user_input: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone` Whether URLs in user messages are fetchable: "all" or "none". - `use_cache: optional boolean` Whether to use cached content. Set to false to bypass the cache and fetch fresh content. Only set to false when the user explicitly requests fresh content or when fetching rapidly-changing sources. - `beta_advisor_tool_20260301: object` - `type: "advisor_20260301"` - `model: "claude-haiku-5-5" or "claude-sonnet-5-5" or "claude-fable-5-1" or 17 more or string` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-haiku-5-5"` Fastest model for high-volume, real-time tasks - `"claude-sonnet-5-5"` Efficient model for coding and agents - `"claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows - `"claude-opus-5-5"` Powerful intelligence for coding, knowledge work, and long-running agents - `"claude-mythos-5-1"` Our most capable model for cybersecurity and biology research, available through trusted access programs - `"claude-sonnet-5"` Efficient model for coding and agents - `"claude-fable-5"` Next generation of intelligence for the hardest knowledge work and coding problems - `"claude-mythos-5"` Most capable model for cybersecurity and biology research - `"claude-opus-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-8"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-7"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-6"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-6"` Best combination of speed and intelligence - `"claude-haiku-4-5"` - `"claude-haiku-4-5-20251001"` - `"claude-opus-4-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-5-20251101"` Powerful intelligence for long-running agents and coding - `"claude-mythos-preview"` **Deprecated**: Will reach end-of-life on June 30, 2026. Please migrate to claude-mythos-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. New class of intelligence, strongest in coding and cybersecurity - `"claude-sonnet-4-5"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `"claude-sonnet-4-5-20250929"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `name: "advisor"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `caching: optional object` Caching for the advisor's own prompt. When set, each advisor call writes a cache entry at the given TTL so subsequent calls in the same conversation read the stable prefix. When omitted, the advisor prompt is not cached. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_tokens: optional number` Bounds the advisor's total output (thinking + text) per call. When the advisor hits this cap, the returned advisor_result or advisor_redacted_result block carries stop_reason='max_tokens', and a truncation note is appended to the advice text the worker model sees (inside the encrypted blob in redacted mode). When set, the server also emits a remaining-tokens budget block in the advisor's prompt so the advisor self-shapes toward the cap. When omitted, the advisor model's default output cap applies and no budget block is emitted. minimum: 1024 - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_search_tool_bm25_20251119: object` - `type: "tool_search_tool_bm25_20251119" or "tool_search_tool_bm25"` - `"tool_search_tool_bm25_20251119"` - `"tool_search_tool_bm25"` - `name: "tool_search_tool_bm25"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_search_tool_regex_20251119: object` - `type: "tool_search_tool_regex_20251119" or "tool_search_tool_regex"` - `"tool_search_tool_regex_20251119"` - `"tool_search_tool_regex"` - `name: "tool_search_tool_regex"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_mcp_toolset: object` Configuration for a group of tools from an MCP server. Allows configuring enabled status and defer_loading for all tools from an MCP server, with optional per-tool overrides. - `type: "mcp_toolset"` - `mcp_server_name: string` Name of the MCP server to configure tools for minLength: 1, maxLength: 255 - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `configs: optional map[BetaMCPToolConfig]` Configuration overrides for specific tools, keyed by tool name - `defer_loading: optional boolean` - `enabled: optional boolean` - `default_config: optional object` Default configuration applied to all tools from this server - `defer_loading: optional boolean` - `enabled: optional boolean` - `tools: optional array of BetaMCPToolParam` The server's tool listing, pinned: when present, the server is not asked for its tools before sampling and exactly these entries, with `default_config` and `configs` applied, are the toolset's tools. Copy it from the `mcp_tool_listing` block of an earlier response. - `input_schema: map[unknown]` The tool's input schema as the MCP server lists it, verbatim. - `name: string` The tool's name as the MCP server lists it (not prefixed with the server name). minLength: 1 - `description: optional string` The tool's description as the MCP server lists it. - `beta_response_tool_removal_block: object` An entry of a `compaction` block's `tool_changes`: a tool of the request's `tools` (or an MCP tool or toolset) that the compacted range withdrew. Send it back unchanged. - `type: "tool_removal"` - `tool: BetaResponseToolChangeToolReference or BetaResponseToolChangeMCPToolReference or BetaResponseToolChangeMCPToolsetReference` A reference to the withdrawn `tools` entry, MCP tool or MCP toolset. - `beta_response_tool_change_tool_reference: object` Reference to a single tool, by the name the model uses to call it, as a `compaction` block's `tool_changes` entry reports it: a tool declared in `tools` or defined by an earlier `tool_addition` block. Send it back unchanged with the block. - `beta_response_tool_change_mcp_tool_reference: object` Reference to a single MCP tool, by its server and its name on that server, as a `compaction` block's `tool_changes` entry reports it. Send it back unchanged with the block. - `beta_response_tool_change_mcp_toolset_reference: object` Reference to every tool in the named MCP server's toolset, as a `compaction` block's `tool_changes` entry reports it. Send it back unchanged with the block. ### Beta Compaction Block Param - `beta_compaction_block_param: object` A compaction block containing summary of previous context. Users should round-trip these blocks from responses to subsequent requests to maintain context across compaction boundaries. When content is None, the block represents a failed compaction. The server treats these as no-ops. Empty string content is not allowed. - `type: "compaction"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `"5m"` - `"1h"` - `content: optional string` Summary of previously compacted content, or null if compaction failed - `encrypted_content: optional string` Opaque metadata from prior compaction, to be round-tripped verbatim - `signature: optional string` The block's signature as returned, to be sent back verbatim - `tool_changes: optional array of BetaRequestToolAdditionBlock or BetaRequestToolRemovalBlock` The tool changes of the compacted range, as the server returned them on this block: the `tool_addition` and `tool_removal` entries that take the request's `tools` to the tool set in effect at the end of the range. Send them back unchanged with the block. - `beta_request_tool_addition_block: object` Mid-conversation directive to make a tool available. `tool` is a reference to a tool (or MCP toolset) declared in the request's `tools`. Under the `inline-tools-2026-09-15` beta it may instead be a reference to a tool defined earlier in `messages`, or a `tool_definition` object that carries an inline tool definition in `definition` (the same object a `tools` entry holds). An `mcp_toolset` definition also requires the `mcp-client-2026-09-15` beta. The tool is offered to the model from this point in the conversation onward. - `type: "tool_addition"` - `tool: BetaToolChangeToolReference or BetaToolChangeMCPToolReference or BetaToolChangeMCPToolsetReference or BetaToolChangeToolDefinitionParam` - `beta_tool_change_tool_reference: object` Reference to a single tool, by the name the model uses to call it: a tool declared in `tools` or defined by an earlier `tool_addition` block. Does not accept the composed `{server}_{name}` form the server assigns to MCP-resolved tools; use `mcp_tool_reference` or `mcp_toolset_reference` for those. - `type: "tool_reference"` - `name: string` pattern: ^[a-zA-Z0-9_-]{1,128}$ - `beta_tool_change_mcp_tool_reference: object` Reference to a single MCP tool by its server and remote name; the same `server_name`/`name` pair `mcp_tool_use` carries. - `type: "mcp_tool_reference"` - `name: string` - `server_name: string` - `beta_tool_change_mcp_toolset_reference: object` Reference to every tool in the named MCP server's toolset. - `type: "mcp_toolset_reference"` - `server_name: string` - `beta_tool_change_tool_definition_param: object` A tool defined by value: `definition` is a `tools` entry (any kind `tools` accepts, an MCP toolset included). An `mcp_toolset` given here also requires the `mcp-client-2026-09-15` beta. - `type: "tool_definition"` - `definition: BetaTool or BetaToolBash20241022 or BetaToolBash20250124 or 25 more` - `beta_tool: object` - `type: optional "custom"` - `input_schema: object` [JSON schema](https://json-schema.org/draft/2020-12) for this tool's input. This defines the shape of the `input` that your tool accepts and that the model will produce. - `type: "object"` - `properties: optional map[unknown]` - `required: optional array of string` - `name: string` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. minLength: 1, maxLength: 128, pattern: ^[a-zA-Z0-9_-]{1,128}$ - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `description: optional string` Description of what this tool does. Tool descriptions should be as detailed as possible. The more information that the model has about what the tool is and how to use it, the better it will perform. You can use natural language descriptions to reinforce important aspects of the tool input JSON schema. - `eager_input_streaming: optional boolean` Enable eager input streaming for this tool. When true, tool input parameters will be streamed incrementally as they are generated, and types will be inferred on-the-fly rather than buffering the full JSON output. When false, streaming is disabled for this tool even if the fine-grained-tool-streaming beta is active. When null (default), uses the default behavior based on beta headers. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_bash_20241022: object` - `type: "bash_20241022"` - `name: "bash"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_bash_20250124: object` - `type: "bash_20250124"` - `name: "bash"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_code_execution_tool_20250522: object` - `type: "code_execution_20250522"` - `name: "code_execution"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_code_execution_tool_20250825: object` - `type: "code_execution_20250825"` - `name: "code_execution"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_code_execution_tool_20260120: object` Code execution tool with REPL state persistence (daemon mode + gVisor checkpoint). - `type: "code_execution_20260120"` - `name: "code_execution"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_code_execution_tool_20260521: object` Code execution tool with REPL state persistence. - `type: "code_execution_20260521"` - `name: "code_execution"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_browser_toolset_20260801: object` The browser toolset: a single `tools[]` entry (carrying no `name`) that declares the browser tool family. The model is served the family's tool with any members disabled via `configs` removed from its schema. - `type: "browser_toolset_20260801"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `configs: optional object` Sparse per-member overrides, keyed by member name. Absent, null, and {} are equivalent; a member's defaults apply wherever its key is absent. - `type: optional object` `type`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `close_tab: optional object` `close_tab`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `double_click: optional object` `double_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `file_upload: optional object` `file_upload`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `find: optional object` `find`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `form_input: optional object` `form_input`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `get_page_text: optional object` `get_page_text`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `hold_key: optional object` `hold_key`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `hover: optional object` `hover`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `javascript_exec: optional object` `javascript_exec`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `key: optional object` `key`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_click: optional object` `left_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_click_drag: optional object` `left_click_drag`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_mouse_down: optional object` `left_mouse_down`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_mouse_up: optional object` `left_mouse_up`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `list_tabs: optional object` `list_tabs`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `middle_click: optional object` `middle_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `mouse_move: optional object` `mouse_move`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `navigate: optional object` `navigate`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `new_tab: optional object` `new_tab`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `read_console: optional object` `read_console`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `read_network: optional object` `read_network`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `read_page: optional object` `read_page`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `right_click: optional object` `right_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `screenshot: optional object` `screenshot`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `scroll: optional object` `scroll`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `scroll_to: optional object` `scroll_to`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `switch_tab: optional object` `switch_tab`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `triple_click: optional object` `triple_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `wait: optional object` `wait`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `zoom: optional object` `zoom`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `beta_tool_computer_use_20241022: object` - `type: "computer_20241022"` - `display_height_px: number` The height of the display in pixels. minimum: 1 - `display_width_px: number` The width of the display in pixels. minimum: 1 - `name: "computer"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `display_number: optional number` The X11 display number (e.g. 0, 1) for the display. minimum: 0 - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_memory_tool_20250818: object` - `type: "memory_20250818"` - `name: "memory"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_computer_use_20250124: object` - `type: "computer_20250124"` - `display_height_px: number` The height of the display in pixels. minimum: 1 - `display_width_px: number` The width of the display in pixels. minimum: 1 - `name: "computer"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `display_number: optional number` The X11 display number (e.g. 0, 1) for the display. minimum: 0 - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_text_editor_20241022: object` - `type: "text_editor_20241022"` - `name: "str_replace_editor"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_computer_use_20251124: object` - `type: "computer_20251124"` - `display_height_px: number` The height of the display in pixels. minimum: 1 - `display_width_px: number` The width of the display in pixels. minimum: 1 - `name: "computer"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `display_number: optional number` The X11 display number (e.g. 0, 1) for the display. minimum: 0 - `enable_zoom: optional boolean` Whether to enable an action to take a zoomed-in screenshot of the screen. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_computer_toolset_20260801: object` The computer toolset: a single `tools[]` entry (carrying no `name`) that declares the computer tool family. The model is served the family's tool with any members disabled via `configs` removed from its schema. Every member is enabled by default, zoom included. The single-tool options `display_number` and `enable_zoom` are not fields of a toolset entry — it carries only `type`, `configs`, and `cache_control`; zoom is controlled via `configs.zoom.enabled`. - `type: "computer_toolset_20260801"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `configs: optional object` Sparse per-member overrides, keyed by member name. Absent, null, and {} are equivalent; a member's defaults apply wherever its key is absent. - `type: optional object` `type`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `cursor_position: optional object` `cursor_position`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `double_click: optional object` `double_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `hold_key: optional object` `hold_key`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `key: optional object` `key`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_click: optional object` `left_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_click_drag: optional object` `left_click_drag`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_mouse_down: optional object` `left_mouse_down`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_mouse_up: optional object` `left_mouse_up`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `middle_click: optional object` `middle_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `mouse_move: optional object` `mouse_move`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `right_click: optional object` `right_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `screenshot: optional object` `screenshot`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `scroll: optional object` `scroll`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `triple_click: optional object` `triple_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `wait: optional object` `wait`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `zoom: optional object` `zoom`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `beta_tool_text_editor_20250124: object` - `type: "text_editor_20250124"` - `name: "str_replace_editor"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_text_editor_20250429: object` - `type: "text_editor_20250429"` - `name: "str_replace_based_edit_tool"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_text_editor_20250728: object` - `type: "text_editor_20250728"` - `name: "str_replace_based_edit_tool"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: optional array of map[unknown]` - `max_characters: optional number` Maximum number of characters to display when viewing a file. If not specified, defaults to displaying the full file. minimum: 1 - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_web_search_tool_20250305: object` - `type: "web_search_20250305"` - `name: "web_search"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: optional array of string` If provided, only these domains will be included in results. Cannot be used alongside `blocked_domains`. - `blocked_domains: optional array of string` If provided, these domains will never appear in results. Cannot be used alongside `allowed_domains`. - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `user_location: optional object` Parameters for the user's location. Used to provide more relevant search results. - `type: "approximate"` - `city: optional string` The city of the user. minLength: 1, maxLength: 255 - `country: optional string` The two letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1_alpha-2) of the user. minLength: 2, maxLength: 2 - `region: optional string` The region of the user. minLength: 1, maxLength: 255 - `timezone: optional string` The [IANA timezone](https://nodatime.org/TimeZones) of the user. minLength: 1, maxLength: 255 - `beta_web_fetch_tool_20250910: object` - `type: "web_fetch_20250910"` - `name: "web_fetch"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: optional array of string` List of domains to allow fetching from - `blocked_domains: optional array of string` List of domains to block fetching from - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `citations: optional object` Citations configuration for fetched documents. Citations are disabled by default. - `enabled: optional boolean` - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_content_tokens: optional number` Maximum number of tokens used by including web page text content in the context. The limit is approximate and does not apply to binary content such as PDFs. minimum: 1 - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `url_sources: optional object` Which sources contribute to the set of URLs the tool may fetch. Omitted means every source. - `client_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which client tools' results contribute fetchable URLs: "all", "none", or an only or except list of client tool names from tools[]. - `beta_web_fetch_url_source_all: object` The `url_sources` variant under which a source contributes in full: every result of the tool filter's source, or all user input. - `type: "all"` - `beta_web_fetch_url_source_none: object` The `url_sources` variant under which a source contributes nothing: no result of the tool filter's source, or no user input. - `type: "none"` - `beta_web_fetch_url_source_only: object` The tool filter variant under which only the named tools' results contribute. - `type: "only"` - `tools: array of BetaWebFetchURLSourceToolReference` - `type: "tool_reference"` - `name: string` - `beta_web_fetch_url_source_except: object` The tool filter variant under which every result but the named tools' contributes. - `type: "except"` - `tools: array of BetaWebFetchURLSourceToolReference` - `type: "tool_reference"` - `name: string` - `server_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which server tools' results contribute fetchable URLs: "all", "none", or an only or except list of server tool names from tools[]; only web_search and web_fetch results ever contribute. - `beta_web_fetch_url_source_all: object` The `url_sources` variant under which a source contributes in full: every result of the tool filter's source, or all user input. - `beta_web_fetch_url_source_none: object` The `url_sources` variant under which a source contributes nothing: no result of the tool filter's source, or no user input. - `beta_web_fetch_url_source_only: object` The tool filter variant under which only the named tools' results contribute. - `beta_web_fetch_url_source_except: object` The tool filter variant under which every result but the named tools' contributes. - `user_input: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone` Whether URLs in user messages are fetchable: "all" or "none". - `beta_web_fetch_url_source_all: object` The `url_sources` variant under which a source contributes in full: every result of the tool filter's source, or all user input. - `beta_web_fetch_url_source_none: object` The `url_sources` variant under which a source contributes nothing: no result of the tool filter's source, or no user input. - `beta_web_search_tool_20260209: object` - `type: "web_search_20260209"` - `name: "web_search"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: optional array of string` If provided, only these domains will be included in results. Cannot be used alongside `blocked_domains`. - `blocked_domains: optional array of string` If provided, these domains will never appear in results. Cannot be used alongside `allowed_domains`. - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `user_location: optional object` Parameters for the user's location. Used to provide more relevant search results. - `type: "approximate"` - `city: optional string` The city of the user. minLength: 1, maxLength: 255 - `country: optional string` The two letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1_alpha-2) of the user. minLength: 2, maxLength: 2 - `region: optional string` The region of the user. minLength: 1, maxLength: 255 - `timezone: optional string` The [IANA timezone](https://nodatime.org/TimeZones) of the user. minLength: 1, maxLength: 255 - `beta_web_fetch_tool_20260209: object` - `type: "web_fetch_20260209"` - `name: "web_fetch"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: optional array of string` List of domains to allow fetching from - `blocked_domains: optional array of string` List of domains to block fetching from - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `citations: optional object` Citations configuration for fetched documents. Citations are disabled by default. - `enabled: optional boolean` - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_content_tokens: optional number` Maximum number of tokens used by including web page text content in the context. The limit is approximate and does not apply to binary content such as PDFs. minimum: 1 - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `url_sources: optional object` Which sources contribute to the set of URLs the tool may fetch. Omitted means every source. - `client_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which client tools' results contribute fetchable URLs: "all", "none", or an only or except list of client tool names from tools[]. - `server_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which server tools' results contribute fetchable URLs: "all", "none", or an only or except list of server tool names from tools[]; only web_search and web_fetch results ever contribute. - `user_input: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone` Whether URLs in user messages are fetchable: "all" or "none". - `beta_web_fetch_tool_20260309: object` Web fetch tool with use_cache parameter for bypassing cached content. - `type: "web_fetch_20260309"` - `name: "web_fetch"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: optional array of string` List of domains to allow fetching from - `blocked_domains: optional array of string` List of domains to block fetching from - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `citations: optional object` Citations configuration for fetched documents. Citations are disabled by default. - `enabled: optional boolean` - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_content_tokens: optional number` Maximum number of tokens used by including web page text content in the context. The limit is approximate and does not apply to binary content such as PDFs. minimum: 1 - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `url_sources: optional object` Which sources contribute to the set of URLs the tool may fetch. Omitted means every source. - `client_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which client tools' results contribute fetchable URLs: "all", "none", or an only or except list of client tool names from tools[]. - `server_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which server tools' results contribute fetchable URLs: "all", "none", or an only or except list of server tool names from tools[]; only web_search and web_fetch results ever contribute. - `user_input: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone` Whether URLs in user messages are fetchable: "all" or "none". - `use_cache: optional boolean` Whether to use cached content. Set to false to bypass the cache and fetch fresh content. Only set to false when the user explicitly requests fresh content or when fetching rapidly-changing sources. - `beta_web_search_tool_20260318: object` - `type: "web_search_20260318"` - `name: "web_search"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: optional array of string` If provided, only these domains will be included in results. Cannot be used alongside `blocked_domains`. - `blocked_domains: optional array of string` If provided, these domains will never appear in results. Cannot be used alongside `allowed_domains`. - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `response_inclusion: optional "full" or "excluded"` How this tool's result blocks appear in the API response when the result was consumed by a completed code_execution call in the same turn. 'full' returns the complete content (default). 'excluded' drops the nested server_tool_use and result block pair entirely. Results from direct calls, or from code_execution calls that paused before completing, are always returned in full so they can be sent back on the next turn. - `"full"` - `"excluded"` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `user_location: optional object` Parameters for the user's location. Used to provide more relevant search results. - `type: "approximate"` - `city: optional string` The city of the user. minLength: 1, maxLength: 255 - `country: optional string` The two letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1_alpha-2) of the user. minLength: 2, maxLength: 2 - `region: optional string` The region of the user. minLength: 1, maxLength: 255 - `timezone: optional string` The [IANA timezone](https://nodatime.org/TimeZones) of the user. minLength: 1, maxLength: 255 - `beta_web_fetch_tool_20260318: object` - `type: "web_fetch_20260318"` - `name: "web_fetch"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: optional array of string` List of domains to allow fetching from - `blocked_domains: optional array of string` List of domains to block fetching from - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `citations: optional object` Citations configuration for fetched documents. Citations are disabled by default. - `enabled: optional boolean` - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_content_tokens: optional number` Maximum number of tokens used by including web page text content in the context. The limit is approximate and does not apply to binary content such as PDFs. minimum: 1 - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `response_inclusion: optional "full" or "excluded"` How this tool's result blocks appear in the API response when the result was consumed by a completed code_execution call in the same turn. 'full' returns the complete content (default). 'excluded' drops the nested server_tool_use and result block pair entirely. Results from direct calls, or from code_execution calls that paused before completing, are always returned in full so they can be sent back on the next turn. - `"full"` - `"excluded"` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `url_sources: optional object` Which sources contribute to the set of URLs the tool may fetch. Omitted means every source. - `client_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which client tools' results contribute fetchable URLs: "all", "none", or an only or except list of client tool names from tools[]. - `server_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which server tools' results contribute fetchable URLs: "all", "none", or an only or except list of server tool names from tools[]; only web_search and web_fetch results ever contribute. - `user_input: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone` Whether URLs in user messages are fetchable: "all" or "none". - `use_cache: optional boolean` Whether to use cached content. Set to false to bypass the cache and fetch fresh content. Only set to false when the user explicitly requests fresh content or when fetching rapidly-changing sources. - `beta_advisor_tool_20260301: object` - `type: "advisor_20260301"` - `model: "claude-haiku-5-5" or "claude-sonnet-5-5" or "claude-fable-5-1" or 17 more or string` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-haiku-5-5"` Fastest model for high-volume, real-time tasks - `"claude-sonnet-5-5"` Efficient model for coding and agents - `"claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows - `"claude-opus-5-5"` Powerful intelligence for coding, knowledge work, and long-running agents - `"claude-mythos-5-1"` Our most capable model for cybersecurity and biology research, available through trusted access programs - `"claude-sonnet-5"` Efficient model for coding and agents - `"claude-fable-5"` Next generation of intelligence for the hardest knowledge work and coding problems - `"claude-mythos-5"` Most capable model for cybersecurity and biology research - `"claude-opus-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-8"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-7"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-6"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-6"` Best combination of speed and intelligence - `"claude-haiku-4-5"` - `"claude-haiku-4-5-20251001"` - `"claude-opus-4-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-5-20251101"` Powerful intelligence for long-running agents and coding - `"claude-mythos-preview"` **Deprecated**: Will reach end-of-life on June 30, 2026. Please migrate to claude-mythos-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. New class of intelligence, strongest in coding and cybersecurity - `"claude-sonnet-4-5"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `"claude-sonnet-4-5-20250929"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `name: "advisor"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `caching: optional object` Caching for the advisor's own prompt. When set, each advisor call writes a cache entry at the given TTL so subsequent calls in the same conversation read the stable prefix. When omitted, the advisor prompt is not cached. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_tokens: optional number` Bounds the advisor's total output (thinking + text) per call. When the advisor hits this cap, the returned advisor_result or advisor_redacted_result block carries stop_reason='max_tokens', and a truncation note is appended to the advice text the worker model sees (inside the encrypted blob in redacted mode). When set, the server also emits a remaining-tokens budget block in the advisor's prompt so the advisor self-shapes toward the cap. When omitted, the advisor model's default output cap applies and no budget block is emitted. minimum: 1024 - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_search_tool_bm25_20251119: object` - `type: "tool_search_tool_bm25_20251119" or "tool_search_tool_bm25"` - `"tool_search_tool_bm25_20251119"` - `"tool_search_tool_bm25"` - `name: "tool_search_tool_bm25"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_search_tool_regex_20251119: object` - `type: "tool_search_tool_regex_20251119" or "tool_search_tool_regex"` - `"tool_search_tool_regex_20251119"` - `"tool_search_tool_regex"` - `name: "tool_search_tool_regex"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_mcp_toolset: object` Configuration for a group of tools from an MCP server. Allows configuring enabled status and defer_loading for all tools from an MCP server, with optional per-tool overrides. - `type: "mcp_toolset"` - `mcp_server_name: string` Name of the MCP server to configure tools for minLength: 1, maxLength: 255 - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `configs: optional map[BetaMCPToolConfig]` Configuration overrides for specific tools, keyed by tool name - `defer_loading: optional boolean` - `enabled: optional boolean` - `default_config: optional object` Default configuration applied to all tools from this server - `defer_loading: optional boolean` - `enabled: optional boolean` - `tools: optional array of BetaMCPToolParam` The server's tool listing, pinned: when present, the server is not asked for its tools before sampling and exactly these entries, with `default_config` and `configs` applied, are the toolset's tools. Copy it from the `mcp_tool_listing` block of an earlier response. - `input_schema: map[unknown]` The tool's input schema as the MCP server lists it, verbatim. - `name: string` The tool's name as the MCP server lists it (not prefixed with the server name). minLength: 1 - `description: optional string` The tool's description as the MCP server lists it. - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `beta_request_tool_removal_block: object` Mid-conversation directive to withdraw a tool. `tool` references a tool (or MCP toolset) by name: one declared in the request's `tools` or defined earlier in `messages`. It is no longer offered to the model from this point in the conversation onward. - `type: "tool_removal"` - `tool: BetaToolChangeToolReference or BetaToolChangeMCPToolReference or BetaToolChangeMCPToolsetReference` - `beta_tool_change_tool_reference: object` Reference to a single tool, by the name the model uses to call it: a tool declared in `tools` or defined by an earlier `tool_addition` block. Does not accept the composed `{server}_{name}` form the server assigns to MCP-resolved tools; use `mcp_tool_reference` or `mcp_toolset_reference` for those. - `beta_tool_change_mcp_tool_reference: object` Reference to a single MCP tool by its server and remote name; the same `server_name`/`name` pair `mcp_tool_use` carries. - `beta_tool_change_mcp_toolset_reference: object` Reference to every tool in the named MCP server's toolset. - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. ### Beta Compaction Config - `beta_compaction_config: object` Compact the whole conversation and return a signed `compaction` block, alone, that a later request sends back first in `messages`, in place of the messages it summarizes. There is no trigger and no pause flag: sending the parameter compacts, and nothing is sampled after the block. The summarization prompt is the server's own unless `instructions` are given, which then replace it for this request; a value that is empty or only whitespace counts as absent. - `type: "summarize"` - `instructions: optional string` Replaces the server's default summarization prompt for this request. An empty or whitespace-only value counts as absent. maxLength: 16384 ### Beta Compaction Content Block Delta - `beta_compaction_content_block_delta: object` - `type: "compaction_delta"` - `content: string` - `encrypted_content: string` Opaque metadata from prior compaction, to be round-tripped verbatim ### Beta Compaction Iteration Usage - `beta_compaction_iteration_usage: object` Token usage for a compaction iteration. - `type: "compaction"` Usage for a compaction iteration - `cache_creation: object` Breakdown of cached tokens by TTL - `ephemeral_1h_input_tokens: number` The number of input tokens used to create the 1 hour cache entry. minimum: 0 - `ephemeral_5m_input_tokens: number` The number of input tokens used to create the 5 minute cache entry. minimum: 0 - `cache_creation_input_tokens: number` The number of input tokens used to create the cache entry. minimum: 0 - `cache_read_input_tokens: number` The number of input tokens read from the cache. minimum: 0 - `input_tokens: number` The number of input tokens which were used. minimum: 0 - `output_tokens: number` The number of output tokens which were used. minimum: 0 ### Beta Computer Cursor Position Config - `beta_computer_cursor_position_config: object` `cursor_position`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. ### Beta Computer Cursor Position Input - `beta_computer_cursor_position_input: object` Get the current (x, y) pixel coordinate of the cursor. ### Beta Computer Cursor Position Tool Use Block - `beta_computer_cursor_position_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Get the current (x, y) pixel coordinate of the cursor. - `name: "cursor_position"` - `toolset_name: "computer"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `type: "direct"` - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `type: "code_execution_20250825"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `beta_server_tool_caller_20260120: object` - `type: "code_execution_20260120"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ ### Beta Computer Double Click Config - `beta_computer_double_click_config: object` `double_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. ### Beta Computer Double Click Input - `beta_computer_double_click_input: object` Double-click the left mouse button at the specified (x, y) pixel coordinate, or the current cursor position if `coordinate` is omitted. - `coordinate: optional array of number` (x, y): x pixels from the left edge, y pixels from the top edge. minItems: 2, maxItems: 2 - `text: optional string` Optional key combination to hold down during this action (e.g. "ctrl", "shift", "ctrl+shift"). ### Beta Computer Double Click Tool Use Block - `beta_computer_double_click_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Double-click the left mouse button at the specified (x, y) pixel coordinate, or the current cursor position if `coordinate` is omitted. - `coordinate: optional array of number` (x, y): x pixels from the left edge, y pixels from the top edge. minItems: 2, maxItems: 2 - `text: optional string` Optional key combination to hold down during this action (e.g. "ctrl", "shift", "ctrl+shift"). - `name: "double_click"` - `toolset_name: "computer"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `type: "direct"` - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `type: "code_execution_20250825"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `beta_server_tool_caller_20260120: object` - `type: "code_execution_20260120"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ ### Beta Computer Hold Key Config - `beta_computer_hold_key_config: object` `hold_key`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. ### Beta Computer Hold Key Input - `beta_computer_hold_key_input: object` Hold down a key or key-combination for a specified duration. Uses the same key syntax as `key`. - `duration: number` Duration to hold the key, in seconds. maximum: 300 - `text: string` The key or key-combination to hold. ### Beta Computer Hold Key Tool Use Block - `beta_computer_hold_key_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Hold down a key or key-combination for a specified duration. Uses the same key syntax as `key`. - `duration: number` Duration to hold the key, in seconds. maximum: 300 - `text: string` The key or key-combination to hold. - `name: "hold_key"` - `toolset_name: "computer"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `type: "direct"` - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `type: "code_execution_20250825"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `beta_server_tool_caller_20260120: object` - `type: "code_execution_20260120"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ ### Beta Computer Key Config - `beta_computer_key_config: object` `key`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. ### Beta Computer Key Input - `beta_computer_key_input: object` Press a key or key-combination on the keyboard. Use "+" to combine modifiers with a key (e.g. "ctrl+s", "alt+Tab", "ctrl+shift+Escape"). Key names are case-insensitive; common names like "Return", "Tab", "Escape", "Up", "Down", "Left", "Right", "Home", "End", "Page_Up", "Page_Down", "Delete", "BackSpace" are supported. - `text: string` The key or key-combination to press. - `repeat: optional number` Number of times to repeat the key press. Default is 1. minimum: 1, maximum: 100 ### Beta Computer Key Tool Use Block - `beta_computer_key_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Press a key or key-combination on the keyboard. Use "+" to combine modifiers with a key (e.g. "ctrl+s", "alt+Tab", "ctrl+shift+Escape"). Key names are case-insensitive; common names like "Return", "Tab", "Escape", "Up", "Down", "Left", "Right", "Home", "End", "Page_Up", "Page_Down", "Delete", "BackSpace" are supported. - `text: string` The key or key-combination to press. - `repeat: optional number` Number of times to repeat the key press. Default is 1. minimum: 1, maximum: 100 - `name: "key"` - `toolset_name: "computer"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `type: "direct"` - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `type: "code_execution_20250825"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `beta_server_tool_caller_20260120: object` - `type: "code_execution_20260120"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ ### Beta Computer Left Click Config - `beta_computer_left_click_config: object` `left_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. ### Beta Computer Left Click Drag Config - `beta_computer_left_click_drag_config: object` `left_click_drag`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. ### Beta Computer Left Click Drag Input - `beta_computer_left_click_drag_input: object` Click and drag the cursor from `start_coordinate` to `coordinate`. - `coordinate: array of number` (x, y): x pixels from the left edge, y pixels from the top edge. minItems: 2, maxItems: 2 - `start_coordinate: array of number` (x, y): x pixels from the left edge, y pixels from the top edge. minItems: 2, maxItems: 2 - `text: optional string` Optional key combination to hold down during this action (e.g. "ctrl", "shift", "ctrl+shift"). ### Beta Computer Left Click Drag Tool Use Block - `beta_computer_left_click_drag_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Click and drag the cursor from `start_coordinate` to `coordinate`. - `coordinate: array of number` (x, y): x pixels from the left edge, y pixels from the top edge. minItems: 2, maxItems: 2 - `start_coordinate: array of number` (x, y): x pixels from the left edge, y pixels from the top edge. minItems: 2, maxItems: 2 - `text: optional string` Optional key combination to hold down during this action (e.g. "ctrl", "shift", "ctrl+shift"). - `name: "left_click_drag"` - `toolset_name: "computer"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `type: "direct"` - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `type: "code_execution_20250825"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `beta_server_tool_caller_20260120: object` - `type: "code_execution_20260120"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ ### Beta Computer Left Click Input - `beta_computer_left_click_input: object` Click the left mouse button at the specified (x, y) pixel coordinate, or the current cursor position if `coordinate` is omitted. - `coordinate: optional array of number` (x, y): x pixels from the left edge, y pixels from the top edge. minItems: 2, maxItems: 2 - `text: optional string` Optional key combination to hold down during this action (e.g. "ctrl", "shift", "ctrl+shift"). ### Beta Computer Left Click Tool Use Block - `beta_computer_left_click_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Click the left mouse button at the specified (x, y) pixel coordinate, or the current cursor position if `coordinate` is omitted. - `coordinate: optional array of number` (x, y): x pixels from the left edge, y pixels from the top edge. minItems: 2, maxItems: 2 - `text: optional string` Optional key combination to hold down during this action (e.g. "ctrl", "shift", "ctrl+shift"). - `name: "left_click"` - `toolset_name: "computer"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `type: "direct"` - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `type: "code_execution_20250825"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `beta_server_tool_caller_20260120: object` - `type: "code_execution_20260120"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ ### Beta Computer Left Mouse Down Config - `beta_computer_left_mouse_down_config: object` `left_mouse_down`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. ### Beta Computer Left Mouse Down Input - `beta_computer_left_mouse_down_input: object` Press and hold the left mouse button at the current cursor position. ### Beta Computer Left Mouse Down Tool Use Block - `beta_computer_left_mouse_down_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Press and hold the left mouse button at the current cursor position. - `name: "left_mouse_down"` - `toolset_name: "computer"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `type: "direct"` - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `type: "code_execution_20250825"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `beta_server_tool_caller_20260120: object` - `type: "code_execution_20260120"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ ### Beta Computer Left Mouse Up Config - `beta_computer_left_mouse_up_config: object` `left_mouse_up`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. ### Beta Computer Left Mouse Up Input - `beta_computer_left_mouse_up_input: object` Release the left mouse button. ### Beta Computer Left Mouse Up Tool Use Block - `beta_computer_left_mouse_up_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Release the left mouse button. - `name: "left_mouse_up"` - `toolset_name: "computer"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `type: "direct"` - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `type: "code_execution_20250825"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `beta_server_tool_caller_20260120: object` - `type: "code_execution_20260120"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ ### Beta Computer Middle Click Config - `beta_computer_middle_click_config: object` `middle_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. ### Beta Computer Middle Click Input - `beta_computer_middle_click_input: object` Click the middle mouse button at the specified (x, y) pixel coordinate, or the current cursor position if `coordinate` is omitted. - `coordinate: optional array of number` (x, y): x pixels from the left edge, y pixels from the top edge. minItems: 2, maxItems: 2 - `text: optional string` Optional key combination to hold down during this action (e.g. "ctrl", "shift", "ctrl+shift"). ### Beta Computer Middle Click Tool Use Block - `beta_computer_middle_click_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Click the middle mouse button at the specified (x, y) pixel coordinate, or the current cursor position if `coordinate` is omitted. - `coordinate: optional array of number` (x, y): x pixels from the left edge, y pixels from the top edge. minItems: 2, maxItems: 2 - `text: optional string` Optional key combination to hold down during this action (e.g. "ctrl", "shift", "ctrl+shift"). - `name: "middle_click"` - `toolset_name: "computer"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `type: "direct"` - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `type: "code_execution_20250825"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `beta_server_tool_caller_20260120: object` - `type: "code_execution_20260120"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ ### Beta Computer Mouse Move Config - `beta_computer_mouse_move_config: object` `mouse_move`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. ### Beta Computer Mouse Move Input - `beta_computer_mouse_move_input: object` Move the cursor to a specified (x, y) pixel coordinate. Use this ONLY to hover without clicking; otherwise use a click action directly. - `coordinate: array of number` (x, y): x pixels from the left edge, y pixels from the top edge. minItems: 2, maxItems: 2 ### Beta Computer Mouse Move Tool Use Block - `beta_computer_mouse_move_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Move the cursor to a specified (x, y) pixel coordinate. Use this ONLY to hover without clicking; otherwise use a click action directly. - `coordinate: array of number` (x, y): x pixels from the left edge, y pixels from the top edge. minItems: 2, maxItems: 2 - `name: "mouse_move"` - `toolset_name: "computer"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `type: "direct"` - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `type: "code_execution_20250825"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `beta_server_tool_caller_20260120: object` - `type: "code_execution_20260120"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ ### Beta Computer Right Click Config - `beta_computer_right_click_config: object` `right_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. ### Beta Computer Right Click Input - `beta_computer_right_click_input: object` Click the right mouse button at the specified (x, y) pixel coordinate, or the current cursor position if `coordinate` is omitted. - `coordinate: optional array of number` (x, y): x pixels from the left edge, y pixels from the top edge. minItems: 2, maxItems: 2 - `text: optional string` Optional key combination to hold down during this action (e.g. "ctrl", "shift", "ctrl+shift"). ### Beta Computer Right Click Tool Use Block - `beta_computer_right_click_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Click the right mouse button at the specified (x, y) pixel coordinate, or the current cursor position if `coordinate` is omitted. - `coordinate: optional array of number` (x, y): x pixels from the left edge, y pixels from the top edge. minItems: 2, maxItems: 2 - `text: optional string` Optional key combination to hold down during this action (e.g. "ctrl", "shift", "ctrl+shift"). - `name: "right_click"` - `toolset_name: "computer"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `type: "direct"` - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `type: "code_execution_20250825"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `beta_server_tool_caller_20260120: object` - `type: "code_execution_20260120"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ ### Beta Computer Screenshot Config - `beta_computer_screenshot_config: object` `screenshot`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. ### Beta Computer Screenshot Input - `beta_computer_screenshot_input: object` Take a screenshot of the screen. ### Beta Computer Screenshot Tool Use Block - `beta_computer_screenshot_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Take a screenshot of the screen. - `name: "screenshot"` - `toolset_name: "computer"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `type: "direct"` - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `type: "code_execution_20250825"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `beta_server_tool_caller_20260120: object` - `type: "code_execution_20260120"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ ### Beta Computer Scroll Config - `beta_computer_scroll_config: object` `scroll`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. ### Beta Computer Scroll Direction - `beta_computer_scroll_direction: "up" or "down" or "left" or "right"` - `"up"` - `"down"` - `"left"` - `"right"` ### Beta Computer Scroll Input - `beta_computer_scroll_input: object` Scroll the screen at the specified (x, y) pixel coordinate, or the current cursor position if `coordinate` is omitted. Do NOT use PageUp/PageDown to scroll. - `scroll_amount: number` Number of 'clicks' of the scroll wheel. - `scroll_direction: "up" or "down" or "left" or "right"` - `"up"` - `"down"` - `"left"` - `"right"` - `coordinate: optional array of number` (x, y): x pixels from the left edge, y pixels from the top edge. minItems: 2, maxItems: 2 - `text: optional string` Optional key combination to hold down during this action (e.g. "ctrl", "shift", "ctrl+shift"). ### Beta Computer Scroll Tool Use Block - `beta_computer_scroll_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Scroll the screen at the specified (x, y) pixel coordinate, or the current cursor position if `coordinate` is omitted. Do NOT use PageUp/PageDown to scroll. - `scroll_amount: number` Number of 'clicks' of the scroll wheel. - `scroll_direction: "up" or "down" or "left" or "right"` - `"up"` - `"down"` - `"left"` - `"right"` - `coordinate: optional array of number` (x, y): x pixels from the left edge, y pixels from the top edge. minItems: 2, maxItems: 2 - `text: optional string` Optional key combination to hold down during this action (e.g. "ctrl", "shift", "ctrl+shift"). - `name: "scroll"` - `toolset_name: "computer"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `type: "direct"` - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `type: "code_execution_20250825"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `beta_server_tool_caller_20260120: object` - `type: "code_execution_20260120"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ ### Beta Computer Tool Use Block - `beta_computer_tool_use_block: BetaComputerKeyToolUseBlock or BetaComputerHoldKeyToolUseBlock or BetaComputerTypeToolUseBlock or 14 more` - `beta_computer_key_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Press a key or key-combination on the keyboard. Use "+" to combine modifiers with a key (e.g. "ctrl+s", "alt+Tab", "ctrl+shift+Escape"). Key names are case-insensitive; common names like "Return", "Tab", "Escape", "Up", "Down", "Left", "Right", "Home", "End", "Page_Up", "Page_Down", "Delete", "BackSpace" are supported. - `text: string` The key or key-combination to press. - `repeat: optional number` Number of times to repeat the key press. Default is 1. minimum: 1, maximum: 100 - `name: "key"` - `toolset_name: "computer"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `type: "direct"` - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `type: "code_execution_20250825"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `beta_server_tool_caller_20260120: object` - `type: "code_execution_20260120"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `beta_computer_hold_key_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Hold down a key or key-combination for a specified duration. Uses the same key syntax as `key`. - `duration: number` Duration to hold the key, in seconds. maximum: 300 - `text: string` The key or key-combination to hold. - `name: "hold_key"` - `toolset_name: "computer"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `beta_server_tool_caller_20260120: object` - `beta_computer_type_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Type a string of text on the keyboard. - `text: string` The text to type. - `name: "type"` - `toolset_name: "computer"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `beta_server_tool_caller_20260120: object` - `beta_computer_cursor_position_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Get the current (x, y) pixel coordinate of the cursor. - `name: "cursor_position"` - `toolset_name: "computer"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `beta_server_tool_caller_20260120: object` - `beta_computer_mouse_move_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Move the cursor to a specified (x, y) pixel coordinate. Use this ONLY to hover without clicking; otherwise use a click action directly. - `coordinate: array of number` (x, y): x pixels from the left edge, y pixels from the top edge. minItems: 2, maxItems: 2 - `name: "mouse_move"` - `toolset_name: "computer"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `beta_server_tool_caller_20260120: object` - `beta_computer_left_mouse_down_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Press and hold the left mouse button at the current cursor position. - `name: "left_mouse_down"` - `toolset_name: "computer"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `beta_server_tool_caller_20260120: object` - `beta_computer_left_mouse_up_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Release the left mouse button. - `name: "left_mouse_up"` - `toolset_name: "computer"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `beta_server_tool_caller_20260120: object` - `beta_computer_left_click_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Click the left mouse button at the specified (x, y) pixel coordinate, or the current cursor position if `coordinate` is omitted. - `coordinate: optional array of number` (x, y): x pixels from the left edge, y pixels from the top edge. minItems: 2, maxItems: 2 - `text: optional string` Optional key combination to hold down during this action (e.g. "ctrl", "shift", "ctrl+shift"). - `name: "left_click"` - `toolset_name: "computer"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `beta_server_tool_caller_20260120: object` - `beta_computer_left_click_drag_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Click and drag the cursor from `start_coordinate` to `coordinate`. - `coordinate: array of number` (x, y): x pixels from the left edge, y pixels from the top edge. minItems: 2, maxItems: 2 - `start_coordinate: array of number` (x, y): x pixels from the left edge, y pixels from the top edge. minItems: 2, maxItems: 2 - `text: optional string` Optional key combination to hold down during this action (e.g. "ctrl", "shift", "ctrl+shift"). - `name: "left_click_drag"` - `toolset_name: "computer"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `beta_server_tool_caller_20260120: object` - `beta_computer_right_click_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Click the right mouse button at the specified (x, y) pixel coordinate, or the current cursor position if `coordinate` is omitted. - `coordinate: optional array of number` (x, y): x pixels from the left edge, y pixels from the top edge. minItems: 2, maxItems: 2 - `text: optional string` Optional key combination to hold down during this action (e.g. "ctrl", "shift", "ctrl+shift"). - `name: "right_click"` - `toolset_name: "computer"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `beta_server_tool_caller_20260120: object` - `beta_computer_middle_click_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Click the middle mouse button at the specified (x, y) pixel coordinate, or the current cursor position if `coordinate` is omitted. - `coordinate: optional array of number` (x, y): x pixels from the left edge, y pixels from the top edge. minItems: 2, maxItems: 2 - `text: optional string` Optional key combination to hold down during this action (e.g. "ctrl", "shift", "ctrl+shift"). - `name: "middle_click"` - `toolset_name: "computer"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `beta_server_tool_caller_20260120: object` - `beta_computer_double_click_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Double-click the left mouse button at the specified (x, y) pixel coordinate, or the current cursor position if `coordinate` is omitted. - `coordinate: optional array of number` (x, y): x pixels from the left edge, y pixels from the top edge. minItems: 2, maxItems: 2 - `text: optional string` Optional key combination to hold down during this action (e.g. "ctrl", "shift", "ctrl+shift"). - `name: "double_click"` - `toolset_name: "computer"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `beta_server_tool_caller_20260120: object` - `beta_computer_triple_click_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Triple-click the left mouse button at the specified (x, y) pixel coordinate, or the current cursor position if `coordinate` is omitted. - `coordinate: optional array of number` (x, y): x pixels from the left edge, y pixels from the top edge. minItems: 2, maxItems: 2 - `text: optional string` Optional key combination to hold down during this action (e.g. "ctrl", "shift", "ctrl+shift"). - `name: "triple_click"` - `toolset_name: "computer"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `beta_server_tool_caller_20260120: object` - `beta_computer_scroll_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Scroll the screen at the specified (x, y) pixel coordinate, or the current cursor position if `coordinate` is omitted. Do NOT use PageUp/PageDown to scroll. - `scroll_amount: number` Number of 'clicks' of the scroll wheel. - `scroll_direction: "up" or "down" or "left" or "right"` - `"up"` - `"down"` - `"left"` - `"right"` - `coordinate: optional array of number` (x, y): x pixels from the left edge, y pixels from the top edge. minItems: 2, maxItems: 2 - `text: optional string` Optional key combination to hold down during this action (e.g. "ctrl", "shift", "ctrl+shift"). - `name: "scroll"` - `toolset_name: "computer"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `beta_server_tool_caller_20260120: object` - `beta_computer_wait_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Wait for a specified duration. - `duration: number` Duration to wait, in seconds. maximum: 300 - `name: "wait"` - `toolset_name: "computer"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `beta_server_tool_caller_20260120: object` - `beta_computer_screenshot_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Take a screenshot of the screen. - `name: "screenshot"` - `toolset_name: "computer"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `beta_server_tool_caller_20260120: object` - `beta_computer_zoom_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Take a screenshot of a rectangular region. Region coordinates are in the full-screenshot space (not physical display pixels). The crop is scaled up to fill the image budget so fine details become legible. - `region: array of number` (x0, y0, x1, y1): The region to capture. minItems: 4, maxItems: 4 - `name: "zoom"` - `toolset_name: "computer"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `beta_server_tool_caller_20260120: object` ### Beta Computer Toolset 20260801 - `beta_computer_toolset_20260801: object` The computer toolset: a single `tools[]` entry (carrying no `name`) that declares the computer tool family. The model is served the family's tool with any members disabled via `configs` removed from its schema. Every member is enabled by default, zoom included. The single-tool options `display_number` and `enable_zoom` are not fields of a toolset entry — it carries only `type`, `configs`, and `cache_control`; zoom is controlled via `configs.zoom.enabled`. - `type: "computer_toolset_20260801"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `"5m"` - `"1h"` - `configs: optional object` Sparse per-member overrides, keyed by member name. Absent, null, and {} are equivalent; a member's defaults apply wherever its key is absent. - `type: optional object` `type`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `cursor_position: optional object` `cursor_position`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `double_click: optional object` `double_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `hold_key: optional object` `hold_key`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `key: optional object` `key`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_click: optional object` `left_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_click_drag: optional object` `left_click_drag`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_mouse_down: optional object` `left_mouse_down`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_mouse_up: optional object` `left_mouse_up`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `middle_click: optional object` `middle_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `mouse_move: optional object` `mouse_move`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `right_click: optional object` `right_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `screenshot: optional object` `screenshot`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `scroll: optional object` `scroll`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `triple_click: optional object` `triple_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `wait: optional object` `wait`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `zoom: optional object` `zoom`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. ### Beta Computer Toolset Configs - `beta_computer_toolset_configs: object` Per-member configuration for `computer_toolset_20260801`: one optional field per member tool, keyed by the member name — the same name the member's `tool_use` blocks carry. Every member is an accepted key, and a member's defaults apply wherever its key is absent. Unknown keys are rejected: the field set is this toolset version's complete member set. - `type: optional object` `type`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `cursor_position: optional object` `cursor_position`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `double_click: optional object` `double_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `hold_key: optional object` `hold_key`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `key: optional object` `key`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_click: optional object` `left_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_click_drag: optional object` `left_click_drag`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_mouse_down: optional object` `left_mouse_down`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_mouse_up: optional object` `left_mouse_up`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `middle_click: optional object` `middle_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `mouse_move: optional object` `mouse_move`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `right_click: optional object` `right_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `screenshot: optional object` `screenshot`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `scroll: optional object` `scroll`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `triple_click: optional object` `triple_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `wait: optional object` `wait`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `zoom: optional object` `zoom`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. ### Beta Computer Triple Click Config - `beta_computer_triple_click_config: object` `triple_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. ### Beta Computer Triple Click Input - `beta_computer_triple_click_input: object` Triple-click the left mouse button at the specified (x, y) pixel coordinate, or the current cursor position if `coordinate` is omitted. - `coordinate: optional array of number` (x, y): x pixels from the left edge, y pixels from the top edge. minItems: 2, maxItems: 2 - `text: optional string` Optional key combination to hold down during this action (e.g. "ctrl", "shift", "ctrl+shift"). ### Beta Computer Triple Click Tool Use Block - `beta_computer_triple_click_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Triple-click the left mouse button at the specified (x, y) pixel coordinate, or the current cursor position if `coordinate` is omitted. - `coordinate: optional array of number` (x, y): x pixels from the left edge, y pixels from the top edge. minItems: 2, maxItems: 2 - `text: optional string` Optional key combination to hold down during this action (e.g. "ctrl", "shift", "ctrl+shift"). - `name: "triple_click"` - `toolset_name: "computer"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `type: "direct"` - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `type: "code_execution_20250825"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `beta_server_tool_caller_20260120: object` - `type: "code_execution_20260120"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ ### Beta Computer Type Config - `beta_computer_type_config: object` `type`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. ### Beta Computer Type Input - `beta_computer_type_input: object` Type a string of text on the keyboard. - `text: string` The text to type. ### Beta Computer Type Tool Use Block - `beta_computer_type_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Type a string of text on the keyboard. - `text: string` The text to type. - `name: "type"` - `toolset_name: "computer"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `type: "direct"` - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `type: "code_execution_20250825"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `beta_server_tool_caller_20260120: object` - `type: "code_execution_20260120"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ ### Beta Computer Wait Config - `beta_computer_wait_config: object` `wait`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. ### Beta Computer Wait Input - `beta_computer_wait_input: object` Wait for a specified duration. - `duration: number` Duration to wait, in seconds. maximum: 300 ### Beta Computer Wait Tool Use Block - `beta_computer_wait_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Wait for a specified duration. - `duration: number` Duration to wait, in seconds. maximum: 300 - `name: "wait"` - `toolset_name: "computer"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `type: "direct"` - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `type: "code_execution_20250825"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `beta_server_tool_caller_20260120: object` - `type: "code_execution_20260120"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ ### Beta Computer Zoom Config - `beta_computer_zoom_config: object` `zoom`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. ### Beta Computer Zoom Input - `beta_computer_zoom_input: object` Take a screenshot of a rectangular region. Region coordinates are in the full-screenshot space (not physical display pixels). The crop is scaled up to fill the image budget so fine details become legible. - `region: array of number` (x0, y0, x1, y1): The region to capture. minItems: 4, maxItems: 4 ### Beta Computer Zoom Tool Use Block - `beta_computer_zoom_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Take a screenshot of a rectangular region. Region coordinates are in the full-screenshot space (not physical display pixels). The crop is scaled up to fill the image budget so fine details become legible. - `region: array of number` (x0, y0, x1, y1): The region to capture. minItems: 4, maxItems: 4 - `name: "zoom"` - `toolset_name: "computer"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `type: "direct"` - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `type: "code_execution_20250825"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `beta_server_tool_caller_20260120: object` - `type: "code_execution_20260120"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ ### Beta Container - `beta_container: object` Information about the container used in the request (for the code execution tool) - `id: string` Identifier for the container used in this request - `expires_at: string` The time at which the container will expire. format: date-time - `skills: array of BetaContainerSkill` Skills loaded in the container - `type: "anthropic" or "custom"` Type of skill - either 'anthropic' (built-in) or 'custom' (user-defined) - `"anthropic"` - `"custom"` - `skill_id: string` Skill ID minLength: 1, maxLength: 64 - `version: string` The resolved version: a skill version ID for custom skills. minLength: 1, maxLength: 64 ### Beta Container Params - `beta_container_params: object` Container parameters with skills to be loaded. - `id: optional string` Container id - `skills: optional array of BetaSkillParams` List of skills to load in the container maxItems: 20 - `type: "anthropic" or "custom"` Type of skill - either 'anthropic' (built-in) or 'custom' (user-defined) - `"anthropic"` - `"custom"` - `skill_id: string` Skill ID minLength: 1, maxLength: 64 - `version: optional string` Skill version or 'latest' for most recent version minLength: 1, maxLength: 64 ### Beta Container Skill - `beta_container_skill: object` A skill that was loaded in a container (response model). - `type: "anthropic" or "custom"` Type of skill - either 'anthropic' (built-in) or 'custom' (user-defined) - `"anthropic"` - `"custom"` - `skill_id: string` Skill ID minLength: 1, maxLength: 64 - `version: string` The resolved version: a skill version ID for custom skills. minLength: 1, maxLength: 64 ### Beta Container Upload Block - `beta_container_upload_block: object` Response model for a file uploaded to the container. - `type: "container_upload"` - `file_id: string` ### Beta Container Upload Block Param - `beta_container_upload_block_param: object` A content block that represents a file to be uploaded to the container Files uploaded via this block will be available in the container's input directory. - `type: "container_upload"` - `file_id: string` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `"5m"` - `"1h"` ### Beta Content Block - `beta_content_block: BetaTextBlock or BetaThinkingBlock or BetaRedactedThinkingBlock or 15 more` - `beta_text_block: object` - `type: "text"` - `citations: array of BetaTextCitation` Citations supporting the text block. The type of citation returned will depend on the type of document being cited. Citing a PDF results in `page_location`, plain text results in `char_location`, and content document results in `content_block_location`. - `beta_citation_char_location: object` - `type: "char_location"` - `cited_text: string` - `document_index: number` minimum: 0 - `document_title: string` - `end_char_index: number` - `file_id: string` - `start_char_index: number` minimum: 0 - `beta_citation_page_location: object` - `type: "page_location"` - `cited_text: string` - `document_index: number` minimum: 0 - `document_title: string` - `end_page_number: number` - `file_id: string` - `start_page_number: number` minimum: 1 - `beta_citation_content_block_location: object` - `type: "content_block_location"` - `cited_text: string` The full text of the cited block range, concatenated. Always equals the contents of `content[start_block_index:end_block_index]` joined together. The text block is the minimal citable unit; this field is never a substring of a single block. Not counted toward output tokens, and not counted toward input tokens when sent back in subsequent turns. - `document_index: number` minimum: 0 - `document_title: string` - `end_block_index: number` Exclusive 0-based end index of the cited block range in the source's `content` array. Always greater than `start_block_index`; a single-block citation has `end_block_index = start_block_index + 1`. - `file_id: string` - `start_block_index: number` 0-based index of the first cited block in the source's `content` array. minimum: 0 - `beta_citations_web_search_result_location: object` - `type: "web_search_result_location"` - `cited_text: string` - `encrypted_index: string` - `title: string` maxLength: 512 - `url: string` - `beta_citation_search_result_location: object` - `type: "search_result_location"` - `cited_text: string` The full text of the cited block range, concatenated. Always equals the contents of `content[start_block_index:end_block_index]` joined together. The text block is the minimal citable unit; this field is never a substring of a single block. Not counted toward output tokens, and not counted toward input tokens when sent back in subsequent turns. - `end_block_index: number` Exclusive 0-based end index of the cited block range in the source's `content` array. Always greater than `start_block_index`; a single-block citation has `end_block_index = start_block_index + 1`. - `search_result_index: number` 0-based index of the cited search result among all `search_result` content blocks in the request, in the order they appear across messages and tool results. Counted separately from `document_index`; server-side web search results are not included in this count. minimum: 0 - `source: string` - `start_block_index: number` 0-based index of the first cited block in the source's `content` array. minimum: 0 - `title: string` - `text: string` - `beta_thinking_block: object` - `type: "thinking"` - `signature: string` A value used to verify that this thinking block was generated by Claude when it is passed back to the API. This is an opaque field and should not be interpreted or parsed. When passing thinking blocks back to the API (required when using tools with extended thinking), pass them back exactly as received, with this field intact. See [extended thinking](https://platform.claude.com/docs/en/build-with-claude/extended-thinking?sdk_languages=cli) for details. - `thinking: string` The text of Claude's thinking process for this block. - `beta_redacted_thinking_block: object` - `type: "redacted_thinking"` - `data: string` The contents of this redacted thinking block, returned when portions of the model's thinking were safety-redacted. This field is opaque and encrypted, with no readable content. Pass `redacted_thinking` blocks back to the API unchanged when continuing a multi-turn conversation. See [extended thinking](https://platform.claude.com/docs/en/build-with-claude/extended-thinking?sdk_languages=cli#redacted-thinking-blocks) for details. - `beta_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: map[unknown]` - `name: string` minLength: 1 - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` - `beta_direct_caller: object` Tool invocation directly from the model. - `type: "direct"` - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `type: "code_execution_20250825"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `beta_server_tool_caller_20260120: object` - `type: "code_execution_20260120"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `toolset_name: optional string` For a toolset member tool_use, the toolset family. minLength: 1, maxLength: 64, pattern: ^[a-zA-Z0-9_-]+$ - `beta_server_tool_use_block: object` - `type: "server_tool_use"` - `id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `input: map[unknown]` - `name: "advisor" or "web_search" or "web_fetch" or 5 more` - `"advisor"` - `"web_search"` - `"web_fetch"` - `"code_execution"` - `"bash_code_execution"` - `"text_editor_code_execution"` - `"tool_search_tool_regex"` - `"tool_search_tool_bm25"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` - `beta_direct_caller: object` Tool invocation directly from the model. - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `beta_server_tool_caller_20260120: object` - `beta_web_search_tool_result_block: object` - `type: "web_search_tool_result"` - `content: BetaWebSearchToolResultError or array of BetaWebSearchResultBlock` - `beta_web_search_tool_result_error: object` - `type: "web_search_tool_result_error"` - `error_code: "invalid_tool_input" or "unavailable" or "max_uses_exceeded" or 3 more` - `"invalid_tool_input"` - `"unavailable"` - `"max_uses_exceeded"` - `"too_many_requests"` - `"query_too_long"` - `"request_too_large"` - `union_member_1: array of BetaWebSearchResultBlock` - `type: "web_search_result"` - `encrypted_content: string` - `page_age: string` - `title: string` - `url: string` - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` - `beta_direct_caller: object` Tool invocation directly from the model. - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `beta_server_tool_caller_20260120: object` - `beta_web_fetch_tool_result_block: object` - `type: "web_fetch_tool_result"` - `content: BetaWebFetchToolResultErrorBlock or BetaWebFetchBlock` - `beta_web_fetch_tool_result_error_block: object` - `type: "web_fetch_tool_result_error"` - `error_code: "invalid_tool_input" or "url_too_long" or "url_not_allowed" or 7 more` - `"invalid_tool_input"` - `"url_too_long"` - `"url_not_allowed"` - `"url_not_in_prior_context"` - `"url_not_accessible"` - `"unsupported_content_type"` - `"too_many_requests"` - `"max_uses_exceeded"` - `"unavailable"` - `"content_too_large"` - `beta_web_fetch_block: object` - `type: "web_fetch_result"` - `content: object` - `type: "document"` - `citations: object` Citation configuration for the document - `enabled: boolean` - `source: BetaBase64PDFSource or BetaPlainTextSource` - `beta_base64_pdf_source: object` - `type: "base64"` - `data: string` format: byte - `media_type: "application/pdf"` - `beta_plain_text_source: object` - `type: "text"` - `data: string` - `media_type: "text/plain"` - `title: string` The title of the document - `retrieved_at: string` ISO 8601 timestamp when the content was retrieved - `url: string` Fetched content URL - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` - `beta_direct_caller: object` Tool invocation directly from the model. - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `beta_server_tool_caller_20260120: object` - `beta_advisor_tool_result_block: object` - `type: "advisor_tool_result"` - `content: BetaAdvisorToolResultError or BetaAdvisorResultBlock or BetaAdvisorRedactedResultBlock` - `beta_advisor_tool_result_error: object` - `type: "advisor_tool_result_error"` - `error_code: "max_uses_exceeded" or "prompt_too_long" or "too_many_requests" or 4 more` - `"max_uses_exceeded"` - `"prompt_too_long"` - `"too_many_requests"` - `"overloaded"` - `"unavailable"` - `"execution_time_exceeded"` - `"model_not_found"` - `beta_advisor_result_block: object` - `type: "advisor_result"` - `stop_reason: string` The advisor sub-inference's stop reason (same values as the top-level message `stop_reason`). `max_tokens` indicates the advisor's output was truncated at the tool's `max_tokens` value or the advisor model's policy cap. - `text: string` - `beta_advisor_redacted_result_block: object` - `type: "advisor_redacted_result"` - `encrypted_content: string` Opaque blob containing the advisor's output. Round-trip verbatim; do not inspect or modify. - `stop_reason: string` The advisor sub-inference's stop reason (same values as the top-level message `stop_reason`). - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `beta_code_execution_tool_result_block: object` - `type: "code_execution_tool_result"` - `content: BetaCodeExecutionToolResultError or BetaCodeExecutionResultBlock or BetaEncryptedCodeExecutionResultBlock` - `beta_code_execution_tool_result_error: object` - `type: "code_execution_tool_result_error"` - `error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or "execution_time_exceeded"` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `beta_code_execution_result_block: object` - `type: "code_execution_result"` - `content: array of BetaCodeExecutionOutputBlock` - `type: "code_execution_output"` - `file_id: string` - `return_code: number` - `stderr: string` - `stdout: string` - `beta_encrypted_code_execution_result_block: object` Code execution result with encrypted stdout for PFC + web_search results. - `type: "encrypted_code_execution_result"` - `content: array of BetaCodeExecutionOutputBlock` - `type: "code_execution_output"` - `file_id: string` - `encrypted_stdout: string` - `return_code: number` - `stderr: string` - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `beta_bash_code_execution_tool_result_block: object` - `type: "bash_code_execution_tool_result"` - `content: BetaBashCodeExecutionToolResultError or BetaBashCodeExecutionResultBlock` - `beta_bash_code_execution_tool_result_error: object` - `type: "bash_code_execution_tool_result_error"` - `error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or 2 more` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `"output_file_too_large"` - `beta_bash_code_execution_result_block: object` - `type: "bash_code_execution_result"` - `content: array of BetaBashCodeExecutionOutputBlock` - `type: "bash_code_execution_output"` - `file_id: string` - `return_code: number` - `stderr: string` - `stdout: string` - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `beta_text_editor_code_execution_tool_result_block: object` - `type: "text_editor_code_execution_tool_result"` - `content: BetaTextEditorCodeExecutionToolResultError or BetaTextEditorCodeExecutionViewResultBlock or BetaTextEditorCodeExecutionCreateResultBlock or BetaTextEditorCodeExecutionStrReplaceResultBlock` - `beta_text_editor_code_execution_tool_result_error: object` - `type: "text_editor_code_execution_tool_result_error"` - `error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or 2 more` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `"file_not_found"` - `error_message: string` - `beta_text_editor_code_execution_view_result_block: object` - `type: "text_editor_code_execution_view_result"` - `content: string` - `file_type: "text" or "image" or "pdf"` - `"text"` - `"image"` - `"pdf"` - `num_lines: number` - `start_line: number` - `total_lines: number` - `beta_text_editor_code_execution_create_result_block: object` - `type: "text_editor_code_execution_create_result"` - `is_file_update: boolean` - `beta_text_editor_code_execution_str_replace_result_block: object` - `type: "text_editor_code_execution_str_replace_result"` - `lines: array of string` - `new_lines: number` - `new_start: number` - `old_lines: number` - `old_start: number` - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `beta_tool_search_tool_result_block: object` - `type: "tool_search_tool_result"` - `content: BetaToolSearchToolResultError or BetaToolSearchToolSearchResultBlock` - `beta_tool_search_tool_result_error: object` - `type: "tool_search_tool_result_error"` - `error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or "execution_time_exceeded"` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `error_message: string` - `beta_tool_search_tool_search_result_block: object` - `type: "tool_search_tool_search_result"` - `tool_references: array of BetaToolReferenceBlock` - `type: "tool_reference"` - `tool_name: string` minLength: 1, maxLength: 256, pattern: ^[a-zA-Z0-9_-]{1,256}$ - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `beta_mcp_tool_use_block: object` - `type: "mcp_tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: map[unknown]` - `name: string` The name of the MCP tool - `server_name: string` The name of the MCP server - `beta_mcp_tool_result_block: object` - `type: "mcp_tool_result"` - `content: string or array of BetaTextBlock` - `union_member_0: string` - `beta_mcp_tool_result_block_content: array of BetaTextBlock` - `type: "text"` - `citations: array of BetaTextCitation` Citations supporting the text block. The type of citation returned will depend on the type of document being cited. Citing a PDF results in `page_location`, plain text results in `char_location`, and content document results in `content_block_location`. - `text: string` - `is_error: boolean` - `tool_use_id: string` pattern: ^[a-zA-Z0-9_-]+$ - `beta_container_upload_block: object` Response model for a file uploaded to the container. - `type: "container_upload"` - `file_id: string` - `beta_compaction_block: object` A compaction block returned when autocompact is triggered. When content is None, it indicates the compaction failed to produce a valid summary (e.g., malformed output from the model). Clients may round-trip compaction blocks with null content; the server treats them as no-ops. - `type: "compaction"` - `content: string` Summary of compacted content, or null if compaction failed - `encrypted_content: string` Opaque metadata from prior compaction, to be round-tripped verbatim - `signature: optional string` Signature over the summary, to be sent back with the block verbatim - `tool_changes: optional array of BetaResponseToolAdditionBlock or BetaResponseToolRemovalBlock` The tool changes of the compacted range: the `tool_addition` and `tool_removal` blocks that take the request's `tools` to the tool set in effect at the end of the range, or `[]` when the range changed no tool. Absent when the server did not compute them. Send the block back unchanged. - `beta_response_tool_addition_block: object` An entry of a `compaction` block's `tool_changes`: a tool the compacted range made available, as a reference to a `tools` entry or MCP toolset, or as the tool definition in effect at the end of the range, by value. Send it back unchanged. - `type: "tool_addition"` - `tool: BetaResponseToolChangeToolReference or BetaResponseToolChangeMCPToolReference or BetaResponseToolChangeMCPToolsetReference or BetaToolChangeToolDefinition` The tool made available: a reference to a `tools` entry or MCP toolset, or a `tool_definition` carrying the definition by value. - `beta_response_tool_change_tool_reference: object` Reference to a single tool, by the name the model uses to call it, as a `compaction` block's `tool_changes` entry reports it: a tool declared in `tools` or defined by an earlier `tool_addition` block. Send it back unchanged with the block. - `type: "tool_reference"` - `name: string` - `beta_response_tool_change_mcp_tool_reference: object` Reference to a single MCP tool, by its server and its name on that server, as a `compaction` block's `tool_changes` entry reports it. Send it back unchanged with the block. - `type: "mcp_tool_reference"` - `name: string` - `server_name: string` - `beta_response_tool_change_mcp_toolset_reference: object` Reference to every tool in the named MCP server's toolset, as a `compaction` block's `tool_changes` entry reports it. Send it back unchanged with the block. - `type: "mcp_toolset_reference"` - `server_name: string` - `beta_tool_change_tool_definition: object` A tool defined by value, as a `compaction` block's `tool_changes` entry reports it: `definition` is the tool's definition as it was sent, in the form of a `tools` entry, without `cache_control`. Send it back unchanged with the block. - `type: "tool_definition"` - `definition: BetaResponseTool or BetaToolBash20241022 or BetaToolBash20250124 or 25 more` - `beta_response_tool: object` A custom tool definition, as sent. - `type: optional "custom"` - `input_schema: object` [JSON schema](https://json-schema.org/draft/2020-12) for this tool's input. This defines the shape of the `input` that your tool accepts and that the model will produce. - `type: "object"` - `properties: optional map[unknown]` - `required: optional array of string` - `name: string` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. minLength: 1, maxLength: 128, pattern: ^[a-zA-Z0-9_-]{1,128}$ - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `description: optional string` Description of what this tool does. Tool descriptions should be as detailed as possible. The more information that the model has about what the tool is and how to use it, the better it will perform. You can use natural language descriptions to reinforce important aspects of the tool input JSON schema. - `eager_input_streaming: optional boolean` Enable eager input streaming for this tool. When true, tool input parameters will be streamed incrementally as they are generated, and types will be inferred on-the-fly rather than buffering the full JSON output. When false, streaming is disabled for this tool even if the fine-grained-tool-streaming beta is active. When null (default), uses the default behavior based on beta headers. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_bash_20241022: object` - `type: "bash_20241022"` - `name: "bash"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `"5m"` - `"1h"` - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_bash_20250124: object` - `type: "bash_20250124"` - `name: "bash"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_code_execution_tool_20250522: object` - `type: "code_execution_20250522"` - `name: "code_execution"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_code_execution_tool_20250825: object` - `type: "code_execution_20250825"` - `name: "code_execution"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_code_execution_tool_20260120: object` Code execution tool with REPL state persistence (daemon mode + gVisor checkpoint). - `type: "code_execution_20260120"` - `name: "code_execution"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_code_execution_tool_20260521: object` Code execution tool with REPL state persistence. - `type: "code_execution_20260521"` - `name: "code_execution"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_browser_toolset_20260801: object` The browser toolset: a single `tools[]` entry (carrying no `name`) that declares the browser tool family. The model is served the family's tool with any members disabled via `configs` removed from its schema. - `type: "browser_toolset_20260801"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `configs: optional object` Sparse per-member overrides, keyed by member name. Absent, null, and {} are equivalent; a member's defaults apply wherever its key is absent. - `type: optional object` `type`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `close_tab: optional object` `close_tab`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `double_click: optional object` `double_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `file_upload: optional object` `file_upload`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `find: optional object` `find`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `form_input: optional object` `form_input`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `get_page_text: optional object` `get_page_text`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `hold_key: optional object` `hold_key`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `hover: optional object` `hover`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `javascript_exec: optional object` `javascript_exec`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `key: optional object` `key`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_click: optional object` `left_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_click_drag: optional object` `left_click_drag`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_mouse_down: optional object` `left_mouse_down`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_mouse_up: optional object` `left_mouse_up`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `list_tabs: optional object` `list_tabs`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `middle_click: optional object` `middle_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `mouse_move: optional object` `mouse_move`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `navigate: optional object` `navigate`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `new_tab: optional object` `new_tab`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `read_console: optional object` `read_console`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `read_network: optional object` `read_network`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `read_page: optional object` `read_page`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `right_click: optional object` `right_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `screenshot: optional object` `screenshot`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `scroll: optional object` `scroll`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `scroll_to: optional object` `scroll_to`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `switch_tab: optional object` `switch_tab`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `triple_click: optional object` `triple_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `wait: optional object` `wait`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `zoom: optional object` `zoom`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `beta_tool_computer_use_20241022: object` - `type: "computer_20241022"` - `display_height_px: number` The height of the display in pixels. minimum: 1 - `display_width_px: number` The width of the display in pixels. minimum: 1 - `name: "computer"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `display_number: optional number` The X11 display number (e.g. 0, 1) for the display. minimum: 0 - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_memory_tool_20250818: object` - `type: "memory_20250818"` - `name: "memory"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_computer_use_20250124: object` - `type: "computer_20250124"` - `display_height_px: number` The height of the display in pixels. minimum: 1 - `display_width_px: number` The width of the display in pixels. minimum: 1 - `name: "computer"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `display_number: optional number` The X11 display number (e.g. 0, 1) for the display. minimum: 0 - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_text_editor_20241022: object` - `type: "text_editor_20241022"` - `name: "str_replace_editor"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_computer_use_20251124: object` - `type: "computer_20251124"` - `display_height_px: number` The height of the display in pixels. minimum: 1 - `display_width_px: number` The width of the display in pixels. minimum: 1 - `name: "computer"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `display_number: optional number` The X11 display number (e.g. 0, 1) for the display. minimum: 0 - `enable_zoom: optional boolean` Whether to enable an action to take a zoomed-in screenshot of the screen. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_computer_toolset_20260801: object` The computer toolset: a single `tools[]` entry (carrying no `name`) that declares the computer tool family. The model is served the family's tool with any members disabled via `configs` removed from its schema. Every member is enabled by default, zoom included. The single-tool options `display_number` and `enable_zoom` are not fields of a toolset entry — it carries only `type`, `configs`, and `cache_control`; zoom is controlled via `configs.zoom.enabled`. - `type: "computer_toolset_20260801"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `configs: optional object` Sparse per-member overrides, keyed by member name. Absent, null, and {} are equivalent; a member's defaults apply wherever its key is absent. - `type: optional object` `type`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `cursor_position: optional object` `cursor_position`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `double_click: optional object` `double_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `hold_key: optional object` `hold_key`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `key: optional object` `key`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_click: optional object` `left_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_click_drag: optional object` `left_click_drag`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_mouse_down: optional object` `left_mouse_down`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_mouse_up: optional object` `left_mouse_up`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `middle_click: optional object` `middle_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `mouse_move: optional object` `mouse_move`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `right_click: optional object` `right_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `screenshot: optional object` `screenshot`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `scroll: optional object` `scroll`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `triple_click: optional object` `triple_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `wait: optional object` `wait`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `zoom: optional object` `zoom`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `beta_tool_text_editor_20250124: object` - `type: "text_editor_20250124"` - `name: "str_replace_editor"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_text_editor_20250429: object` - `type: "text_editor_20250429"` - `name: "str_replace_based_edit_tool"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_text_editor_20250728: object` - `type: "text_editor_20250728"` - `name: "str_replace_based_edit_tool"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: optional array of map[unknown]` - `max_characters: optional number` Maximum number of characters to display when viewing a file. If not specified, defaults to displaying the full file. minimum: 1 - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_web_search_tool_20250305: object` - `type: "web_search_20250305"` - `name: "web_search"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: optional array of string` If provided, only these domains will be included in results. Cannot be used alongside `blocked_domains`. - `blocked_domains: optional array of string` If provided, these domains will never appear in results. Cannot be used alongside `allowed_domains`. - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `user_location: optional object` Parameters for the user's location. Used to provide more relevant search results. - `type: "approximate"` - `city: optional string` The city of the user. minLength: 1, maxLength: 255 - `country: optional string` The two letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1_alpha-2) of the user. minLength: 2, maxLength: 2 - `region: optional string` The region of the user. minLength: 1, maxLength: 255 - `timezone: optional string` The [IANA timezone](https://nodatime.org/TimeZones) of the user. minLength: 1, maxLength: 255 - `beta_web_fetch_tool_20250910: object` - `type: "web_fetch_20250910"` - `name: "web_fetch"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: optional array of string` List of domains to allow fetching from - `blocked_domains: optional array of string` List of domains to block fetching from - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `citations: optional object` Citations configuration for fetched documents. Citations are disabled by default. - `enabled: optional boolean` - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_content_tokens: optional number` Maximum number of tokens used by including web page text content in the context. The limit is approximate and does not apply to binary content such as PDFs. minimum: 1 - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `url_sources: optional object` Which sources contribute to the set of URLs the tool may fetch. Omitted means every source. - `client_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which client tools' results contribute fetchable URLs: "all", "none", or an only or except list of client tool names from tools[]. - `beta_web_fetch_url_source_all: object` The `url_sources` variant under which a source contributes in full: every result of the tool filter's source, or all user input. - `type: "all"` - `beta_web_fetch_url_source_none: object` The `url_sources` variant under which a source contributes nothing: no result of the tool filter's source, or no user input. - `type: "none"` - `beta_web_fetch_url_source_only: object` The tool filter variant under which only the named tools' results contribute. - `type: "only"` - `tools: array of BetaWebFetchURLSourceToolReference` - `type: "tool_reference"` - `name: string` - `beta_web_fetch_url_source_except: object` The tool filter variant under which every result but the named tools' contributes. - `type: "except"` - `tools: array of BetaWebFetchURLSourceToolReference` - `type: "tool_reference"` - `name: string` - `server_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which server tools' results contribute fetchable URLs: "all", "none", or an only or except list of server tool names from tools[]; only web_search and web_fetch results ever contribute. - `beta_web_fetch_url_source_all: object` The `url_sources` variant under which a source contributes in full: every result of the tool filter's source, or all user input. - `beta_web_fetch_url_source_none: object` The `url_sources` variant under which a source contributes nothing: no result of the tool filter's source, or no user input. - `beta_web_fetch_url_source_only: object` The tool filter variant under which only the named tools' results contribute. - `beta_web_fetch_url_source_except: object` The tool filter variant under which every result but the named tools' contributes. - `user_input: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone` Whether URLs in user messages are fetchable: "all" or "none". - `beta_web_fetch_url_source_all: object` The `url_sources` variant under which a source contributes in full: every result of the tool filter's source, or all user input. - `beta_web_fetch_url_source_none: object` The `url_sources` variant under which a source contributes nothing: no result of the tool filter's source, or no user input. - `beta_web_search_tool_20260209: object` - `type: "web_search_20260209"` - `name: "web_search"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: optional array of string` If provided, only these domains will be included in results. Cannot be used alongside `blocked_domains`. - `blocked_domains: optional array of string` If provided, these domains will never appear in results. Cannot be used alongside `allowed_domains`. - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `user_location: optional object` Parameters for the user's location. Used to provide more relevant search results. - `type: "approximate"` - `city: optional string` The city of the user. minLength: 1, maxLength: 255 - `country: optional string` The two letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1_alpha-2) of the user. minLength: 2, maxLength: 2 - `region: optional string` The region of the user. minLength: 1, maxLength: 255 - `timezone: optional string` The [IANA timezone](https://nodatime.org/TimeZones) of the user. minLength: 1, maxLength: 255 - `beta_web_fetch_tool_20260209: object` - `type: "web_fetch_20260209"` - `name: "web_fetch"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: optional array of string` List of domains to allow fetching from - `blocked_domains: optional array of string` List of domains to block fetching from - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `citations: optional object` Citations configuration for fetched documents. Citations are disabled by default. - `enabled: optional boolean` - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_content_tokens: optional number` Maximum number of tokens used by including web page text content in the context. The limit is approximate and does not apply to binary content such as PDFs. minimum: 1 - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `url_sources: optional object` Which sources contribute to the set of URLs the tool may fetch. Omitted means every source. - `client_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which client tools' results contribute fetchable URLs: "all", "none", or an only or except list of client tool names from tools[]. - `server_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which server tools' results contribute fetchable URLs: "all", "none", or an only or except list of server tool names from tools[]; only web_search and web_fetch results ever contribute. - `user_input: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone` Whether URLs in user messages are fetchable: "all" or "none". - `beta_web_fetch_tool_20260309: object` Web fetch tool with use_cache parameter for bypassing cached content. - `type: "web_fetch_20260309"` - `name: "web_fetch"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: optional array of string` List of domains to allow fetching from - `blocked_domains: optional array of string` List of domains to block fetching from - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `citations: optional object` Citations configuration for fetched documents. Citations are disabled by default. - `enabled: optional boolean` - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_content_tokens: optional number` Maximum number of tokens used by including web page text content in the context. The limit is approximate and does not apply to binary content such as PDFs. minimum: 1 - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `url_sources: optional object` Which sources contribute to the set of URLs the tool may fetch. Omitted means every source. - `client_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which client tools' results contribute fetchable URLs: "all", "none", or an only or except list of client tool names from tools[]. - `server_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which server tools' results contribute fetchable URLs: "all", "none", or an only or except list of server tool names from tools[]; only web_search and web_fetch results ever contribute. - `user_input: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone` Whether URLs in user messages are fetchable: "all" or "none". - `use_cache: optional boolean` Whether to use cached content. Set to false to bypass the cache and fetch fresh content. Only set to false when the user explicitly requests fresh content or when fetching rapidly-changing sources. - `beta_web_search_tool_20260318: object` - `type: "web_search_20260318"` - `name: "web_search"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: optional array of string` If provided, only these domains will be included in results. Cannot be used alongside `blocked_domains`. - `blocked_domains: optional array of string` If provided, these domains will never appear in results. Cannot be used alongside `allowed_domains`. - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `response_inclusion: optional "full" or "excluded"` How this tool's result blocks appear in the API response when the result was consumed by a completed code_execution call in the same turn. 'full' returns the complete content (default). 'excluded' drops the nested server_tool_use and result block pair entirely. Results from direct calls, or from code_execution calls that paused before completing, are always returned in full so they can be sent back on the next turn. - `"full"` - `"excluded"` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `user_location: optional object` Parameters for the user's location. Used to provide more relevant search results. - `type: "approximate"` - `city: optional string` The city of the user. minLength: 1, maxLength: 255 - `country: optional string` The two letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1_alpha-2) of the user. minLength: 2, maxLength: 2 - `region: optional string` The region of the user. minLength: 1, maxLength: 255 - `timezone: optional string` The [IANA timezone](https://nodatime.org/TimeZones) of the user. minLength: 1, maxLength: 255 - `beta_web_fetch_tool_20260318: object` - `type: "web_fetch_20260318"` - `name: "web_fetch"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: optional array of string` List of domains to allow fetching from - `blocked_domains: optional array of string` List of domains to block fetching from - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `citations: optional object` Citations configuration for fetched documents. Citations are disabled by default. - `enabled: optional boolean` - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_content_tokens: optional number` Maximum number of tokens used by including web page text content in the context. The limit is approximate and does not apply to binary content such as PDFs. minimum: 1 - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `response_inclusion: optional "full" or "excluded"` How this tool's result blocks appear in the API response when the result was consumed by a completed code_execution call in the same turn. 'full' returns the complete content (default). 'excluded' drops the nested server_tool_use and result block pair entirely. Results from direct calls, or from code_execution calls that paused before completing, are always returned in full so they can be sent back on the next turn. - `"full"` - `"excluded"` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `url_sources: optional object` Which sources contribute to the set of URLs the tool may fetch. Omitted means every source. - `client_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which client tools' results contribute fetchable URLs: "all", "none", or an only or except list of client tool names from tools[]. - `server_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which server tools' results contribute fetchable URLs: "all", "none", or an only or except list of server tool names from tools[]; only web_search and web_fetch results ever contribute. - `user_input: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone` Whether URLs in user messages are fetchable: "all" or "none". - `use_cache: optional boolean` Whether to use cached content. Set to false to bypass the cache and fetch fresh content. Only set to false when the user explicitly requests fresh content or when fetching rapidly-changing sources. - `beta_advisor_tool_20260301: object` - `type: "advisor_20260301"` - `model: "claude-haiku-5-5" or "claude-sonnet-5-5" or "claude-fable-5-1" or 17 more or string` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-haiku-5-5"` Fastest model for high-volume, real-time tasks - `"claude-sonnet-5-5"` Efficient model for coding and agents - `"claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows - `"claude-opus-5-5"` Powerful intelligence for coding, knowledge work, and long-running agents - `"claude-mythos-5-1"` Our most capable model for cybersecurity and biology research, available through trusted access programs - `"claude-sonnet-5"` Efficient model for coding and agents - `"claude-fable-5"` Next generation of intelligence for the hardest knowledge work and coding problems - `"claude-mythos-5"` Most capable model for cybersecurity and biology research - `"claude-opus-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-8"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-7"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-6"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-6"` Best combination of speed and intelligence - `"claude-haiku-4-5"` - `"claude-haiku-4-5-20251001"` - `"claude-opus-4-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-5-20251101"` Powerful intelligence for long-running agents and coding - `"claude-mythos-preview"` **Deprecated**: Will reach end-of-life on June 30, 2026. Please migrate to claude-mythos-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. New class of intelligence, strongest in coding and cybersecurity - `"claude-sonnet-4-5"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `"claude-sonnet-4-5-20250929"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `name: "advisor"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `caching: optional object` Caching for the advisor's own prompt. When set, each advisor call writes a cache entry at the given TTL so subsequent calls in the same conversation read the stable prefix. When omitted, the advisor prompt is not cached. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_tokens: optional number` Bounds the advisor's total output (thinking + text) per call. When the advisor hits this cap, the returned advisor_result or advisor_redacted_result block carries stop_reason='max_tokens', and a truncation note is appended to the advice text the worker model sees (inside the encrypted blob in redacted mode). When set, the server also emits a remaining-tokens budget block in the advisor's prompt so the advisor self-shapes toward the cap. When omitted, the advisor model's default output cap applies and no budget block is emitted. minimum: 1024 - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_search_tool_bm25_20251119: object` - `type: "tool_search_tool_bm25_20251119" or "tool_search_tool_bm25"` - `"tool_search_tool_bm25_20251119"` - `"tool_search_tool_bm25"` - `name: "tool_search_tool_bm25"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_search_tool_regex_20251119: object` - `type: "tool_search_tool_regex_20251119" or "tool_search_tool_regex"` - `"tool_search_tool_regex_20251119"` - `"tool_search_tool_regex"` - `name: "tool_search_tool_regex"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_mcp_toolset: object` Configuration for a group of tools from an MCP server. Allows configuring enabled status and defer_loading for all tools from an MCP server, with optional per-tool overrides. - `type: "mcp_toolset"` - `mcp_server_name: string` Name of the MCP server to configure tools for minLength: 1, maxLength: 255 - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `configs: optional map[BetaMCPToolConfig]` Configuration overrides for specific tools, keyed by tool name - `defer_loading: optional boolean` - `enabled: optional boolean` - `default_config: optional object` Default configuration applied to all tools from this server - `defer_loading: optional boolean` - `enabled: optional boolean` - `tools: optional array of BetaMCPToolParam` The server's tool listing, pinned: when present, the server is not asked for its tools before sampling and exactly these entries, with `default_config` and `configs` applied, are the toolset's tools. Copy it from the `mcp_tool_listing` block of an earlier response. - `input_schema: map[unknown]` The tool's input schema as the MCP server lists it, verbatim. - `name: string` The tool's name as the MCP server lists it (not prefixed with the server name). minLength: 1 - `description: optional string` The tool's description as the MCP server lists it. - `beta_response_tool_removal_block: object` An entry of a `compaction` block's `tool_changes`: a tool of the request's `tools` (or an MCP tool or toolset) that the compacted range withdrew. Send it back unchanged. - `type: "tool_removal"` - `tool: BetaResponseToolChangeToolReference or BetaResponseToolChangeMCPToolReference or BetaResponseToolChangeMCPToolsetReference` A reference to the withdrawn `tools` entry, MCP tool or MCP toolset. - `beta_response_tool_change_tool_reference: object` Reference to a single tool, by the name the model uses to call it, as a `compaction` block's `tool_changes` entry reports it: a tool declared in `tools` or defined by an earlier `tool_addition` block. Send it back unchanged with the block. - `beta_response_tool_change_mcp_tool_reference: object` Reference to a single MCP tool, by its server and its name on that server, as a `compaction` block's `tool_changes` entry reports it. Send it back unchanged with the block. - `beta_response_tool_change_mcp_toolset_reference: object` Reference to every tool in the named MCP server's toolset, as a `compaction` block's `tool_changes` entry reports it. Send it back unchanged with the block. - `beta_fallback_block: object` Marks the point in `content` where one model's output gives way to the next. One block appears per hop where a preceding model actually ran this turn and declined. A turn where no preceding model ran and declined has no such boundary and carries no block — the signal for whether a fallback model served the response is the presence of a `fallback_message` entry in `usage.iterations`, not this block. The block is treated like a server-tool content block for streaming: it arrives via the standard `content_block_start` / `content_block_stop` pair and carries no deltas. - `type: "fallback"` - `from: object` The model whose output ends at this point — the model that declined at this hop. When the declining hop is the requested model, its `model` echoes the top-level `model` string the caller sent (alias or canonical); when the declining hop is a fallback model, its `model` is that model's canonical id. - `model: "claude-haiku-5-5" or "claude-sonnet-5-5" or "claude-fable-5-1" or 17 more or string` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-haiku-5-5"` Fastest model for high-volume, real-time tasks - `"claude-sonnet-5-5"` Efficient model for coding and agents - `"claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows - `"claude-opus-5-5"` Powerful intelligence for coding, knowledge work, and long-running agents - `"claude-mythos-5-1"` Our most capable model for cybersecurity and biology research, available through trusted access programs - `"claude-sonnet-5"` Efficient model for coding and agents - `"claude-fable-5"` Next generation of intelligence for the hardest knowledge work and coding problems - `"claude-mythos-5"` Most capable model for cybersecurity and biology research - `"claude-opus-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-8"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-7"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-6"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-6"` Best combination of speed and intelligence - `"claude-haiku-4-5"` - `"claude-haiku-4-5-20251001"` - `"claude-opus-4-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-5-20251101"` Powerful intelligence for long-running agents and coding - `"claude-mythos-preview"` **Deprecated**: Will reach end-of-life on June 30, 2026. Please migrate to claude-mythos-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. New class of intelligence, strongest in coding and cybersecurity - `"claude-sonnet-4-5"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `"claude-sonnet-4-5-20250929"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `to: object` The fallback model producing the content that follows this block. Its `model` is always the canonical id. - `model: "claude-haiku-5-5" or "claude-sonnet-5-5" or "claude-fable-5-1" or 17 more or string` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `trigger: object` What caused the `from` model to hand over at this hop. - `type: "refusal"` - `category: "cyber" or "bio" or "frontier_llm" or 2 more` The policy category that triggered the `from` model's refusal at this hop. `null` when the refusal doesn't map to a named category. Same vocabulary as `stop_details.category`. - `"cyber"` The request could enable cyber harm, such as malware or exploit development. Benign cybersecurity work can also trigger this category. - `"bio"` The request could enable biological harm, such as dangerous lab methods. Beneficial life sciences work can also trigger this category. - `"frontier_llm"` The request could assist the development of competing AI models, which is restricted under [Anthropic's commercial terms](https://www.anthropic.com/legal/commercial-terms). Benign machine learning work can also trigger this category. - `"reasoning_extraction"` The request asks the model to reproduce its internal reasoning in the response text. To get reasoning in a structured form instead, use [adaptive thinking](https://platform.claude.com/docs/en/build-with-claude/adaptive-thinking?sdk_languages=cli). - `"general_harms"` The request could be related to an area that was determined as harmful. Benign work might sometimes trigger this category. - `beta_mcp_tool_listing_block: object` The tool listing the server fetched from an MCP server while producing this response. Send the assistant message back unchanged, this block included, so later requests use this listing instead of asking the MCP server again. - `type: "mcp_tool_listing"` - `mcp_server_name: string` - `tools: array of BetaMCPTool` - `input_schema: map[unknown]` - `name: string` - `description: optional string` ### Beta Content Block Param - `beta_content_block_param: BetaTextBlockParam or BetaImageBlockParam or BetaRequestDocumentBlock or 21 more` - `beta_text_block_param: object` - `type: "text"` - `text: string` minLength: 1 - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `"5m"` - `"1h"` - `citations: optional array of BetaTextCitationParam` - `beta_citation_char_location_param: object` - `type: "char_location"` - `cited_text: string` - `document_index: number` minimum: 0 - `document_title: string` minLength: 1, maxLength: 500 - `end_char_index: number` - `start_char_index: number` minimum: 0 - `beta_citation_page_location_param: object` - `type: "page_location"` - `cited_text: string` - `document_index: number` minimum: 0 - `document_title: string` minLength: 1, maxLength: 500 - `end_page_number: number` - `start_page_number: number` minimum: 1 - `beta_citation_content_block_location_param: object` - `type: "content_block_location"` - `cited_text: string` The full text of the cited block range, concatenated. Always equals the contents of `content[start_block_index:end_block_index]` joined together. The text block is the minimal citable unit; this field is never a substring of a single block. Not counted toward output tokens, and not counted toward input tokens when sent back in subsequent turns. - `document_index: number` minimum: 0 - `document_title: string` minLength: 1, maxLength: 500 - `end_block_index: number` Exclusive 0-based end index of the cited block range in the source's `content` array. Always greater than `start_block_index`; a single-block citation has `end_block_index = start_block_index + 1`. - `start_block_index: number` 0-based index of the first cited block in the source's `content` array. minimum: 0 - `beta_citation_web_search_result_location_param: object` - `type: "web_search_result_location"` - `cited_text: string` - `encrypted_index: string` - `title: string` minLength: 1, maxLength: 512 - `url: string` minLength: 1 - `beta_citation_search_result_location_param: object` - `type: "search_result_location"` - `cited_text: string` The full text of the cited block range, concatenated. Always equals the contents of `content[start_block_index:end_block_index]` joined together. The text block is the minimal citable unit; this field is never a substring of a single block. Not counted toward output tokens, and not counted toward input tokens when sent back in subsequent turns. - `end_block_index: number` Exclusive 0-based end index of the cited block range in the source's `content` array. Always greater than `start_block_index`; a single-block citation has `end_block_index = start_block_index + 1`. - `search_result_index: number` 0-based index of the cited search result among all `search_result` content blocks in the request, in the order they appear across messages and tool results. Counted separately from `document_index`; server-side web search results are not included in this count. minimum: 0 - `source: string` - `start_block_index: number` 0-based index of the first cited block in the source's `content` array. minimum: 0 - `title: string` - `beta_image_block_param: object` - `type: "image"` - `source: BetaBase64ImageSource or BetaURLImageSource or BetaFileImageSource` - `beta_base64_image_source: object` - `type: "base64"` - `data: string` format: byte - `media_type: "image/jpeg" or "image/png" or "image/gif" or "image/webp"` - `"image/jpeg"` - `"image/png"` - `"image/gif"` - `"image/webp"` - `beta_url_image_source: object` - `type: "url"` - `url: string` - `beta_file_image_source: object` - `type: "file"` - `file_id: string` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `transformations: optional object` Configures the transformations the server applies to this image before the model observes it. Each key names a condition the server transforms images for; its value selects the transformation applied. Omitted keys keep their default behavior, and an empty object is equivalent to omitting the field. - `oversized_image: optional "downsize" or "error"` What the server does when this image exceeds the model's maximum image size. `"downsize"` (the default) scales the image down to fit, which changes the dimensions the model observes without telling you. `"error"` instead rejects the request with a 400 error naming the image's dimensions and the largest dimensions that fit, so you can scale the image deliberately — your image is never silently scaled down. - `"downsize"` - `"error"` - `beta_request_document_block: object` - `type: "document"` - `source: BetaBase64PDFSource or BetaPlainTextSource or BetaContentBlockSource or 2 more` - `beta_base64_pdf_source: object` - `type: "base64"` - `data: string` format: byte - `media_type: "application/pdf"` - `beta_plain_text_source: object` - `type: "text"` - `data: string` - `media_type: "text/plain"` - `beta_content_block_source: object` - `type: "content"` - `content: string or array of BetaContentBlockSourceContent` - `union_member_0: string` - `beta_content_block_source_content: array of BetaContentBlockSourceContent` - `beta_text_block_param: object` - `type: "text"` - `text: string` minLength: 1 - `cache_control: optional object` Create a cache control breakpoint at this content block. - `citations: optional array of BetaTextCitationParam` - `beta_image_block_param: object` - `type: "image"` - `source: BetaBase64ImageSource or BetaURLImageSource or BetaFileImageSource` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `transformations: optional object` Configures the transformations the server applies to this image before the model observes it. Each key names a condition the server transforms images for; its value selects the transformation applied. Omitted keys keep their default behavior, and an empty object is equivalent to omitting the field. - `beta_url_pdf_source: object` - `type: "url"` - `url: string` - `beta_file_document_source: object` - `type: "file"` - `file_id: string` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `citations: optional object` - `enabled: optional boolean` - `context: optional string` minLength: 1 - `title: optional string` minLength: 1, maxLength: 500 - `beta_search_result_block_param: object` - `type: "search_result"` - `content: array of BetaTextBlockParam` - `type: "text"` - `text: string` minLength: 1 - `cache_control: optional object` Create a cache control breakpoint at this content block. - `citations: optional array of BetaTextCitationParam` - `source: string` - `title: string` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `citations: optional object` - `enabled: optional boolean` - `beta_thinking_block_param: object` - `type: "thinking"` - `signature: string` The `signature` value of this thinking block, exactly as returned by the API in a previous response. Used to verify that the block was generated by Claude. Thinking blocks must be passed back unmodified and in their original order; a modified block results in a 400 `invalid_request_error`. - `thinking: string` The `thinking` text of this block as returned by the API. - `beta_redacted_thinking_block_param: object` - `type: "redacted_thinking"` - `data: string` The `data` value of this redacted thinking block, exactly as returned by the API in a previous response. Opaque and encrypted; pass it back unchanged. - `beta_tool_use_block_param: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: map[unknown]` - `name: string` minLength: 1, maxLength: 200 - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` - `beta_direct_caller: object` Tool invocation directly from the model. - `type: "direct"` - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `type: "code_execution_20250825"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `beta_server_tool_caller_20260120: object` - `type: "code_execution_20260120"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `toolset_name: optional string` For a toolset member tool_use, the toolset family this member belongs to. minLength: 1, maxLength: 64, pattern: ^[a-zA-Z0-9_-]+$ - `beta_tool_result_block_param: object` - `type: "tool_result"` - `tool_use_id: string` pattern: ^[a-zA-Z0-9_-]+$ - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `content: optional array of BetaTextBlockParam or BetaImageBlockParam or BetaSearchResultBlockParam or 3 more` - `beta_text_block_param: object` - `type: "text"` - `text: string` minLength: 1 - `cache_control: optional object` Create a cache control breakpoint at this content block. - `citations: optional array of BetaTextCitationParam` - `beta_image_block_param: object` - `type: "image"` - `source: BetaBase64ImageSource or BetaURLImageSource or BetaFileImageSource` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `transformations: optional object` Configures the transformations the server applies to this image before the model observes it. Each key names a condition the server transforms images for; its value selects the transformation applied. Omitted keys keep their default behavior, and an empty object is equivalent to omitting the field. - `beta_search_result_block_param: object` - `type: "search_result"` - `content: array of BetaTextBlockParam` - `source: string` - `title: string` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `citations: optional object` - `beta_request_document_block: object` - `type: "document"` - `source: BetaBase64PDFSource or BetaPlainTextSource or BetaContentBlockSource or 2 more` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `citations: optional object` - `context: optional string` minLength: 1 - `title: optional string` minLength: 1, maxLength: 500 - `beta_tool_reference_block_param: object` Tool reference block that can be included in tool_result content. - `type: "tool_reference"` - `tool_name: string` minLength: 1, maxLength: 256, pattern: ^[a-zA-Z0-9_-]{1,256}$ - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `beta_browser_state_block_param: object` The caller's browser state after a browser toolset member call — the full inventory of open tabs, which tab is active, and any side effects (tabs opened, download state changes) the call produced. At most one per `tool_result`, only on a non-error result answering a browser toolset member `tool_use`. The server renders the model-visible text from it; the model never sees the raw fields. - `type: "browser_state"` - `tabs: array of BetaBrowserStateTabEntry` All tabs open in the browser after this call — the full inventory, not a delta. May be empty. Whenever non-empty, exactly one entry carries `active: true`. maxItems: 100 - `tab_id: string` The caller-assigned identifier for this tab, unique within the inventory. minLength: 1, maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `title: string` The title of the page the tab is showing. May be empty. maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `url: string` The URL of the page the tab is showing. May be empty. maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `active: optional boolean` Whether this tab is the active tab after this call. Whenever `tabs` is non-empty, exactly one entry is marked `active: true`. - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `state_changes: optional array of BetaBrowserStateChange` Tabs opened and download state changes during this call. "Nothing to report" is expressed by omitting the field, never by an empty list. minItems: 1, maxItems: 200 - `beta_browser_state_change_tab_opened: object` A tab this call's execution opened that remains open at its end — the creation delta of the `tabs` inventory, not an event log. Carries only the `tab_id`; the tab's `title` and `url` live on its `tabs` entry, which must include the same `tab_id`. A tab opened during a failed call gets no deferred `tab_opened`; it simply appears in the next result's `tabs` inventory. - `type: "tab_opened"` - `tab_id: string` The `tab_id` of the opened tab, present in `tabs`. minLength: 1, maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `beta_browser_state_change_download_started: object` A file download that started during this call. - `type: "download_started"` - `download_id: string` The caller-assigned identifier for this download, stable across the state changes reporting it. minLength: 1, maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `url: string` The final post-redirect URL the download was served from. maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `beta_browser_state_change_download_completed: object` A file download that finished during this call, reported with the same `download_id` as its `download_started` — or without a prior `download_started`, when the download finished during the call that started it (at most one state change per `download_id` per result). - `type: "download_completed"` - `download_id: string` The caller-assigned identifier for this download, stable across the state changes reporting it. minLength: 1, maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `url: string` The final post-redirect URL the download was served from. maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `path: optional string` Where the executor saved the file, on the executor's filesystem. Only included when another tool in the same environment can read the file at that path. maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `size_bytes: optional number` The completed download's size. minimum: 0 - `beta_browser_state_change_download_failed: object` A file download that failed — or was cancelled — during this call. - `type: "download_failed"` - `download_id: string` The caller-assigned identifier for this download, stable across the state changes reporting it. minLength: 1, maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `url: string` The final post-redirect URL the download was served from. maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `error: optional string` The failure or cancellation detail, when known. maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `is_error: optional boolean` - `toolset_name: optional string` For a toolset member tool_result, the toolset family of the paired tool_use. minLength: 1, maxLength: 64, pattern: ^[a-zA-Z0-9_-]+$ - `beta_server_tool_use_block_param: object` - `type: "server_tool_use"` - `id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `input: map[unknown]` - `name: "advisor" or "web_search" or "web_fetch" or 5 more` - `"advisor"` - `"web_search"` - `"web_fetch"` - `"code_execution"` - `"bash_code_execution"` - `"text_editor_code_execution"` - `"tool_search_tool_regex"` - `"tool_search_tool_bm25"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` - `beta_direct_caller: object` Tool invocation directly from the model. - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `beta_server_tool_caller_20260120: object` - `beta_web_search_tool_result_block_param: object` - `type: "web_search_tool_result"` - `content: array of BetaWebSearchResultBlockParam or BetaWebSearchToolRequestError` - `Result Block: array of BetaWebSearchResultBlockParam` - `type: "web_search_result"` - `encrypted_content: string` - `title: string` - `url: string` - `page_age: optional string` - `beta_web_search_tool_request_error: object` - `type: "web_search_tool_result_error"` - `error_code: "invalid_tool_input" or "unavailable" or "max_uses_exceeded" or 3 more` - `"invalid_tool_input"` - `"unavailable"` - `"max_uses_exceeded"` - `"too_many_requests"` - `"query_too_long"` - `"request_too_large"` - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` - `beta_direct_caller: object` Tool invocation directly from the model. - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `beta_server_tool_caller_20260120: object` - `beta_web_fetch_tool_result_block_param: object` - `type: "web_fetch_tool_result"` - `content: BetaWebFetchToolResultErrorBlockParam or BetaWebFetchBlockParam` - `beta_web_fetch_tool_result_error_block_param: object` - `type: "web_fetch_tool_result_error"` - `error_code: "invalid_tool_input" or "url_too_long" or "url_not_allowed" or 7 more` - `"invalid_tool_input"` - `"url_too_long"` - `"url_not_allowed"` - `"url_not_in_prior_context"` - `"url_not_accessible"` - `"unsupported_content_type"` - `"too_many_requests"` - `"max_uses_exceeded"` - `"unavailable"` - `"content_too_large"` - `beta_web_fetch_block_param: object` - `type: "web_fetch_result"` - `content: object` - `type: "document"` - `source: BetaBase64PDFSource or BetaPlainTextSource or BetaContentBlockSource or 2 more` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `citations: optional object` - `context: optional string` minLength: 1 - `title: optional string` minLength: 1, maxLength: 500 - `url: string` Fetched content URL - `retrieved_at: optional string` ISO 8601 timestamp when the content was retrieved - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` - `beta_direct_caller: object` Tool invocation directly from the model. - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `beta_server_tool_caller_20260120: object` - `beta_advisor_tool_result_block_param: object` - `type: "advisor_tool_result"` - `content: BetaAdvisorToolResultErrorParam or BetaAdvisorResultBlockParam or BetaAdvisorRedactedResultBlockParam` - `beta_advisor_tool_result_error_param: object` - `type: "advisor_tool_result_error"` - `error_code: "max_uses_exceeded" or "prompt_too_long" or "too_many_requests" or 4 more` - `"max_uses_exceeded"` - `"prompt_too_long"` - `"too_many_requests"` - `"overloaded"` - `"unavailable"` - `"execution_time_exceeded"` - `"model_not_found"` - `beta_advisor_result_block_param: object` - `type: "advisor_result"` - `text: string` - `stop_reason: optional string` - `beta_advisor_redacted_result_block_param: object` - `type: "advisor_redacted_result"` - `encrypted_content: string` Opaque blob produced by a prior response; must be round-tripped verbatim. - `stop_reason: optional string` - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `beta_code_execution_tool_result_block_param: object` - `type: "code_execution_tool_result"` - `content: BetaCodeExecutionToolResultErrorParam or BetaCodeExecutionResultBlockParam or BetaEncryptedCodeExecutionResultBlockParam` - `beta_code_execution_tool_result_error_param: object` - `type: "code_execution_tool_result_error"` - `error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or "execution_time_exceeded"` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `beta_code_execution_result_block_param: object` - `type: "code_execution_result"` - `content: array of BetaCodeExecutionOutputBlockParam` - `type: "code_execution_output"` - `file_id: string` - `return_code: number` - `stderr: string` - `stdout: string` - `beta_encrypted_code_execution_result_block_param: object` Code execution result with encrypted stdout for PFC + web_search results. - `type: "encrypted_code_execution_result"` - `content: array of BetaCodeExecutionOutputBlockParam` - `type: "code_execution_output"` - `file_id: string` - `encrypted_stdout: string` - `return_code: number` - `stderr: string` - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `beta_bash_code_execution_tool_result_block_param: object` - `type: "bash_code_execution_tool_result"` - `content: BetaBashCodeExecutionToolResultErrorParam or BetaBashCodeExecutionResultBlockParam` - `beta_bash_code_execution_tool_result_error_param: object` - `type: "bash_code_execution_tool_result_error"` - `error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or 2 more` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `"output_file_too_large"` - `beta_bash_code_execution_result_block_param: object` - `type: "bash_code_execution_result"` - `content: array of BetaBashCodeExecutionOutputBlockParam` - `type: "bash_code_execution_output"` - `file_id: string` - `return_code: number` - `stderr: string` - `stdout: string` - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `beta_text_editor_code_execution_tool_result_block_param: object` - `type: "text_editor_code_execution_tool_result"` - `content: BetaTextEditorCodeExecutionToolResultErrorParam or BetaTextEditorCodeExecutionViewResultBlockParam or BetaTextEditorCodeExecutionCreateResultBlockParam or BetaTextEditorCodeExecutionStrReplaceResultBlockParam` - `beta_text_editor_code_execution_tool_result_error_param: object` - `type: "text_editor_code_execution_tool_result_error"` - `error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or 2 more` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `"file_not_found"` - `error_message: optional string` - `beta_text_editor_code_execution_view_result_block_param: object` - `type: "text_editor_code_execution_view_result"` - `content: string` - `file_type: "text" or "image" or "pdf"` - `"text"` - `"image"` - `"pdf"` - `num_lines: optional number` - `start_line: optional number` - `total_lines: optional number` - `beta_text_editor_code_execution_create_result_block_param: object` - `type: "text_editor_code_execution_create_result"` - `is_file_update: boolean` - `beta_text_editor_code_execution_str_replace_result_block_param: object` - `type: "text_editor_code_execution_str_replace_result"` - `lines: optional array of string` - `new_lines: optional number` - `new_start: optional number` - `old_lines: optional number` - `old_start: optional number` - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `beta_tool_search_tool_result_block_param: object` - `type: "tool_search_tool_result"` - `content: BetaToolSearchToolResultErrorParam or BetaToolSearchToolSearchResultBlockParam` - `beta_tool_search_tool_result_error_param: object` - `type: "tool_search_tool_result_error"` - `error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or "execution_time_exceeded"` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `error_message: optional string` - `beta_tool_search_tool_search_result_block_param: object` - `type: "tool_search_tool_search_result"` - `tool_references: array of BetaToolReferenceBlockParam` - `type: "tool_reference"` - `tool_name: string` minLength: 1, maxLength: 256, pattern: ^[a-zA-Z0-9_-]{1,256}$ - `cache_control: optional object` Create a cache control breakpoint at this content block. - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `beta_mcp_tool_use_block_param: object` - `type: "mcp_tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: map[unknown]` - `name: string` - `server_name: string` The name of the MCP server - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `beta_request_mcp_tool_result_block_param: object` - `type: "mcp_tool_result"` - `tool_use_id: string` pattern: ^[a-zA-Z0-9_-]+$ - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `content: optional string or array of BetaTextBlockParam` - `union_member_0: string` - `beta_mcp_tool_result_block_param_content: array of BetaTextBlockParam` - `type: "text"` - `text: string` minLength: 1 - `cache_control: optional object` Create a cache control breakpoint at this content block. - `citations: optional array of BetaTextCitationParam` - `is_error: optional boolean` - `beta_container_upload_block_param: object` A content block that represents a file to be uploaded to the container Files uploaded via this block will be available in the container's input directory. - `type: "container_upload"` - `file_id: string` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `beta_compaction_block_param: object` A compaction block containing summary of previous context. Users should round-trip these blocks from responses to subsequent requests to maintain context across compaction boundaries. When content is None, the block represents a failed compaction. The server treats these as no-ops. Empty string content is not allowed. - `type: "compaction"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `content: optional string` Summary of previously compacted content, or null if compaction failed - `encrypted_content: optional string` Opaque metadata from prior compaction, to be round-tripped verbatim - `signature: optional string` The block's signature as returned, to be sent back verbatim - `tool_changes: optional array of BetaRequestToolAdditionBlock or BetaRequestToolRemovalBlock` The tool changes of the compacted range, as the server returned them on this block: the `tool_addition` and `tool_removal` entries that take the request's `tools` to the tool set in effect at the end of the range. Send them back unchanged with the block. - `beta_request_tool_addition_block: object` Mid-conversation directive to make a tool available. `tool` is a reference to a tool (or MCP toolset) declared in the request's `tools`. Under the `inline-tools-2026-09-15` beta it may instead be a reference to a tool defined earlier in `messages`, or a `tool_definition` object that carries an inline tool definition in `definition` (the same object a `tools` entry holds). An `mcp_toolset` definition also requires the `mcp-client-2026-09-15` beta. The tool is offered to the model from this point in the conversation onward. - `type: "tool_addition"` - `tool: BetaToolChangeToolReference or BetaToolChangeMCPToolReference or BetaToolChangeMCPToolsetReference or BetaToolChangeToolDefinitionParam` - `beta_tool_change_tool_reference: object` Reference to a single tool, by the name the model uses to call it: a tool declared in `tools` or defined by an earlier `tool_addition` block. Does not accept the composed `{server}_{name}` form the server assigns to MCP-resolved tools; use `mcp_tool_reference` or `mcp_toolset_reference` for those. - `type: "tool_reference"` - `name: string` pattern: ^[a-zA-Z0-9_-]{1,128}$ - `beta_tool_change_mcp_tool_reference: object` Reference to a single MCP tool by its server and remote name; the same `server_name`/`name` pair `mcp_tool_use` carries. - `type: "mcp_tool_reference"` - `name: string` - `server_name: string` - `beta_tool_change_mcp_toolset_reference: object` Reference to every tool in the named MCP server's toolset. - `type: "mcp_toolset_reference"` - `server_name: string` - `beta_tool_change_tool_definition_param: object` A tool defined by value: `definition` is a `tools` entry (any kind `tools` accepts, an MCP toolset included). An `mcp_toolset` given here also requires the `mcp-client-2026-09-15` beta. - `type: "tool_definition"` - `definition: BetaTool or BetaToolBash20241022 or BetaToolBash20250124 or 25 more` - `beta_tool: object` - `type: optional "custom"` - `input_schema: object` [JSON schema](https://json-schema.org/draft/2020-12) for this tool's input. This defines the shape of the `input` that your tool accepts and that the model will produce. - `type: "object"` - `properties: optional map[unknown]` - `required: optional array of string` - `name: string` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. minLength: 1, maxLength: 128, pattern: ^[a-zA-Z0-9_-]{1,128}$ - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `description: optional string` Description of what this tool does. Tool descriptions should be as detailed as possible. The more information that the model has about what the tool is and how to use it, the better it will perform. You can use natural language descriptions to reinforce important aspects of the tool input JSON schema. - `eager_input_streaming: optional boolean` Enable eager input streaming for this tool. When true, tool input parameters will be streamed incrementally as they are generated, and types will be inferred on-the-fly rather than buffering the full JSON output. When false, streaming is disabled for this tool even if the fine-grained-tool-streaming beta is active. When null (default), uses the default behavior based on beta headers. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_bash_20241022: object` - `type: "bash_20241022"` - `name: "bash"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_bash_20250124: object` - `type: "bash_20250124"` - `name: "bash"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_code_execution_tool_20250522: object` - `type: "code_execution_20250522"` - `name: "code_execution"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_code_execution_tool_20250825: object` - `type: "code_execution_20250825"` - `name: "code_execution"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_code_execution_tool_20260120: object` Code execution tool with REPL state persistence (daemon mode + gVisor checkpoint). - `type: "code_execution_20260120"` - `name: "code_execution"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_code_execution_tool_20260521: object` Code execution tool with REPL state persistence. - `type: "code_execution_20260521"` - `name: "code_execution"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_browser_toolset_20260801: object` The browser toolset: a single `tools[]` entry (carrying no `name`) that declares the browser tool family. The model is served the family's tool with any members disabled via `configs` removed from its schema. - `type: "browser_toolset_20260801"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `configs: optional object` Sparse per-member overrides, keyed by member name. Absent, null, and {} are equivalent; a member's defaults apply wherever its key is absent. - `type: optional object` `type`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `close_tab: optional object` `close_tab`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `double_click: optional object` `double_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `file_upload: optional object` `file_upload`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `find: optional object` `find`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `form_input: optional object` `form_input`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `get_page_text: optional object` `get_page_text`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `hold_key: optional object` `hold_key`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `hover: optional object` `hover`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `javascript_exec: optional object` `javascript_exec`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `key: optional object` `key`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_click: optional object` `left_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_click_drag: optional object` `left_click_drag`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_mouse_down: optional object` `left_mouse_down`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_mouse_up: optional object` `left_mouse_up`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `list_tabs: optional object` `list_tabs`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `middle_click: optional object` `middle_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `mouse_move: optional object` `mouse_move`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `navigate: optional object` `navigate`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `new_tab: optional object` `new_tab`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `read_console: optional object` `read_console`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `read_network: optional object` `read_network`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `read_page: optional object` `read_page`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `right_click: optional object` `right_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `screenshot: optional object` `screenshot`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `scroll: optional object` `scroll`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `scroll_to: optional object` `scroll_to`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `switch_tab: optional object` `switch_tab`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `triple_click: optional object` `triple_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `wait: optional object` `wait`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `zoom: optional object` `zoom`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `beta_tool_computer_use_20241022: object` - `type: "computer_20241022"` - `display_height_px: number` The height of the display in pixels. minimum: 1 - `display_width_px: number` The width of the display in pixels. minimum: 1 - `name: "computer"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `display_number: optional number` The X11 display number (e.g. 0, 1) for the display. minimum: 0 - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_memory_tool_20250818: object` - `type: "memory_20250818"` - `name: "memory"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_computer_use_20250124: object` - `type: "computer_20250124"` - `display_height_px: number` The height of the display in pixels. minimum: 1 - `display_width_px: number` The width of the display in pixels. minimum: 1 - `name: "computer"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `display_number: optional number` The X11 display number (e.g. 0, 1) for the display. minimum: 0 - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_text_editor_20241022: object` - `type: "text_editor_20241022"` - `name: "str_replace_editor"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_computer_use_20251124: object` - `type: "computer_20251124"` - `display_height_px: number` The height of the display in pixels. minimum: 1 - `display_width_px: number` The width of the display in pixels. minimum: 1 - `name: "computer"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `display_number: optional number` The X11 display number (e.g. 0, 1) for the display. minimum: 0 - `enable_zoom: optional boolean` Whether to enable an action to take a zoomed-in screenshot of the screen. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_computer_toolset_20260801: object` The computer toolset: a single `tools[]` entry (carrying no `name`) that declares the computer tool family. The model is served the family's tool with any members disabled via `configs` removed from its schema. Every member is enabled by default, zoom included. The single-tool options `display_number` and `enable_zoom` are not fields of a toolset entry — it carries only `type`, `configs`, and `cache_control`; zoom is controlled via `configs.zoom.enabled`. - `type: "computer_toolset_20260801"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `configs: optional object` Sparse per-member overrides, keyed by member name. Absent, null, and {} are equivalent; a member's defaults apply wherever its key is absent. - `type: optional object` `type`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `cursor_position: optional object` `cursor_position`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `double_click: optional object` `double_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `hold_key: optional object` `hold_key`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `key: optional object` `key`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_click: optional object` `left_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_click_drag: optional object` `left_click_drag`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_mouse_down: optional object` `left_mouse_down`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_mouse_up: optional object` `left_mouse_up`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `middle_click: optional object` `middle_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `mouse_move: optional object` `mouse_move`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `right_click: optional object` `right_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `screenshot: optional object` `screenshot`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `scroll: optional object` `scroll`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `triple_click: optional object` `triple_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `wait: optional object` `wait`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `zoom: optional object` `zoom`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `beta_tool_text_editor_20250124: object` - `type: "text_editor_20250124"` - `name: "str_replace_editor"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_text_editor_20250429: object` - `type: "text_editor_20250429"` - `name: "str_replace_based_edit_tool"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_text_editor_20250728: object` - `type: "text_editor_20250728"` - `name: "str_replace_based_edit_tool"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: optional array of map[unknown]` - `max_characters: optional number` Maximum number of characters to display when viewing a file. If not specified, defaults to displaying the full file. minimum: 1 - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_web_search_tool_20250305: object` - `type: "web_search_20250305"` - `name: "web_search"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: optional array of string` If provided, only these domains will be included in results. Cannot be used alongside `blocked_domains`. - `blocked_domains: optional array of string` If provided, these domains will never appear in results. Cannot be used alongside `allowed_domains`. - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `user_location: optional object` Parameters for the user's location. Used to provide more relevant search results. - `type: "approximate"` - `city: optional string` The city of the user. minLength: 1, maxLength: 255 - `country: optional string` The two letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1_alpha-2) of the user. minLength: 2, maxLength: 2 - `region: optional string` The region of the user. minLength: 1, maxLength: 255 - `timezone: optional string` The [IANA timezone](https://nodatime.org/TimeZones) of the user. minLength: 1, maxLength: 255 - `beta_web_fetch_tool_20250910: object` - `type: "web_fetch_20250910"` - `name: "web_fetch"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: optional array of string` List of domains to allow fetching from - `blocked_domains: optional array of string` List of domains to block fetching from - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `citations: optional object` Citations configuration for fetched documents. Citations are disabled by default. - `enabled: optional boolean` - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_content_tokens: optional number` Maximum number of tokens used by including web page text content in the context. The limit is approximate and does not apply to binary content such as PDFs. minimum: 1 - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `url_sources: optional object` Which sources contribute to the set of URLs the tool may fetch. Omitted means every source. - `client_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which client tools' results contribute fetchable URLs: "all", "none", or an only or except list of client tool names from tools[]. - `beta_web_fetch_url_source_all: object` The `url_sources` variant under which a source contributes in full: every result of the tool filter's source, or all user input. - `type: "all"` - `beta_web_fetch_url_source_none: object` The `url_sources` variant under which a source contributes nothing: no result of the tool filter's source, or no user input. - `type: "none"` - `beta_web_fetch_url_source_only: object` The tool filter variant under which only the named tools' results contribute. - `type: "only"` - `tools: array of BetaWebFetchURLSourceToolReference` - `type: "tool_reference"` - `name: string` - `beta_web_fetch_url_source_except: object` The tool filter variant under which every result but the named tools' contributes. - `type: "except"` - `tools: array of BetaWebFetchURLSourceToolReference` - `type: "tool_reference"` - `name: string` - `server_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which server tools' results contribute fetchable URLs: "all", "none", or an only or except list of server tool names from tools[]; only web_search and web_fetch results ever contribute. - `beta_web_fetch_url_source_all: object` The `url_sources` variant under which a source contributes in full: every result of the tool filter's source, or all user input. - `beta_web_fetch_url_source_none: object` The `url_sources` variant under which a source contributes nothing: no result of the tool filter's source, or no user input. - `beta_web_fetch_url_source_only: object` The tool filter variant under which only the named tools' results contribute. - `beta_web_fetch_url_source_except: object` The tool filter variant under which every result but the named tools' contributes. - `user_input: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone` Whether URLs in user messages are fetchable: "all" or "none". - `beta_web_fetch_url_source_all: object` The `url_sources` variant under which a source contributes in full: every result of the tool filter's source, or all user input. - `beta_web_fetch_url_source_none: object` The `url_sources` variant under which a source contributes nothing: no result of the tool filter's source, or no user input. - `beta_web_search_tool_20260209: object` - `type: "web_search_20260209"` - `name: "web_search"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: optional array of string` If provided, only these domains will be included in results. Cannot be used alongside `blocked_domains`. - `blocked_domains: optional array of string` If provided, these domains will never appear in results. Cannot be used alongside `allowed_domains`. - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `user_location: optional object` Parameters for the user's location. Used to provide more relevant search results. - `type: "approximate"` - `city: optional string` The city of the user. minLength: 1, maxLength: 255 - `country: optional string` The two letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1_alpha-2) of the user. minLength: 2, maxLength: 2 - `region: optional string` The region of the user. minLength: 1, maxLength: 255 - `timezone: optional string` The [IANA timezone](https://nodatime.org/TimeZones) of the user. minLength: 1, maxLength: 255 - `beta_web_fetch_tool_20260209: object` - `type: "web_fetch_20260209"` - `name: "web_fetch"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: optional array of string` List of domains to allow fetching from - `blocked_domains: optional array of string` List of domains to block fetching from - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `citations: optional object` Citations configuration for fetched documents. Citations are disabled by default. - `enabled: optional boolean` - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_content_tokens: optional number` Maximum number of tokens used by including web page text content in the context. The limit is approximate and does not apply to binary content such as PDFs. minimum: 1 - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `url_sources: optional object` Which sources contribute to the set of URLs the tool may fetch. Omitted means every source. - `client_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which client tools' results contribute fetchable URLs: "all", "none", or an only or except list of client tool names from tools[]. - `server_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which server tools' results contribute fetchable URLs: "all", "none", or an only or except list of server tool names from tools[]; only web_search and web_fetch results ever contribute. - `user_input: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone` Whether URLs in user messages are fetchable: "all" or "none". - `beta_web_fetch_tool_20260309: object` Web fetch tool with use_cache parameter for bypassing cached content. - `type: "web_fetch_20260309"` - `name: "web_fetch"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: optional array of string` List of domains to allow fetching from - `blocked_domains: optional array of string` List of domains to block fetching from - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `citations: optional object` Citations configuration for fetched documents. Citations are disabled by default. - `enabled: optional boolean` - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_content_tokens: optional number` Maximum number of tokens used by including web page text content in the context. The limit is approximate and does not apply to binary content such as PDFs. minimum: 1 - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `url_sources: optional object` Which sources contribute to the set of URLs the tool may fetch. Omitted means every source. - `client_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which client tools' results contribute fetchable URLs: "all", "none", or an only or except list of client tool names from tools[]. - `server_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which server tools' results contribute fetchable URLs: "all", "none", or an only or except list of server tool names from tools[]; only web_search and web_fetch results ever contribute. - `user_input: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone` Whether URLs in user messages are fetchable: "all" or "none". - `use_cache: optional boolean` Whether to use cached content. Set to false to bypass the cache and fetch fresh content. Only set to false when the user explicitly requests fresh content or when fetching rapidly-changing sources. - `beta_web_search_tool_20260318: object` - `type: "web_search_20260318"` - `name: "web_search"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: optional array of string` If provided, only these domains will be included in results. Cannot be used alongside `blocked_domains`. - `blocked_domains: optional array of string` If provided, these domains will never appear in results. Cannot be used alongside `allowed_domains`. - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `response_inclusion: optional "full" or "excluded"` How this tool's result blocks appear in the API response when the result was consumed by a completed code_execution call in the same turn. 'full' returns the complete content (default). 'excluded' drops the nested server_tool_use and result block pair entirely. Results from direct calls, or from code_execution calls that paused before completing, are always returned in full so they can be sent back on the next turn. - `"full"` - `"excluded"` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `user_location: optional object` Parameters for the user's location. Used to provide more relevant search results. - `type: "approximate"` - `city: optional string` The city of the user. minLength: 1, maxLength: 255 - `country: optional string` The two letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1_alpha-2) of the user. minLength: 2, maxLength: 2 - `region: optional string` The region of the user. minLength: 1, maxLength: 255 - `timezone: optional string` The [IANA timezone](https://nodatime.org/TimeZones) of the user. minLength: 1, maxLength: 255 - `beta_web_fetch_tool_20260318: object` - `type: "web_fetch_20260318"` - `name: "web_fetch"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: optional array of string` List of domains to allow fetching from - `blocked_domains: optional array of string` List of domains to block fetching from - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `citations: optional object` Citations configuration for fetched documents. Citations are disabled by default. - `enabled: optional boolean` - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_content_tokens: optional number` Maximum number of tokens used by including web page text content in the context. The limit is approximate and does not apply to binary content such as PDFs. minimum: 1 - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `response_inclusion: optional "full" or "excluded"` How this tool's result blocks appear in the API response when the result was consumed by a completed code_execution call in the same turn. 'full' returns the complete content (default). 'excluded' drops the nested server_tool_use and result block pair entirely. Results from direct calls, or from code_execution calls that paused before completing, are always returned in full so they can be sent back on the next turn. - `"full"` - `"excluded"` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `url_sources: optional object` Which sources contribute to the set of URLs the tool may fetch. Omitted means every source. - `client_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which client tools' results contribute fetchable URLs: "all", "none", or an only or except list of client tool names from tools[]. - `server_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which server tools' results contribute fetchable URLs: "all", "none", or an only or except list of server tool names from tools[]; only web_search and web_fetch results ever contribute. - `user_input: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone` Whether URLs in user messages are fetchable: "all" or "none". - `use_cache: optional boolean` Whether to use cached content. Set to false to bypass the cache and fetch fresh content. Only set to false when the user explicitly requests fresh content or when fetching rapidly-changing sources. - `beta_advisor_tool_20260301: object` - `type: "advisor_20260301"` - `model: "claude-haiku-5-5" or "claude-sonnet-5-5" or "claude-fable-5-1" or 17 more or string` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-haiku-5-5"` Fastest model for high-volume, real-time tasks - `"claude-sonnet-5-5"` Efficient model for coding and agents - `"claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows - `"claude-opus-5-5"` Powerful intelligence for coding, knowledge work, and long-running agents - `"claude-mythos-5-1"` Our most capable model for cybersecurity and biology research, available through trusted access programs - `"claude-sonnet-5"` Efficient model for coding and agents - `"claude-fable-5"` Next generation of intelligence for the hardest knowledge work and coding problems - `"claude-mythos-5"` Most capable model for cybersecurity and biology research - `"claude-opus-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-8"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-7"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-6"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-6"` Best combination of speed and intelligence - `"claude-haiku-4-5"` - `"claude-haiku-4-5-20251001"` - `"claude-opus-4-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-5-20251101"` Powerful intelligence for long-running agents and coding - `"claude-mythos-preview"` **Deprecated**: Will reach end-of-life on June 30, 2026. Please migrate to claude-mythos-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. New class of intelligence, strongest in coding and cybersecurity - `"claude-sonnet-4-5"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `"claude-sonnet-4-5-20250929"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `name: "advisor"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `caching: optional object` Caching for the advisor's own prompt. When set, each advisor call writes a cache entry at the given TTL so subsequent calls in the same conversation read the stable prefix. When omitted, the advisor prompt is not cached. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_tokens: optional number` Bounds the advisor's total output (thinking + text) per call. When the advisor hits this cap, the returned advisor_result or advisor_redacted_result block carries stop_reason='max_tokens', and a truncation note is appended to the advice text the worker model sees (inside the encrypted blob in redacted mode). When set, the server also emits a remaining-tokens budget block in the advisor's prompt so the advisor self-shapes toward the cap. When omitted, the advisor model's default output cap applies and no budget block is emitted. minimum: 1024 - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_search_tool_bm25_20251119: object` - `type: "tool_search_tool_bm25_20251119" or "tool_search_tool_bm25"` - `"tool_search_tool_bm25_20251119"` - `"tool_search_tool_bm25"` - `name: "tool_search_tool_bm25"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_search_tool_regex_20251119: object` - `type: "tool_search_tool_regex_20251119" or "tool_search_tool_regex"` - `"tool_search_tool_regex_20251119"` - `"tool_search_tool_regex"` - `name: "tool_search_tool_regex"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_mcp_toolset: object` Configuration for a group of tools from an MCP server. Allows configuring enabled status and defer_loading for all tools from an MCP server, with optional per-tool overrides. - `type: "mcp_toolset"` - `mcp_server_name: string` Name of the MCP server to configure tools for minLength: 1, maxLength: 255 - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `configs: optional map[BetaMCPToolConfig]` Configuration overrides for specific tools, keyed by tool name - `defer_loading: optional boolean` - `enabled: optional boolean` - `default_config: optional object` Default configuration applied to all tools from this server - `defer_loading: optional boolean` - `enabled: optional boolean` - `tools: optional array of BetaMCPToolParam` The server's tool listing, pinned: when present, the server is not asked for its tools before sampling and exactly these entries, with `default_config` and `configs` applied, are the toolset's tools. Copy it from the `mcp_tool_listing` block of an earlier response. - `input_schema: map[unknown]` The tool's input schema as the MCP server lists it, verbatim. - `name: string` The tool's name as the MCP server lists it (not prefixed with the server name). minLength: 1 - `description: optional string` The tool's description as the MCP server lists it. - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `beta_request_tool_removal_block: object` Mid-conversation directive to withdraw a tool. `tool` references a tool (or MCP toolset) by name: one declared in the request's `tools` or defined earlier in `messages`. It is no longer offered to the model from this point in the conversation onward. - `type: "tool_removal"` - `tool: BetaToolChangeToolReference or BetaToolChangeMCPToolReference or BetaToolChangeMCPToolsetReference` - `beta_tool_change_tool_reference: object` Reference to a single tool, by the name the model uses to call it: a tool declared in `tools` or defined by an earlier `tool_addition` block. Does not accept the composed `{server}_{name}` form the server assigns to MCP-resolved tools; use `mcp_tool_reference` or `mcp_toolset_reference` for those. - `beta_tool_change_mcp_tool_reference: object` Reference to a single MCP tool by its server and remote name; the same `server_name`/`name` pair `mcp_tool_use` carries. - `beta_tool_change_mcp_toolset_reference: object` Reference to every tool in the named MCP server's toolset. - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `beta_request_tool_addition_block: object` Mid-conversation directive to make a tool available. `tool` is a reference to a tool (or MCP toolset) declared in the request's `tools`. Under the `inline-tools-2026-09-15` beta it may instead be a reference to a tool defined earlier in `messages`, or a `tool_definition` object that carries an inline tool definition in `definition` (the same object a `tools` entry holds). An `mcp_toolset` definition also requires the `mcp-client-2026-09-15` beta. The tool is offered to the model from this point in the conversation onward. - `type: "tool_addition"` - `tool: BetaToolChangeToolReference or BetaToolChangeMCPToolReference or BetaToolChangeMCPToolsetReference or BetaToolChangeToolDefinitionParam` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `beta_request_tool_removal_block: object` Mid-conversation directive to withdraw a tool. `tool` references a tool (or MCP toolset) by name: one declared in the request's `tools` or defined earlier in `messages`. It is no longer offered to the model from this point in the conversation onward. - `type: "tool_removal"` - `tool: BetaToolChangeToolReference or BetaToolChangeMCPToolReference or BetaToolChangeMCPToolsetReference` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `beta_mcp_tool_listing_block_param: object` The tool listing an MCP server returned while an earlier response was produced, as that response carried it. Send the assistant message back unchanged, this block included, and the server uses this listing for the matching `mcp_toolset` instead of asking the MCP server again. - `type: "mcp_tool_listing"` - `mcp_server_name: string` The name of the MCP server this listing came from, as `mcp_servers` declares it. minLength: 1, maxLength: 255 - `tools: array of BetaMCPToolParam` The server's tools, exactly as the response listed them. - `input_schema: map[unknown]` The tool's input schema as the MCP server lists it, verbatim. - `name: string` The tool's name as the MCP server lists it (not prefixed with the server name). minLength: 1 - `description: optional string` The tool's description as the MCP server lists it. - `beta_fallback_block_param: object` A `fallback` block echoed back from a prior response. Accepted in `messages[].content` and not rendered into the prompt; not validated against the request's `fallbacks` chain or top-level `model`. Echo the assistant turn back verbatim, including this block in its original position. The block marks the boundary between content produced before and after a fallback hop, and the server relies on that boundary to validate the turn: when thinking runs flank the boundary, omitting the block merges them into one span the server cannot validate (the request is rejected), and moving it into the middle of a single run is likewise rejected; between non-thinking blocks the block's placement has no validation effect. - `type: "fallback"` - `from: object` Identifies one hop of a fallback transition. - `model: "claude-haiku-5-5" or "claude-sonnet-5-5" or "claude-fable-5-1" or 17 more or string` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-haiku-5-5"` Fastest model for high-volume, real-time tasks - `"claude-sonnet-5-5"` Efficient model for coding and agents - `"claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows - `"claude-opus-5-5"` Powerful intelligence for coding, knowledge work, and long-running agents - `"claude-mythos-5-1"` Our most capable model for cybersecurity and biology research, available through trusted access programs - `"claude-sonnet-5"` Efficient model for coding and agents - `"claude-fable-5"` Next generation of intelligence for the hardest knowledge work and coding problems - `"claude-mythos-5"` Most capable model for cybersecurity and biology research - `"claude-opus-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-8"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-7"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-6"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-6"` Best combination of speed and intelligence - `"claude-haiku-4-5"` - `"claude-haiku-4-5-20251001"` - `"claude-opus-4-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-5-20251101"` Powerful intelligence for long-running agents and coding - `"claude-mythos-preview"` **Deprecated**: Will reach end-of-life on June 30, 2026. Please migrate to claude-mythos-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. New class of intelligence, strongest in coding and cybersecurity - `"claude-sonnet-4-5"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `"claude-sonnet-4-5-20250929"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `to: object` Identifies one hop of a fallback transition. - `model: "claude-haiku-5-5" or "claude-sonnet-5-5" or "claude-fable-5-1" or 17 more or string` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `trigger: optional unknown` The response block's `trigger`, echoed verbatim. Accepted and ignored by the server; any object or `null` is allowed. ### Beta Content Block Source - `beta_content_block_source: object` - `type: "content"` - `content: string or array of BetaContentBlockSourceContent` - `union_member_0: string` - `beta_content_block_source_content: array of BetaContentBlockSourceContent` - `beta_text_block_param: object` - `type: "text"` - `text: string` minLength: 1 - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `"5m"` - `"1h"` - `citations: optional array of BetaTextCitationParam` - `beta_citation_char_location_param: object` - `type: "char_location"` - `cited_text: string` - `document_index: number` minimum: 0 - `document_title: string` minLength: 1, maxLength: 500 - `end_char_index: number` - `start_char_index: number` minimum: 0 - `beta_citation_page_location_param: object` - `type: "page_location"` - `cited_text: string` - `document_index: number` minimum: 0 - `document_title: string` minLength: 1, maxLength: 500 - `end_page_number: number` - `start_page_number: number` minimum: 1 - `beta_citation_content_block_location_param: object` - `type: "content_block_location"` - `cited_text: string` The full text of the cited block range, concatenated. Always equals the contents of `content[start_block_index:end_block_index]` joined together. The text block is the minimal citable unit; this field is never a substring of a single block. Not counted toward output tokens, and not counted toward input tokens when sent back in subsequent turns. - `document_index: number` minimum: 0 - `document_title: string` minLength: 1, maxLength: 500 - `end_block_index: number` Exclusive 0-based end index of the cited block range in the source's `content` array. Always greater than `start_block_index`; a single-block citation has `end_block_index = start_block_index + 1`. - `start_block_index: number` 0-based index of the first cited block in the source's `content` array. minimum: 0 - `beta_citation_web_search_result_location_param: object` - `type: "web_search_result_location"` - `cited_text: string` - `encrypted_index: string` - `title: string` minLength: 1, maxLength: 512 - `url: string` minLength: 1 - `beta_citation_search_result_location_param: object` - `type: "search_result_location"` - `cited_text: string` The full text of the cited block range, concatenated. Always equals the contents of `content[start_block_index:end_block_index]` joined together. The text block is the minimal citable unit; this field is never a substring of a single block. Not counted toward output tokens, and not counted toward input tokens when sent back in subsequent turns. - `end_block_index: number` Exclusive 0-based end index of the cited block range in the source's `content` array. Always greater than `start_block_index`; a single-block citation has `end_block_index = start_block_index + 1`. - `search_result_index: number` 0-based index of the cited search result among all `search_result` content blocks in the request, in the order they appear across messages and tool results. Counted separately from `document_index`; server-side web search results are not included in this count. minimum: 0 - `source: string` - `start_block_index: number` 0-based index of the first cited block in the source's `content` array. minimum: 0 - `title: string` - `beta_image_block_param: object` - `type: "image"` - `source: BetaBase64ImageSource or BetaURLImageSource or BetaFileImageSource` - `beta_base64_image_source: object` - `type: "base64"` - `data: string` format: byte - `media_type: "image/jpeg" or "image/png" or "image/gif" or "image/webp"` - `"image/jpeg"` - `"image/png"` - `"image/gif"` - `"image/webp"` - `beta_url_image_source: object` - `type: "url"` - `url: string` - `beta_file_image_source: object` - `type: "file"` - `file_id: string` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `transformations: optional object` Configures the transformations the server applies to this image before the model observes it. Each key names a condition the server transforms images for; its value selects the transformation applied. Omitted keys keep their default behavior, and an empty object is equivalent to omitting the field. - `oversized_image: optional "downsize" or "error"` What the server does when this image exceeds the model's maximum image size. `"downsize"` (the default) scales the image down to fit, which changes the dimensions the model observes without telling you. `"error"` instead rejects the request with a 400 error naming the image's dimensions and the largest dimensions that fit, so you can scale the image deliberately — your image is never silently scaled down. - `"downsize"` - `"error"` ### Beta Content Block Source Content - `beta_content_block_source_content: BetaTextBlockParam or BetaImageBlockParam` - `beta_text_block_param: object` - `type: "text"` - `text: string` minLength: 1 - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `"5m"` - `"1h"` - `citations: optional array of BetaTextCitationParam` - `beta_citation_char_location_param: object` - `type: "char_location"` - `cited_text: string` - `document_index: number` minimum: 0 - `document_title: string` minLength: 1, maxLength: 500 - `end_char_index: number` - `start_char_index: number` minimum: 0 - `beta_citation_page_location_param: object` - `type: "page_location"` - `cited_text: string` - `document_index: number` minimum: 0 - `document_title: string` minLength: 1, maxLength: 500 - `end_page_number: number` - `start_page_number: number` minimum: 1 - `beta_citation_content_block_location_param: object` - `type: "content_block_location"` - `cited_text: string` The full text of the cited block range, concatenated. Always equals the contents of `content[start_block_index:end_block_index]` joined together. The text block is the minimal citable unit; this field is never a substring of a single block. Not counted toward output tokens, and not counted toward input tokens when sent back in subsequent turns. - `document_index: number` minimum: 0 - `document_title: string` minLength: 1, maxLength: 500 - `end_block_index: number` Exclusive 0-based end index of the cited block range in the source's `content` array. Always greater than `start_block_index`; a single-block citation has `end_block_index = start_block_index + 1`. - `start_block_index: number` 0-based index of the first cited block in the source's `content` array. minimum: 0 - `beta_citation_web_search_result_location_param: object` - `type: "web_search_result_location"` - `cited_text: string` - `encrypted_index: string` - `title: string` minLength: 1, maxLength: 512 - `url: string` minLength: 1 - `beta_citation_search_result_location_param: object` - `type: "search_result_location"` - `cited_text: string` The full text of the cited block range, concatenated. Always equals the contents of `content[start_block_index:end_block_index]` joined together. The text block is the minimal citable unit; this field is never a substring of a single block. Not counted toward output tokens, and not counted toward input tokens when sent back in subsequent turns. - `end_block_index: number` Exclusive 0-based end index of the cited block range in the source's `content` array. Always greater than `start_block_index`; a single-block citation has `end_block_index = start_block_index + 1`. - `search_result_index: number` 0-based index of the cited search result among all `search_result` content blocks in the request, in the order they appear across messages and tool results. Counted separately from `document_index`; server-side web search results are not included in this count. minimum: 0 - `source: string` - `start_block_index: number` 0-based index of the first cited block in the source's `content` array. minimum: 0 - `title: string` - `beta_image_block_param: object` - `type: "image"` - `source: BetaBase64ImageSource or BetaURLImageSource or BetaFileImageSource` - `beta_base64_image_source: object` - `type: "base64"` - `data: string` format: byte - `media_type: "image/jpeg" or "image/png" or "image/gif" or "image/webp"` - `"image/jpeg"` - `"image/png"` - `"image/gif"` - `"image/webp"` - `beta_url_image_source: object` - `type: "url"` - `url: string` - `beta_file_image_source: object` - `type: "file"` - `file_id: string` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `transformations: optional object` Configures the transformations the server applies to this image before the model observes it. Each key names a condition the server transforms images for; its value selects the transformation applied. Omitted keys keep their default behavior, and an empty object is equivalent to omitting the field. - `oversized_image: optional "downsize" or "error"` What the server does when this image exceeds the model's maximum image size. `"downsize"` (the default) scales the image down to fit, which changes the dimensions the model observes without telling you. `"error"` instead rejects the request with a 400 error naming the image's dimensions and the largest dimensions that fit, so you can scale the image deliberately — your image is never silently scaled down. - `"downsize"` - `"error"` ### Beta Context Management Config - `beta_context_management_config: object` - `edits: optional array of BetaClearToolUses20250919Edit or BetaClearThinking20251015Edit or BetaCompact20260112Edit` List of context management edits to apply - `beta_clear_tool_uses_20250919_edit: object` - `type: "clear_tool_uses_20250919"` - `clear_at_least: optional object` Minimum number of tokens that must be cleared when triggered. Context will only be modified if at least this many tokens can be removed. - `type: "input_tokens"` - `value: number` minimum: 0 - `clear_tool_inputs: optional boolean or array of string` Whether to clear all tool inputs (bool) or specific tool inputs to clear (list) - `union_member_0: boolean` - `union_member_1: array of string` - `exclude_tools: optional array of string` Tool names whose uses are preserved from clearing - `keep: optional object` Number of tool uses to retain in the conversation - `type: "tool_uses"` - `value: number` minimum: 0 - `trigger: optional BetaInputTokensTrigger or BetaToolUsesTrigger` Condition that triggers the context management strategy - `beta_input_tokens_trigger: object` - `type: "input_tokens"` - `value: number` minimum: 1 - `beta_tool_uses_trigger: object` - `type: "tool_uses"` - `value: number` minimum: 1 - `beta_clear_thinking_20251015_edit: object` - `type: "clear_thinking_20251015"` - `keep: optional BetaThinkingTurns or BetaAllThinkingTurns or "all"` Number of most recent assistant turns to keep thinking blocks for. Older turns will have their thinking blocks removed. - `beta_thinking_turns: object` - `type: "thinking_turns"` - `value: number` minimum: 1 - `beta_all_thinking_turns: object` - `type: "all"` - `union_member_2: "all"` - `beta_compact_20260112_edit: object` Automatically compact older context when reaching the configured trigger threshold. - `type: "compact_20260112"` - `instructions: optional string` Additional instructions for summarization. - `pause_after_compaction: optional boolean` Whether to pause after compaction and return the compaction block to the user. - `trigger: optional object` When to trigger compaction. Defaults to 150000 input tokens. - `type: "input_tokens"` - `value: number` minimum: 1 ### Beta Context Management Response - `beta_context_management_response: object` - `applied_edits: array of BetaClearToolUses20250919EditResponse or BetaClearThinking20251015EditResponse` List of context management edits that were applied. - `beta_clear_tool_uses_20250919_edit_response: object` - `type: "clear_tool_uses_20250919"` The type of context management edit applied. - `cleared_input_tokens: number` Number of input tokens cleared by this edit. minimum: 0 - `cleared_tool_uses: number` Number of tool uses that were cleared. minimum: 0 - `beta_clear_thinking_20251015_edit_response: object` - `type: "clear_thinking_20251015"` The type of context management edit applied. - `cleared_input_tokens: number` Number of input tokens cleared by this edit. minimum: 0 - `cleared_thinking_turns: number` Number of thinking turns that were cleared. minimum: 0 ### Beta Count Tokens Context Management Response - `beta_count_tokens_context_management_response: object` - `original_input_tokens: number` The original token count before context management was applied ### Beta Diagnostics - `beta_diagnostics: object` Request-level diagnostics: why the prompt cache could not fully reuse the prefix of the request named by `diagnostics.previous_message_id`. - `cache_miss_reason: BetaCacheMissModelChanged or BetaCacheMissSystemChanged or BetaCacheMissToolsChanged or 3 more` Explains why the prompt cache could not fully reuse the prefix from the request identified by `diagnostics.previous_message_id`. `null` means diagnosis is still pending — the response was serialized before the background comparison completed. - `beta_cache_miss_model_changed: object` - `type: "model_changed"` - `cache_missed_input_tokens: number` Approximate number of input tokens that would have been read from cache had the prefix matched the previous request. - `beta_cache_miss_system_changed: object` - `type: "system_changed"` - `cache_missed_input_tokens: number` Approximate number of input tokens that would have been read from cache had the prefix matched the previous request. - `beta_cache_miss_tools_changed: object` - `type: "tools_changed"` - `cache_missed_input_tokens: number` Approximate number of input tokens that would have been read from cache had the prefix matched the previous request. - `beta_cache_miss_messages_changed: object` - `type: "messages_changed"` - `cache_missed_input_tokens: number` Approximate number of input tokens that would have been read from cache had the prefix matched the previous request. - `beta_cache_miss_previous_message_not_found: object` - `type: "previous_message_not_found"` - `beta_cache_miss_unavailable: object` - `type: "unavailable"` ### Beta Diagnostics Param - `beta_diagnostics_param: object` Request-level diagnostics. Currently carries the previous response id for prompt-cache divergence reporting. - `previous_message_id: optional string` The `id` (`msg_...`) from this client's previous /v1/messages response. The server compares that request's prompt fingerprint against this one and returns `diagnostics.cache_miss_reason` when the prompt-cache prefix could not be reused. Pass `null` on the first turn to opt in without a prior message to compare. maxLength: 256 ### Beta Direct Caller - `beta_direct_caller: object` Tool invocation directly from the model. - `type: "direct"` ### Beta Document Block - `beta_document_block: object` - `type: "document"` - `citations: object` Citation configuration for the document - `enabled: boolean` - `source: BetaBase64PDFSource or BetaPlainTextSource` - `beta_base64_pdf_source: object` - `type: "base64"` - `data: string` format: byte - `media_type: "application/pdf"` - `beta_plain_text_source: object` - `type: "text"` - `data: string` - `media_type: "text/plain"` - `title: string` The title of the document ### Beta Encrypted Code Execution Result Block - `beta_encrypted_code_execution_result_block: object` Code execution result with encrypted stdout for PFC + web_search results. - `type: "encrypted_code_execution_result"` - `content: array of BetaCodeExecutionOutputBlock` - `type: "code_execution_output"` - `file_id: string` - `encrypted_stdout: string` - `return_code: number` - `stderr: string` ### Beta Encrypted Code Execution Result Block Param - `beta_encrypted_code_execution_result_block_param: object` Code execution result with encrypted stdout for PFC + web_search results. - `type: "encrypted_code_execution_result"` - `content: array of BetaCodeExecutionOutputBlockParam` - `type: "code_execution_output"` - `file_id: string` - `encrypted_stdout: string` - `return_code: number` - `stderr: string` ### Beta Fallback Block - `beta_fallback_block: object` Marks the point in `content` where one model's output gives way to the next. One block appears per hop where a preceding model actually ran this turn and declined. A turn where no preceding model ran and declined has no such boundary and carries no block — the signal for whether a fallback model served the response is the presence of a `fallback_message` entry in `usage.iterations`, not this block. The block is treated like a server-tool content block for streaming: it arrives via the standard `content_block_start` / `content_block_stop` pair and carries no deltas. - `type: "fallback"` - `from: object` The model whose output ends at this point — the model that declined at this hop. When the declining hop is the requested model, its `model` echoes the top-level `model` string the caller sent (alias or canonical); when the declining hop is a fallback model, its `model` is that model's canonical id. - `model: "claude-haiku-5-5" or "claude-sonnet-5-5" or "claude-fable-5-1" or 17 more or string` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-haiku-5-5"` Fastest model for high-volume, real-time tasks - `"claude-sonnet-5-5"` Efficient model for coding and agents - `"claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows - `"claude-opus-5-5"` Powerful intelligence for coding, knowledge work, and long-running agents - `"claude-mythos-5-1"` Our most capable model for cybersecurity and biology research, available through trusted access programs - `"claude-sonnet-5"` Efficient model for coding and agents - `"claude-fable-5"` Next generation of intelligence for the hardest knowledge work and coding problems - `"claude-mythos-5"` Most capable model for cybersecurity and biology research - `"claude-opus-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-8"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-7"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-6"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-6"` Best combination of speed and intelligence - `"claude-haiku-4-5"` - `"claude-haiku-4-5-20251001"` - `"claude-opus-4-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-5-20251101"` Powerful intelligence for long-running agents and coding - `"claude-mythos-preview"` **Deprecated**: Will reach end-of-life on June 30, 2026. Please migrate to claude-mythos-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. New class of intelligence, strongest in coding and cybersecurity - `"claude-sonnet-4-5"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `"claude-sonnet-4-5-20250929"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `to: object` The fallback model producing the content that follows this block. Its `model` is always the canonical id. - `model: "claude-haiku-5-5" or "claude-sonnet-5-5" or "claude-fable-5-1" or 17 more or string` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `trigger: object` What caused the `from` model to hand over at this hop. - `type: "refusal"` - `category: "cyber" or "bio" or "frontier_llm" or 2 more` The policy category that triggered the `from` model's refusal at this hop. `null` when the refusal doesn't map to a named category. Same vocabulary as `stop_details.category`. - `"cyber"` The request could enable cyber harm, such as malware or exploit development. Benign cybersecurity work can also trigger this category. - `"bio"` The request could enable biological harm, such as dangerous lab methods. Beneficial life sciences work can also trigger this category. - `"frontier_llm"` The request could assist the development of competing AI models, which is restricted under [Anthropic's commercial terms](https://www.anthropic.com/legal/commercial-terms). Benign machine learning work can also trigger this category. - `"reasoning_extraction"` The request asks the model to reproduce its internal reasoning in the response text. To get reasoning in a structured form instead, use [adaptive thinking](https://platform.claude.com/docs/en/build-with-claude/adaptive-thinking?sdk_languages=cli). - `"general_harms"` The request could be related to an area that was determined as harmful. Benign work might sometimes trigger this category. ### Beta Fallback Block Param - `beta_fallback_block_param: object` A `fallback` block echoed back from a prior response. Accepted in `messages[].content` and not rendered into the prompt; not validated against the request's `fallbacks` chain or top-level `model`. Echo the assistant turn back verbatim, including this block in its original position. The block marks the boundary between content produced before and after a fallback hop, and the server relies on that boundary to validate the turn: when thinking runs flank the boundary, omitting the block merges them into one span the server cannot validate (the request is rejected), and moving it into the middle of a single run is likewise rejected; between non-thinking blocks the block's placement has no validation effect. - `type: "fallback"` - `from: object` Identifies one hop of a fallback transition. - `model: "claude-haiku-5-5" or "claude-sonnet-5-5" or "claude-fable-5-1" or 17 more or string` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-haiku-5-5"` Fastest model for high-volume, real-time tasks - `"claude-sonnet-5-5"` Efficient model for coding and agents - `"claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows - `"claude-opus-5-5"` Powerful intelligence for coding, knowledge work, and long-running agents - `"claude-mythos-5-1"` Our most capable model for cybersecurity and biology research, available through trusted access programs - `"claude-sonnet-5"` Efficient model for coding and agents - `"claude-fable-5"` Next generation of intelligence for the hardest knowledge work and coding problems - `"claude-mythos-5"` Most capable model for cybersecurity and biology research - `"claude-opus-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-8"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-7"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-6"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-6"` Best combination of speed and intelligence - `"claude-haiku-4-5"` - `"claude-haiku-4-5-20251001"` - `"claude-opus-4-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-5-20251101"` Powerful intelligence for long-running agents and coding - `"claude-mythos-preview"` **Deprecated**: Will reach end-of-life on June 30, 2026. Please migrate to claude-mythos-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. New class of intelligence, strongest in coding and cybersecurity - `"claude-sonnet-4-5"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `"claude-sonnet-4-5-20250929"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `to: object` Identifies one hop of a fallback transition. - `model: "claude-haiku-5-5" or "claude-sonnet-5-5" or "claude-fable-5-1" or 17 more or string` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `trigger: optional unknown` The response block's `trigger`, echoed verbatim. Accepted and ignored by the server; any object or `null` is allowed. ### Beta Fallback Credit Not Applied - `beta_fallback_credit_not_applied: object` No reprice was applied; `reason` says why. - `type: "not_applied"` - `reason: "body_mismatch" or "continuation_excluded" or "continuation_only" or 9 more` Why the reprice was not applied. A closed enum; additions to the redemption-check vocabulary arrive as deliberate schema updates. - `"body_mismatch"` - `"continuation_excluded"` - `"continuation_only"` - `"expired"` - `"invalid_target_model"` - `"not_enabled"` - `"reprice_unavailable"` - `"temporarily_unavailable"` - `"variant_fields_present"` - `"wrong_organization"` - `"wrong_platform"` - `"wrong_workspace"` - `remove_to_redeem: optional array of string` Request fields to remove before retrying, so the retry can redeem this token. Present exactly when `reason` is `variant_fields_present` — never null, never an empty array; absent otherwise. Fields are named only from your own request, and only after the sealed variant hash matched. A served best-effort retry has already been billed at normal price; nothing redeems retroactively, but a corrected re-send inside the token's five-minute window can still redeem. ### Beta Fallback Credit Redeemed - `beta_fallback_credit_redeemed: object` The reprice was applied: the retry is billed as if the conversation had been on the retry model all along. - `type: "redeemed"` ### Beta Fallback Credit Token Param - `beta_fallback_credit_token_param: object` Object form of `fallback_credit_token`: the token plus a redemption mode. Requires `anthropic-beta: fallback-credit-2026-07-01`; without that header the field accepts the bare string only. The bare string and the mode-less object are equivalent (both select `strict`), so wrapping an existing token changes nothing by itself. - `token: string` The opaque `fallback_credit_token` from a prior refusal's `stop_details` — the same string the bare-string form carries. minLength: 1, maxLength: 2048 - `mode: optional "strict" or "best_effort"` How a failing token affects the retry. `strict` (the default, and the bare-string behavior): a failing redemption is a 400 and the retry is not served. `best_effort`: the retry is served either way — a token-layer failure no longer rejects the request; the retry proceeds at normal price and the outcome is reported on the response's `usage.fallback_credit`. Two failures stay hard in both modes: a malformed token, and combining `fallback_credit_token` with `fallbacks`. - `"strict"` - `"best_effort"` ### Beta Fallback Credit Usage - `beta_fallback_credit_usage: object` Outcome of the `fallback_credit_token` presented on this request. - `status: BetaFallbackCreditRedeemed or BetaFallbackCreditNotApplied` Whether the fallback-credit reprice was applied to this response's billing. A union discriminated on `type`. `redeemed`: the retry is billed as if the conversation had been on the retry model all along — including when the resulting shift is zero because there was nothing to move. `not_applied`: no reprice was applied; the arm's `reason` says why. - `beta_fallback_credit_redeemed: object` The reprice was applied: the retry is billed as if the conversation had been on the retry model all along. - `type: "redeemed"` - `beta_fallback_credit_not_applied: object` No reprice was applied; `reason` says why. - `type: "not_applied"` - `reason: "body_mismatch" or "continuation_excluded" or "continuation_only" or 9 more` Why the reprice was not applied. A closed enum; additions to the redemption-check vocabulary arrive as deliberate schema updates. - `"body_mismatch"` - `"continuation_excluded"` - `"continuation_only"` - `"expired"` - `"invalid_target_model"` - `"not_enabled"` - `"reprice_unavailable"` - `"temporarily_unavailable"` - `"variant_fields_present"` - `"wrong_organization"` - `"wrong_platform"` - `"wrong_workspace"` - `remove_to_redeem: optional array of string` Request fields to remove before retrying, so the retry can redeem this token. Present exactly when `reason` is `variant_fields_present` — never null, never an empty array; absent otherwise. Fields are named only from your own request, and only after the sealed variant hash matched. A served best-effort retry has already been billed at normal price; nothing redeems retroactively, but a corrected re-send inside the token's five-minute window can still redeem. ### Beta Fallback Info - `beta_fallback_info: object` Identifies one hop of a fallback transition. - `model: "claude-haiku-5-5" or "claude-sonnet-5-5" or "claude-fable-5-1" or 17 more or string` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-haiku-5-5"` Fastest model for high-volume, real-time tasks - `"claude-sonnet-5-5"` Efficient model for coding and agents - `"claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows - `"claude-opus-5-5"` Powerful intelligence for coding, knowledge work, and long-running agents - `"claude-mythos-5-1"` Our most capable model for cybersecurity and biology research, available through trusted access programs - `"claude-sonnet-5"` Efficient model for coding and agents - `"claude-fable-5"` Next generation of intelligence for the hardest knowledge work and coding problems - `"claude-mythos-5"` Most capable model for cybersecurity and biology research - `"claude-opus-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-8"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-7"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-6"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-6"` Best combination of speed and intelligence - `"claude-haiku-4-5"` - `"claude-haiku-4-5-20251001"` - `"claude-opus-4-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-5-20251101"` Powerful intelligence for long-running agents and coding - `"claude-mythos-preview"` **Deprecated**: Will reach end-of-life on June 30, 2026. Please migrate to claude-mythos-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. New class of intelligence, strongest in coding and cybersecurity - `"claude-sonnet-4-5"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `"claude-sonnet-4-5-20250929"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding ### Beta Fallback Info Param - `beta_fallback_info_param: object` Identifies one hop of a fallback transition. - `model: "claude-haiku-5-5" or "claude-sonnet-5-5" or "claude-fable-5-1" or 17 more or string` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-haiku-5-5"` Fastest model for high-volume, real-time tasks - `"claude-sonnet-5-5"` Efficient model for coding and agents - `"claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows - `"claude-opus-5-5"` Powerful intelligence for coding, knowledge work, and long-running agents - `"claude-mythos-5-1"` Our most capable model for cybersecurity and biology research, available through trusted access programs - `"claude-sonnet-5"` Efficient model for coding and agents - `"claude-fable-5"` Next generation of intelligence for the hardest knowledge work and coding problems - `"claude-mythos-5"` Most capable model for cybersecurity and biology research - `"claude-opus-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-8"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-7"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-6"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-6"` Best combination of speed and intelligence - `"claude-haiku-4-5"` - `"claude-haiku-4-5-20251001"` - `"claude-opus-4-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-5-20251101"` Powerful intelligence for long-running agents and coding - `"claude-mythos-preview"` **Deprecated**: Will reach end-of-life on June 30, 2026. Please migrate to claude-mythos-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. New class of intelligence, strongest in coding and cybersecurity - `"claude-sonnet-4-5"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `"claude-sonnet-4-5-20250929"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding ### Beta Fallback Message Iteration Usage - `beta_fallback_message_iteration_usage: object` Token usage for the fallback-model attempt of a server-side fallback request. The terminal entry of a fallback-served turn: when a fallback hop's output is the returned message, the entry for the iteration that completed it carries this type in place of `message`. A declined hop and the serving hop's earlier tool-loop iterations produce `message` entries. Whether a fallback model served the response is signalled by the presence of this entry in `usage.iterations`. - `type: "fallback_message"` Usage for the fallback-model attempt that served the response - `cache_creation: object` Breakdown of cached tokens by TTL - `ephemeral_1h_input_tokens: number` The number of input tokens used to create the 1 hour cache entry. minimum: 0 - `ephemeral_5m_input_tokens: number` The number of input tokens used to create the 5 minute cache entry. minimum: 0 - `cache_creation_input_tokens: number` The number of input tokens used to create the cache entry. minimum: 0 - `cache_read_input_tokens: number` The number of input tokens read from the cache. minimum: 0 - `input_tokens: number` The number of input tokens which were used. minimum: 0 - `model: "claude-haiku-5-5" or "claude-sonnet-5-5" or "claude-fable-5-1" or 17 more or string` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-haiku-5-5"` Fastest model for high-volume, real-time tasks - `"claude-sonnet-5-5"` Efficient model for coding and agents - `"claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows - `"claude-opus-5-5"` Powerful intelligence for coding, knowledge work, and long-running agents - `"claude-mythos-5-1"` Our most capable model for cybersecurity and biology research, available through trusted access programs - `"claude-sonnet-5"` Efficient model for coding and agents - `"claude-fable-5"` Next generation of intelligence for the hardest knowledge work and coding problems - `"claude-mythos-5"` Most capable model for cybersecurity and biology research - `"claude-opus-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-8"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-7"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-6"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-6"` Best combination of speed and intelligence - `"claude-haiku-4-5"` - `"claude-haiku-4-5-20251001"` - `"claude-opus-4-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-5-20251101"` Powerful intelligence for long-running agents and coding - `"claude-mythos-preview"` **Deprecated**: Will reach end-of-life on June 30, 2026. Please migrate to claude-mythos-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. New class of intelligence, strongest in coding and cybersecurity - `"claude-sonnet-4-5"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `"claude-sonnet-4-5-20250929"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `output_tokens: number` The number of output tokens which were used. minimum: 0 ### Beta Fallback Param - `beta_fallback_param: object` One entry in the `fallbacks` chain on a `/v1/messages` request. `model` is required. The override fields (`max_tokens`, `thinking`, `output_config`, and `speed`) set the corresponding parameter for this attempt only and are validated as if the request were made to `model`. Any other key is rejected at parse time. - `model: "claude-haiku-5-5" or "claude-sonnet-5-5" or "claude-fable-5-1" or 17 more or string` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-haiku-5-5"` Fastest model for high-volume, real-time tasks - `"claude-sonnet-5-5"` Efficient model for coding and agents - `"claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows - `"claude-opus-5-5"` Powerful intelligence for coding, knowledge work, and long-running agents - `"claude-mythos-5-1"` Our most capable model for cybersecurity and biology research, available through trusted access programs - `"claude-sonnet-5"` Efficient model for coding and agents - `"claude-fable-5"` Next generation of intelligence for the hardest knowledge work and coding problems - `"claude-mythos-5"` Most capable model for cybersecurity and biology research - `"claude-opus-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-8"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-7"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-6"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-6"` Best combination of speed and intelligence - `"claude-haiku-4-5"` - `"claude-haiku-4-5-20251001"` - `"claude-opus-4-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-5-20251101"` Powerful intelligence for long-running agents and coding - `"claude-mythos-preview"` **Deprecated**: Will reach end-of-life on June 30, 2026. Please migrate to claude-mythos-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. New class of intelligence, strongest in coding and cybersecurity - `"claude-sonnet-4-5"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `"claude-sonnet-4-5-20250929"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `max_tokens: optional number` - `output_config: optional object` - `effort: optional "low" or "medium" or "high" or 2 more` How much effort the model should put into its response. Higher effort levels may result in more thorough analysis but take longer. Valid values are `low`, `medium`, `high`, `xhigh`, or `max`. - `"low"` - `"medium"` - `"high"` - `"xhigh"` - `"max"` - `format: optional object` A schema to specify Claude's output format in responses. See [structured outputs](https://platform.claude.com/docs/en/build-with-claude/structured-outputs?sdk_languages=cli) - `type: "json_schema"` - `schema: map[unknown]` The JSON schema of the format - `task_budget: optional object` Configuration for token budget tracking across contexts. - `type: "tokens"` The budget type. Currently only 'tokens' is supported. - `total: number` Total token budget across all contexts in the session. minimum: 1024 - `remaining: optional number` Remaining tokens in the budget. Use this to track usage across contexts when implementing compaction client-side. Defaults to total if not provided. minimum: 0 - `speed: optional "standard" or "fast"` Inference speed mode. `fast` provides significantly faster output token generation at premium pricing. Not all models support `fast`; invalid combinations are rejected at create time. - `"standard"` - `"fast"` - `thinking: optional BetaThinkingConfigEnabled or BetaThinkingConfigDisabled or BetaThinkingConfigBetweenTools or BetaThinkingConfigAdaptive` - `beta_thinking_config_enabled: object` - `type: "enabled"` - `budget_tokens: number` Determines how many tokens Claude can use for its internal reasoning process. Larger budgets can enable more thorough analysis for complex problems, improving response quality. Must be ≥1024 and less than `max_tokens`. See [extended thinking](https://platform.claude.com/docs/en/build-with-claude/extended-thinking?sdk_languages=cli) for details. minimum: 1024 - `block_binding: optional object` Controls for block binding: what happens when a thinking block this request sends back fails the conversation check. `null`, absent or an empty object means every default. - `prefix_mismatch_behavior: optional "error" or "drop_block"` "error" (default) | "drop_block". What happens when a thinking block in `messages` fails the conversation check (it was created in a different conversation, or the messages before it have changed since). "error" fails the request with a 400 error. "drop_block" removes the failing blocks and the request proceeds; each removal is reported in `input_transformations`. - `"error"` - `"drop_block"` - `display: optional "summarized" or "omitted" or "updates"` Controls how thinking content appears in the response. When set to `summarized`, thinking is returned normally. When set to `omitted`, thinking content is redacted but a signature is returned for multi-turn continuity. The default depends on the model; see [Controlling thinking display](https://platform.claude.com/docs/en/build-with-claude/thinking?sdk_languages=cli#controlling-thinking-display). - `"summarized"` - `"omitted"` - `"updates"` - `beta_thinking_config_disabled: object` - `type: "disabled"` - `beta_thinking_config_between_tools: object` - `type: "between_tools"` - `beta_thinking_config_adaptive: object` - `type: "adaptive"` - `block_binding: optional object` Controls for block binding: what happens when a thinking block this request sends back fails the conversation check. `null`, absent or an empty object means every default. - `prefix_mismatch_behavior: optional "error" or "drop_block"` "error" (default) | "drop_block". What happens when a thinking block in `messages` fails the conversation check (it was created in a different conversation, or the messages before it have changed since). "error" fails the request with a 400 error. "drop_block" removes the failing blocks and the request proceeds; each removal is reported in `input_transformations`. - `display: optional "summarized" or "omitted" or "updates"` Controls how thinking content appears in the response. When set to `summarized`, thinking is returned normally. When set to `omitted`, thinking content is redacted but a signature is returned for multi-turn continuity. The default depends on the model; see [Controlling thinking display](https://platform.claude.com/docs/en/build-with-claude/thinking?sdk_languages=cli#controlling-thinking-display). - `"summarized"` - `"omitted"` - `"updates"` ### Beta Fallback Refusal Trigger - `beta_fallback_refusal_trigger: object` The `from` model declined for policy reasons. - `type: "refusal"` - `category: "cyber" or "bio" or "frontier_llm" or 2 more` The policy category that triggered the `from` model's refusal at this hop. `null` when the refusal doesn't map to a named category. Same vocabulary as `stop_details.category`. - `"cyber"` The request could enable cyber harm, such as malware or exploit development. Benign cybersecurity work can also trigger this category. - `"bio"` The request could enable biological harm, such as dangerous lab methods. Beneficial life sciences work can also trigger this category. - `"frontier_llm"` The request could assist the development of competing AI models, which is restricted under [Anthropic's commercial terms](https://www.anthropic.com/legal/commercial-terms). Benign machine learning work can also trigger this category. - `"reasoning_extraction"` The request asks the model to reproduce its internal reasoning in the response text. To get reasoning in a structured form instead, use [adaptive thinking](https://platform.claude.com/docs/en/build-with-claude/adaptive-thinking?sdk_languages=cli). - `"general_harms"` The request could be related to an area that was determined as harmful. Benign work might sometimes trigger this category. ### Beta Fallbacks Param - `beta_fallbacks_param: array of BetaFallbackParam or "default"` Opt-in server-side retry on one or more substitute models when the requested model declines for policy reasons. Tried in order: if the first entry also declines, the second is tried, and so on. Some models don't support fallbacks; on those models, a list of fallback models returns a 400 error. See [Server-side fallback](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback?sdk_languages=cli#server-side-fallback). The string "default" requests the requested model's server-defined default fallback configuration. On a model that doesn't support fallbacks, the request runs on the requested model alone, so a declined request stays declined. - `union_member_0: array of BetaFallbackParam` - `model: "claude-haiku-5-5" or "claude-sonnet-5-5" or "claude-fable-5-1" or 17 more or string` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-haiku-5-5"` Fastest model for high-volume, real-time tasks - `"claude-sonnet-5-5"` Efficient model for coding and agents - `"claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows - `"claude-opus-5-5"` Powerful intelligence for coding, knowledge work, and long-running agents - `"claude-mythos-5-1"` Our most capable model for cybersecurity and biology research, available through trusted access programs - `"claude-sonnet-5"` Efficient model for coding and agents - `"claude-fable-5"` Next generation of intelligence for the hardest knowledge work and coding problems - `"claude-mythos-5"` Most capable model for cybersecurity and biology research - `"claude-opus-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-8"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-7"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-6"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-6"` Best combination of speed and intelligence - `"claude-haiku-4-5"` - `"claude-haiku-4-5-20251001"` - `"claude-opus-4-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-5-20251101"` Powerful intelligence for long-running agents and coding - `"claude-mythos-preview"` **Deprecated**: Will reach end-of-life on June 30, 2026. Please migrate to claude-mythos-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. New class of intelligence, strongest in coding and cybersecurity - `"claude-sonnet-4-5"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `"claude-sonnet-4-5-20250929"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `max_tokens: optional number` - `output_config: optional object` - `effort: optional "low" or "medium" or "high" or 2 more` How much effort the model should put into its response. Higher effort levels may result in more thorough analysis but take longer. Valid values are `low`, `medium`, `high`, `xhigh`, or `max`. - `"low"` - `"medium"` - `"high"` - `"xhigh"` - `"max"` - `format: optional object` A schema to specify Claude's output format in responses. See [structured outputs](https://platform.claude.com/docs/en/build-with-claude/structured-outputs?sdk_languages=cli) - `type: "json_schema"` - `schema: map[unknown]` The JSON schema of the format - `task_budget: optional object` Configuration for token budget tracking across contexts. - `type: "tokens"` The budget type. Currently only 'tokens' is supported. - `total: number` Total token budget across all contexts in the session. minimum: 1024 - `remaining: optional number` Remaining tokens in the budget. Use this to track usage across contexts when implementing compaction client-side. Defaults to total if not provided. minimum: 0 - `speed: optional "standard" or "fast"` Inference speed mode. `fast` provides significantly faster output token generation at premium pricing. Not all models support `fast`; invalid combinations are rejected at create time. - `"standard"` - `"fast"` - `thinking: optional BetaThinkingConfigEnabled or BetaThinkingConfigDisabled or BetaThinkingConfigBetweenTools or BetaThinkingConfigAdaptive` - `beta_thinking_config_enabled: object` - `type: "enabled"` - `budget_tokens: number` Determines how many tokens Claude can use for its internal reasoning process. Larger budgets can enable more thorough analysis for complex problems, improving response quality. Must be ≥1024 and less than `max_tokens`. See [extended thinking](https://platform.claude.com/docs/en/build-with-claude/extended-thinking?sdk_languages=cli) for details. minimum: 1024 - `block_binding: optional object` Controls for block binding: what happens when a thinking block this request sends back fails the conversation check. `null`, absent or an empty object means every default. - `prefix_mismatch_behavior: optional "error" or "drop_block"` "error" (default) | "drop_block". What happens when a thinking block in `messages` fails the conversation check (it was created in a different conversation, or the messages before it have changed since). "error" fails the request with a 400 error. "drop_block" removes the failing blocks and the request proceeds; each removal is reported in `input_transformations`. - `"error"` - `"drop_block"` - `display: optional "summarized" or "omitted" or "updates"` Controls how thinking content appears in the response. When set to `summarized`, thinking is returned normally. When set to `omitted`, thinking content is redacted but a signature is returned for multi-turn continuity. The default depends on the model; see [Controlling thinking display](https://platform.claude.com/docs/en/build-with-claude/thinking?sdk_languages=cli#controlling-thinking-display). - `"summarized"` - `"omitted"` - `"updates"` - `beta_thinking_config_disabled: object` - `type: "disabled"` - `beta_thinking_config_between_tools: object` - `type: "between_tools"` - `beta_thinking_config_adaptive: object` - `type: "adaptive"` - `block_binding: optional object` Controls for block binding: what happens when a thinking block this request sends back fails the conversation check. `null`, absent or an empty object means every default. - `prefix_mismatch_behavior: optional "error" or "drop_block"` "error" (default) | "drop_block". What happens when a thinking block in `messages` fails the conversation check (it was created in a different conversation, or the messages before it have changed since). "error" fails the request with a 400 error. "drop_block" removes the failing blocks and the request proceeds; each removal is reported in `input_transformations`. - `display: optional "summarized" or "omitted" or "updates"` Controls how thinking content appears in the response. When set to `summarized`, thinking is returned normally. When set to `omitted`, thinking content is redacted but a signature is returned for multi-turn continuity. The default depends on the model; see [Controlling thinking display](https://platform.claude.com/docs/en/build-with-claude/thinking?sdk_languages=cli#controlling-thinking-display). - `"summarized"` - `"omitted"` - `"updates"` - `Default: "default"` ### Beta File Document Source - `beta_file_document_source: object` - `type: "file"` - `file_id: string` ### Beta File Image Source - `beta_file_image_source: object` - `type: "file"` - `file_id: string` ### Beta Image Block Param - `beta_image_block_param: object` - `type: "image"` - `source: BetaBase64ImageSource or BetaURLImageSource or BetaFileImageSource` - `beta_base64_image_source: object` - `type: "base64"` - `data: string` format: byte - `media_type: "image/jpeg" or "image/png" or "image/gif" or "image/webp"` - `"image/jpeg"` - `"image/png"` - `"image/gif"` - `"image/webp"` - `beta_url_image_source: object` - `type: "url"` - `url: string` - `beta_file_image_source: object` - `type: "file"` - `file_id: string` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `"5m"` - `"1h"` - `transformations: optional object` Configures the transformations the server applies to this image before the model observes it. Each key names a condition the server transforms images for; its value selects the transformation applied. Omitted keys keep their default behavior, and an empty object is equivalent to omitting the field. - `oversized_image: optional "downsize" or "error"` What the server does when this image exceeds the model's maximum image size. `"downsize"` (the default) scales the image down to fit, which changes the dimensions the model observes without telling you. `"error"` instead rejects the request with a 400 error naming the image's dimensions and the largest dimensions that fit, so you can scale the image deliberately — your image is never silently scaled down. - `"downsize"` - `"error"` ### Beta Image Transformations Param - `beta_image_transformations_param: object` Configures the transformations the server applies to this image before the model observes it. Each key names a condition the server transforms images for; its value selects the transformation applied. Omitted keys keep their default behavior, and an empty object is equivalent to omitting the field. - `oversized_image: optional "downsize" or "error"` What the server does when this image exceeds the model's maximum image size. `"downsize"` (the default) scales the image down to fit, which changes the dimensions the model observes without telling you. `"error"` instead rejects the request with a 400 error naming the image's dimensions and the largest dimensions that fit, so you can scale the image deliberately — your image is never silently scaled down. - `"downsize"` - `"error"` ### Beta Input JSON Delta - `beta_input_json_delta: object` - `type: "input_json_delta"` - `partial_json: string` ### Beta Input Tokens Clear At Least - `beta_input_tokens_clear_at_least: object` - `type: "input_tokens"` - `value: number` minimum: 0 ### Beta Input Tokens Trigger - `beta_input_tokens_trigger: object` - `type: "input_tokens"` - `value: number` minimum: 1 ### Beta Input Transformation - `beta_input_transformation: BetaThinkingDroppedInputTransformation or BetaThinkingMismatchAllowedInputTransformation` One entry of `input_transformations`: either a change the API made to the request's input before showing it to the model, or a block that failed a binding check and was still shown to the model unchanged. The `type` field says which. - `beta_thinking_dropped_input_transformation: object` - `type: "thinking_dropped"` Always `thinking_dropped` for this entry type. - `path: string` Where the removed block was in your request, as `messages.{i}.content.{j}`: `i` indexes the `messages` array you sent and `j` that message's `content` array — the same form error messages use. - `reason: "model_binding_mismatch" or "prefix_binding_mismatch" or "organization_binding_mismatch" or "end_user_binding_mismatch"` Which binding check removed the block: `model_binding_mismatch` — it was created by a model whose reasoning the requested model may not read; `prefix_binding_mismatch` — the conversation before it differs from the conversation it was created in (the rest of that turn's consecutive thinking blocks are removed with it, each with this reason); `organization_binding_mismatch` — it was created under a different organization (an Anthropic organization, AWS account or Google Cloud project) and this organization is not one of its additional organizations; `end_user_binding_mismatch` — it was created for a different end user, or was removed by the consumer-organization binding. A block that would fail several checks reports one reason, in this order of precedence: `organization_binding_mismatch`, `end_user_binding_mismatch`, `model_binding_mismatch`, `prefix_binding_mismatch`. - `"model_binding_mismatch"` - `"prefix_binding_mismatch"` - `"organization_binding_mismatch"` - `"end_user_binding_mismatch"` - `beta_thinking_mismatch_allowed_input_transformation: object` - `type: "thinking_mismatch_allowed"` Always `thinking_mismatch_allowed` for this entry type. - `path: string` Where the block is in your request, as `messages.{i}.content.{j}`: `i` indexes the `messages` array you sent and `j` that message's `content` array — the same form error messages use. - `reason: "model_binding_mismatch" or "prefix_binding_mismatch" or "organization_binding_mismatch" or "end_user_binding_mismatch"` Which binding check the block failed; the block was shown to the model all the same. Always `prefix_binding_mismatch` today — the conversation before the block differs from the conversation it was created in, or the block carries no record of one on a model that requires it. Were the check enforced for this request, the block would have been removed or the request rejected (`thinking.block_binding.prefix_mismatch_behavior`). A removal also takes the rest of that turn's consecutive thinking blocks, whereas here each block is checked on its own, so `thinking_mismatch_allowed` entries are a lower bound on what enforcement would remove. - `"model_binding_mismatch"` - `"prefix_binding_mismatch"` - `"organization_binding_mismatch"` - `"end_user_binding_mismatch"` ### Beta Iterations Usage - `beta_iterations_usage: array of BetaMessageIterationUsage or BetaCompactionIterationUsage or BetaAdvisorMessageIterationUsage or BetaFallbackMessageIterationUsage` Per-iteration token usage breakdown. Each entry represents one sampling iteration, with its own input/output token counts and cache statistics, discriminated by `type`. For `message` entries (model sampling iterations, such as the turns of a server-side tool use loop), this allows you to: - Calculate the context window size from the last `message` entry - Understand token accumulation across server-side tool use loops A `compaction` entry reports the token usage of the compaction operation itself — the server-side request that summarizes the context being closed — NOT the size of the context that was compacted away, and its token counts can be much smaller than that closed context (for example, a compaction that closes a ~200k-token context can report only a few thousand tokens). Do not derive the context window size from a `compaction` entry, even when it is the last entry. A `compaction` entry's tokens are not included in the top-level `usage` fields. When an input-token trigger is in effect (the default — 150,000 tokens unless configured otherwise), each `compaction` entry closes a context that had reached at least that threshold, though the context can exceed it by the final iteration's output and tool results. - `beta_message_iteration_usage: object` Token usage for a sampling iteration. - `type: "message"` Usage for a sampling iteration - `cache_creation: object` Breakdown of cached tokens by TTL - `ephemeral_1h_input_tokens: number` The number of input tokens used to create the 1 hour cache entry. minimum: 0 - `ephemeral_5m_input_tokens: number` The number of input tokens used to create the 5 minute cache entry. minimum: 0 - `cache_creation_input_tokens: number` The number of input tokens used to create the cache entry. minimum: 0 - `cache_read_input_tokens: number` The number of input tokens read from the cache. minimum: 0 - `input_tokens: number` The number of input tokens which were used. minimum: 0 - `model: "claude-haiku-5-5" or "claude-sonnet-5-5" or "claude-fable-5-1" or 17 more or string` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-haiku-5-5"` Fastest model for high-volume, real-time tasks - `"claude-sonnet-5-5"` Efficient model for coding and agents - `"claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows - `"claude-opus-5-5"` Powerful intelligence for coding, knowledge work, and long-running agents - `"claude-mythos-5-1"` Our most capable model for cybersecurity and biology research, available through trusted access programs - `"claude-sonnet-5"` Efficient model for coding and agents - `"claude-fable-5"` Next generation of intelligence for the hardest knowledge work and coding problems - `"claude-mythos-5"` Most capable model for cybersecurity and biology research - `"claude-opus-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-8"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-7"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-6"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-6"` Best combination of speed and intelligence - `"claude-haiku-4-5"` - `"claude-haiku-4-5-20251001"` - `"claude-opus-4-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-5-20251101"` Powerful intelligence for long-running agents and coding - `"claude-mythos-preview"` **Deprecated**: Will reach end-of-life on June 30, 2026. Please migrate to claude-mythos-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. New class of intelligence, strongest in coding and cybersecurity - `"claude-sonnet-4-5"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `"claude-sonnet-4-5-20250929"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `output_tokens: number` The number of output tokens which were used. minimum: 0 - `beta_compaction_iteration_usage: object` Token usage for a compaction iteration. - `type: "compaction"` Usage for a compaction iteration - `cache_creation: object` Breakdown of cached tokens by TTL - `ephemeral_1h_input_tokens: number` The number of input tokens used to create the 1 hour cache entry. minimum: 0 - `ephemeral_5m_input_tokens: number` The number of input tokens used to create the 5 minute cache entry. minimum: 0 - `cache_creation_input_tokens: number` The number of input tokens used to create the cache entry. minimum: 0 - `cache_read_input_tokens: number` The number of input tokens read from the cache. minimum: 0 - `input_tokens: number` The number of input tokens which were used. minimum: 0 - `output_tokens: number` The number of output tokens which were used. minimum: 0 - `beta_advisor_message_iteration_usage: object` Token usage for an advisor sub-inference iteration. - `type: "advisor_message"` Usage for an advisor sub-inference iteration - `cache_creation: object` Breakdown of cached tokens by TTL - `ephemeral_1h_input_tokens: number` The number of input tokens used to create the 1 hour cache entry. minimum: 0 - `ephemeral_5m_input_tokens: number` The number of input tokens used to create the 5 minute cache entry. minimum: 0 - `cache_creation_input_tokens: number` The number of input tokens used to create the cache entry. minimum: 0 - `cache_read_input_tokens: number` The number of input tokens read from the cache. minimum: 0 - `input_tokens: number` The number of input tokens which were used. minimum: 0 - `model: "claude-haiku-5-5" or "claude-sonnet-5-5" or "claude-fable-5-1" or 17 more or string` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-haiku-5-5"` Fastest model for high-volume, real-time tasks - `"claude-sonnet-5-5"` Efficient model for coding and agents - `"claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows - `"claude-opus-5-5"` Powerful intelligence for coding, knowledge work, and long-running agents - `"claude-mythos-5-1"` Our most capable model for cybersecurity and biology research, available through trusted access programs - `"claude-sonnet-5"` Efficient model for coding and agents - `"claude-fable-5"` Next generation of intelligence for the hardest knowledge work and coding problems - `"claude-mythos-5"` Most capable model for cybersecurity and biology research - `"claude-opus-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-8"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-7"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-6"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-6"` Best combination of speed and intelligence - `"claude-haiku-4-5"` - `"claude-haiku-4-5-20251001"` - `"claude-opus-4-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-5-20251101"` Powerful intelligence for long-running agents and coding - `"claude-mythos-preview"` **Deprecated**: Will reach end-of-life on June 30, 2026. Please migrate to claude-mythos-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. New class of intelligence, strongest in coding and cybersecurity - `"claude-sonnet-4-5"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `"claude-sonnet-4-5-20250929"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `output_tokens: number` The number of output tokens which were used. minimum: 0 - `beta_fallback_message_iteration_usage: object` Token usage for the fallback-model attempt of a server-side fallback request. The terminal entry of a fallback-served turn: when a fallback hop's output is the returned message, the entry for the iteration that completed it carries this type in place of `message`. A declined hop and the serving hop's earlier tool-loop iterations produce `message` entries. Whether a fallback model served the response is signalled by the presence of this entry in `usage.iterations`. - `type: "fallback_message"` Usage for the fallback-model attempt that served the response - `cache_creation: object` Breakdown of cached tokens by TTL - `ephemeral_1h_input_tokens: number` The number of input tokens used to create the 1 hour cache entry. minimum: 0 - `ephemeral_5m_input_tokens: number` The number of input tokens used to create the 5 minute cache entry. minimum: 0 - `cache_creation_input_tokens: number` The number of input tokens used to create the cache entry. minimum: 0 - `cache_read_input_tokens: number` The number of input tokens read from the cache. minimum: 0 - `input_tokens: number` The number of input tokens which were used. minimum: 0 - `model: "claude-haiku-5-5" or "claude-sonnet-5-5" or "claude-fable-5-1" or 17 more or string` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-haiku-5-5"` Fastest model for high-volume, real-time tasks - `"claude-sonnet-5-5"` Efficient model for coding and agents - `"claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows - `"claude-opus-5-5"` Powerful intelligence for coding, knowledge work, and long-running agents - `"claude-mythos-5-1"` Our most capable model for cybersecurity and biology research, available through trusted access programs - `"claude-sonnet-5"` Efficient model for coding and agents - `"claude-fable-5"` Next generation of intelligence for the hardest knowledge work and coding problems - `"claude-mythos-5"` Most capable model for cybersecurity and biology research - `"claude-opus-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-8"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-7"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-6"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-6"` Best combination of speed and intelligence - `"claude-haiku-4-5"` - `"claude-haiku-4-5-20251001"` - `"claude-opus-4-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-5-20251101"` Powerful intelligence for long-running agents and coding - `"claude-mythos-preview"` **Deprecated**: Will reach end-of-life on June 30, 2026. Please migrate to claude-mythos-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. New class of intelligence, strongest in coding and cybersecurity - `"claude-sonnet-4-5"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `"claude-sonnet-4-5-20250929"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `output_tokens: number` The number of output tokens which were used. minimum: 0 ### Beta JSON Output Format - `beta_json_output_format: object` - `type: "json_schema"` - `schema: map[unknown]` The JSON schema of the format ### Beta MCP Tool - `beta_mcp_tool: object` A tool as an MCP server lists it: its name on that server, its description, and its input schema. - `input_schema: map[unknown]` - `name: string` - `description: optional string` ### Beta MCP Tool Config - `beta_mcp_tool_config: object` Configuration for a specific tool in an MCP toolset. - `defer_loading: optional boolean` - `enabled: optional boolean` ### Beta MCP Tool Default Config - `beta_mcp_tool_default_config: object` Default configuration for tools in an MCP toolset. - `defer_loading: optional boolean` - `enabled: optional boolean` ### Beta MCP Tool Listing Block - `beta_mcp_tool_listing_block: object` The tool listing the server fetched from an MCP server while producing this response. Send the assistant message back unchanged, this block included, so later requests use this listing instead of asking the MCP server again. - `type: "mcp_tool_listing"` - `mcp_server_name: string` - `tools: array of BetaMCPTool` - `input_schema: map[unknown]` - `name: string` - `description: optional string` ### Beta MCP Tool Listing Block Param - `beta_mcp_tool_listing_block_param: object` The tool listing an MCP server returned while an earlier response was produced, as that response carried it. Send the assistant message back unchanged, this block included, and the server uses this listing for the matching `mcp_toolset` instead of asking the MCP server again. - `type: "mcp_tool_listing"` - `mcp_server_name: string` The name of the MCP server this listing came from, as `mcp_servers` declares it. minLength: 1, maxLength: 255 - `tools: array of BetaMCPToolParam` The server's tools, exactly as the response listed them. - `input_schema: map[unknown]` The tool's input schema as the MCP server lists it, verbatim. - `name: string` The tool's name as the MCP server lists it (not prefixed with the server name). minLength: 1 - `description: optional string` The tool's description as the MCP server lists it. ### Beta MCP Tool Param - `beta_mcp_tool_param: object` A tool as an MCP server lists it: its name on that server, its description, and its input schema. - `input_schema: map[unknown]` The tool's input schema as the MCP server lists it, verbatim. - `name: string` The tool's name as the MCP server lists it (not prefixed with the server name). minLength: 1 - `description: optional string` The tool's description as the MCP server lists it. ### Beta MCP Tool Result Block - `beta_mcp_tool_result_block: object` - `type: "mcp_tool_result"` - `content: string or array of BetaTextBlock` - `union_member_0: string` - `beta_mcp_tool_result_block_content: array of BetaTextBlock` - `type: "text"` - `citations: array of BetaTextCitation` Citations supporting the text block. The type of citation returned will depend on the type of document being cited. Citing a PDF results in `page_location`, plain text results in `char_location`, and content document results in `content_block_location`. - `beta_citation_char_location: object` - `type: "char_location"` - `cited_text: string` - `document_index: number` minimum: 0 - `document_title: string` - `end_char_index: number` - `file_id: string` - `start_char_index: number` minimum: 0 - `beta_citation_page_location: object` - `type: "page_location"` - `cited_text: string` - `document_index: number` minimum: 0 - `document_title: string` - `end_page_number: number` - `file_id: string` - `start_page_number: number` minimum: 1 - `beta_citation_content_block_location: object` - `type: "content_block_location"` - `cited_text: string` The full text of the cited block range, concatenated. Always equals the contents of `content[start_block_index:end_block_index]` joined together. The text block is the minimal citable unit; this field is never a substring of a single block. Not counted toward output tokens, and not counted toward input tokens when sent back in subsequent turns. - `document_index: number` minimum: 0 - `document_title: string` - `end_block_index: number` Exclusive 0-based end index of the cited block range in the source's `content` array. Always greater than `start_block_index`; a single-block citation has `end_block_index = start_block_index + 1`. - `file_id: string` - `start_block_index: number` 0-based index of the first cited block in the source's `content` array. minimum: 0 - `beta_citations_web_search_result_location: object` - `type: "web_search_result_location"` - `cited_text: string` - `encrypted_index: string` - `title: string` maxLength: 512 - `url: string` - `beta_citation_search_result_location: object` - `type: "search_result_location"` - `cited_text: string` The full text of the cited block range, concatenated. Always equals the contents of `content[start_block_index:end_block_index]` joined together. The text block is the minimal citable unit; this field is never a substring of a single block. Not counted toward output tokens, and not counted toward input tokens when sent back in subsequent turns. - `end_block_index: number` Exclusive 0-based end index of the cited block range in the source's `content` array. Always greater than `start_block_index`; a single-block citation has `end_block_index = start_block_index + 1`. - `search_result_index: number` 0-based index of the cited search result among all `search_result` content blocks in the request, in the order they appear across messages and tool results. Counted separately from `document_index`; server-side web search results are not included in this count. minimum: 0 - `source: string` - `start_block_index: number` 0-based index of the first cited block in the source's `content` array. minimum: 0 - `title: string` - `text: string` - `is_error: boolean` - `tool_use_id: string` pattern: ^[a-zA-Z0-9_-]+$ ### Beta MCP Tool Use Block - `beta_mcp_tool_use_block: object` - `type: "mcp_tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: map[unknown]` - `name: string` The name of the MCP tool - `server_name: string` The name of the MCP server ### Beta MCP Tool Use Block Param - `beta_mcp_tool_use_block_param: object` - `type: "mcp_tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: map[unknown]` - `name: string` - `server_name: string` The name of the MCP server - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `"5m"` - `"1h"` ### Beta MCP Toolset - `beta_mcp_toolset: object` Configuration for a group of tools from an MCP server. Allows configuring enabled status and defer_loading for all tools from an MCP server, with optional per-tool overrides. - `type: "mcp_toolset"` - `mcp_server_name: string` Name of the MCP server to configure tools for minLength: 1, maxLength: 255 - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `"5m"` - `"1h"` - `configs: optional map[BetaMCPToolConfig]` Configuration overrides for specific tools, keyed by tool name - `defer_loading: optional boolean` - `enabled: optional boolean` - `default_config: optional object` Default configuration applied to all tools from this server - `defer_loading: optional boolean` - `enabled: optional boolean` - `tools: optional array of BetaMCPToolParam` The server's tool listing, pinned: when present, the server is not asked for its tools before sampling and exactly these entries, with `default_config` and `configs` applied, are the toolset's tools. Copy it from the `mcp_tool_listing` block of an earlier response. - `input_schema: map[unknown]` The tool's input schema as the MCP server lists it, verbatim. - `name: string` The tool's name as the MCP server lists it (not prefixed with the server name). minLength: 1 - `description: optional string` The tool's description as the MCP server lists it. ### Beta Memory Tool 20250818 - `beta_memory_tool_20250818: object` - `type: "memory_20250818"` - `name: "memory"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `"5m"` - `"1h"` - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs ### Beta Memory Tool 20250818 Command - `beta_memory_tool_20250818_command: BetaMemoryTool20250818ViewCommand or BetaMemoryTool20250818CreateCommand or BetaMemoryTool20250818StrReplaceCommand or 3 more` - `beta_memory_tool_20250818_view_command: object` - `command: "view"` Command type identifier - `path: string` Path to directory or file to view - `view_range: optional array of number` Optional line range for viewing specific lines minItems: 2, maxItems: 2 - `beta_memory_tool_20250818_create_command: object` - `command: "create"` Command type identifier - `file_text: string` Content to write to the file - `path: string` Path where the file should be created - `beta_memory_tool_20250818_str_replace_command: object` - `command: "str_replace"` Command type identifier - `new_str: string` Text to replace with - `old_str: string` Text to search for and replace - `path: string` Path to the file where text should be replaced - `beta_memory_tool_20250818_insert_command: object` - `command: "insert"` Command type identifier - `insert_line: number` Line number where text should be inserted minimum: 1 - `insert_text: string` Text to insert at the specified line - `path: string` Path to the file where text should be inserted - `beta_memory_tool_20250818_delete_command: object` - `command: "delete"` Command type identifier - `path: string` Path to the file or directory to delete - `beta_memory_tool_20250818_rename_command: object` - `command: "rename"` Command type identifier - `new_path: string` New path for the file or directory - `old_path: string` Current path of the file or directory ### Beta Memory Tool 20250818 Create Command - `beta_memory_tool_20250818_create_command: object` - `command: "create"` Command type identifier - `file_text: string` Content to write to the file - `path: string` Path where the file should be created ### Beta Memory Tool 20250818 Delete Command - `beta_memory_tool_20250818_delete_command: object` - `command: "delete"` Command type identifier - `path: string` Path to the file or directory to delete ### Beta Memory Tool 20250818 Insert Command - `beta_memory_tool_20250818_insert_command: object` - `command: "insert"` Command type identifier - `insert_line: number` Line number where text should be inserted minimum: 1 - `insert_text: string` Text to insert at the specified line - `path: string` Path to the file where text should be inserted ### Beta Memory Tool 20250818 Rename Command - `beta_memory_tool_20250818_rename_command: object` - `command: "rename"` Command type identifier - `new_path: string` New path for the file or directory - `old_path: string` Current path of the file or directory ### Beta Memory Tool 20250818 Str Replace Command - `beta_memory_tool_20250818_str_replace_command: object` - `command: "str_replace"` Command type identifier - `new_str: string` Text to replace with - `old_str: string` Text to search for and replace - `path: string` Path to the file where text should be replaced ### Beta Memory Tool 20250818 View Command - `beta_memory_tool_20250818_view_command: object` - `command: "view"` Command type identifier - `path: string` Path to directory or file to view - `view_range: optional array of number` Optional line range for viewing specific lines minItems: 2, maxItems: 2 ### Beta Message - `beta_message: object` - `type: "message"` Object type. For Messages, this is always `"message"`. - `id: string` Unique object identifier. The format and length of IDs may change over time. - `container: object` Information about the container used in this request. This will be non-null if a container tool (e.g. code execution) was used. - `id: string` Identifier for the container used in this request - `expires_at: string` The time at which the container will expire. format: date-time - `skills: array of BetaContainerSkill` Skills loaded in the container - `type: "anthropic" or "custom"` Type of skill - either 'anthropic' (built-in) or 'custom' (user-defined) - `"anthropic"` - `"custom"` - `skill_id: string` Skill ID minLength: 1, maxLength: 64 - `version: string` The resolved version: a skill version ID for custom skills. minLength: 1, maxLength: 64 - `content: array of BetaContentBlock` Content generated by the model. This is an array of content blocks, each of which has a `type` that determines its shape. Example: ```json [{"type": "text", "text": "Hi, I'm Claude."}] ``` If the request input `messages` ended with an `assistant` turn, then the response `content` will continue directly from that last turn. You can use this to constrain the model's output. For example, if the input `messages` were: ```json [ {"role": "user", "content": "What's the Greek name for Sun? (A) Sol (B) Helios (C) Sun"}, {"role": "assistant", "content": "The best answer is ("} ] ``` Then the response `content` might be: ```json [{"type": "text", "text": "B)"}] ``` - `beta_text_block: object` - `type: "text"` - `citations: array of BetaTextCitation` Citations supporting the text block. The type of citation returned will depend on the type of document being cited. Citing a PDF results in `page_location`, plain text results in `char_location`, and content document results in `content_block_location`. - `beta_citation_char_location: object` - `type: "char_location"` - `cited_text: string` - `document_index: number` minimum: 0 - `document_title: string` - `end_char_index: number` - `file_id: string` - `start_char_index: number` minimum: 0 - `beta_citation_page_location: object` - `type: "page_location"` - `cited_text: string` - `document_index: number` minimum: 0 - `document_title: string` - `end_page_number: number` - `file_id: string` - `start_page_number: number` minimum: 1 - `beta_citation_content_block_location: object` - `type: "content_block_location"` - `cited_text: string` The full text of the cited block range, concatenated. Always equals the contents of `content[start_block_index:end_block_index]` joined together. The text block is the minimal citable unit; this field is never a substring of a single block. Not counted toward output tokens, and not counted toward input tokens when sent back in subsequent turns. - `document_index: number` minimum: 0 - `document_title: string` - `end_block_index: number` Exclusive 0-based end index of the cited block range in the source's `content` array. Always greater than `start_block_index`; a single-block citation has `end_block_index = start_block_index + 1`. - `file_id: string` - `start_block_index: number` 0-based index of the first cited block in the source's `content` array. minimum: 0 - `beta_citations_web_search_result_location: object` - `type: "web_search_result_location"` - `cited_text: string` - `encrypted_index: string` - `title: string` maxLength: 512 - `url: string` - `beta_citation_search_result_location: object` - `type: "search_result_location"` - `cited_text: string` The full text of the cited block range, concatenated. Always equals the contents of `content[start_block_index:end_block_index]` joined together. The text block is the minimal citable unit; this field is never a substring of a single block. Not counted toward output tokens, and not counted toward input tokens when sent back in subsequent turns. - `end_block_index: number` Exclusive 0-based end index of the cited block range in the source's `content` array. Always greater than `start_block_index`; a single-block citation has `end_block_index = start_block_index + 1`. - `search_result_index: number` 0-based index of the cited search result among all `search_result` content blocks in the request, in the order they appear across messages and tool results. Counted separately from `document_index`; server-side web search results are not included in this count. minimum: 0 - `source: string` - `start_block_index: number` 0-based index of the first cited block in the source's `content` array. minimum: 0 - `title: string` - `text: string` - `beta_thinking_block: object` - `type: "thinking"` - `signature: string` A value used to verify that this thinking block was generated by Claude when it is passed back to the API. This is an opaque field and should not be interpreted or parsed. When passing thinking blocks back to the API (required when using tools with extended thinking), pass them back exactly as received, with this field intact. See [extended thinking](https://platform.claude.com/docs/en/build-with-claude/extended-thinking?sdk_languages=cli) for details. - `thinking: string` The text of Claude's thinking process for this block. - `beta_redacted_thinking_block: object` - `type: "redacted_thinking"` - `data: string` The contents of this redacted thinking block, returned when portions of the model's thinking were safety-redacted. This field is opaque and encrypted, with no readable content. Pass `redacted_thinking` blocks back to the API unchanged when continuing a multi-turn conversation. See [extended thinking](https://platform.claude.com/docs/en/build-with-claude/extended-thinking?sdk_languages=cli#redacted-thinking-blocks) for details. - `beta_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: map[unknown]` - `name: string` minLength: 1 - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` - `beta_direct_caller: object` Tool invocation directly from the model. - `type: "direct"` - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `type: "code_execution_20250825"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `beta_server_tool_caller_20260120: object` - `type: "code_execution_20260120"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `toolset_name: optional string` For a toolset member tool_use, the toolset family. minLength: 1, maxLength: 64, pattern: ^[a-zA-Z0-9_-]+$ - `beta_server_tool_use_block: object` - `type: "server_tool_use"` - `id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `input: map[unknown]` - `name: "advisor" or "web_search" or "web_fetch" or 5 more` - `"advisor"` - `"web_search"` - `"web_fetch"` - `"code_execution"` - `"bash_code_execution"` - `"text_editor_code_execution"` - `"tool_search_tool_regex"` - `"tool_search_tool_bm25"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` - `beta_direct_caller: object` Tool invocation directly from the model. - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `beta_server_tool_caller_20260120: object` - `beta_web_search_tool_result_block: object` - `type: "web_search_tool_result"` - `content: BetaWebSearchToolResultError or array of BetaWebSearchResultBlock` - `beta_web_search_tool_result_error: object` - `type: "web_search_tool_result_error"` - `error_code: "invalid_tool_input" or "unavailable" or "max_uses_exceeded" or 3 more` - `"invalid_tool_input"` - `"unavailable"` - `"max_uses_exceeded"` - `"too_many_requests"` - `"query_too_long"` - `"request_too_large"` - `union_member_1: array of BetaWebSearchResultBlock` - `type: "web_search_result"` - `encrypted_content: string` - `page_age: string` - `title: string` - `url: string` - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` - `beta_direct_caller: object` Tool invocation directly from the model. - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `beta_server_tool_caller_20260120: object` - `beta_web_fetch_tool_result_block: object` - `type: "web_fetch_tool_result"` - `content: BetaWebFetchToolResultErrorBlock or BetaWebFetchBlock` - `beta_web_fetch_tool_result_error_block: object` - `type: "web_fetch_tool_result_error"` - `error_code: "invalid_tool_input" or "url_too_long" or "url_not_allowed" or 7 more` - `"invalid_tool_input"` - `"url_too_long"` - `"url_not_allowed"` - `"url_not_in_prior_context"` - `"url_not_accessible"` - `"unsupported_content_type"` - `"too_many_requests"` - `"max_uses_exceeded"` - `"unavailable"` - `"content_too_large"` - `beta_web_fetch_block: object` - `type: "web_fetch_result"` - `content: object` - `type: "document"` - `citations: object` Citation configuration for the document - `enabled: boolean` - `source: BetaBase64PDFSource or BetaPlainTextSource` - `beta_base64_pdf_source: object` - `type: "base64"` - `data: string` format: byte - `media_type: "application/pdf"` - `beta_plain_text_source: object` - `type: "text"` - `data: string` - `media_type: "text/plain"` - `title: string` The title of the document - `retrieved_at: string` ISO 8601 timestamp when the content was retrieved - `url: string` Fetched content URL - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` - `beta_direct_caller: object` Tool invocation directly from the model. - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `beta_server_tool_caller_20260120: object` - `beta_advisor_tool_result_block: object` - `type: "advisor_tool_result"` - `content: BetaAdvisorToolResultError or BetaAdvisorResultBlock or BetaAdvisorRedactedResultBlock` - `beta_advisor_tool_result_error: object` - `type: "advisor_tool_result_error"` - `error_code: "max_uses_exceeded" or "prompt_too_long" or "too_many_requests" or 4 more` - `"max_uses_exceeded"` - `"prompt_too_long"` - `"too_many_requests"` - `"overloaded"` - `"unavailable"` - `"execution_time_exceeded"` - `"model_not_found"` - `beta_advisor_result_block: object` - `type: "advisor_result"` - `stop_reason: string` The advisor sub-inference's stop reason (same values as the top-level message `stop_reason`). `max_tokens` indicates the advisor's output was truncated at the tool's `max_tokens` value or the advisor model's policy cap. - `text: string` - `beta_advisor_redacted_result_block: object` - `type: "advisor_redacted_result"` - `encrypted_content: string` Opaque blob containing the advisor's output. Round-trip verbatim; do not inspect or modify. - `stop_reason: string` The advisor sub-inference's stop reason (same values as the top-level message `stop_reason`). - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `beta_code_execution_tool_result_block: object` - `type: "code_execution_tool_result"` - `content: BetaCodeExecutionToolResultError or BetaCodeExecutionResultBlock or BetaEncryptedCodeExecutionResultBlock` - `beta_code_execution_tool_result_error: object` - `type: "code_execution_tool_result_error"` - `error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or "execution_time_exceeded"` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `beta_code_execution_result_block: object` - `type: "code_execution_result"` - `content: array of BetaCodeExecutionOutputBlock` - `type: "code_execution_output"` - `file_id: string` - `return_code: number` - `stderr: string` - `stdout: string` - `beta_encrypted_code_execution_result_block: object` Code execution result with encrypted stdout for PFC + web_search results. - `type: "encrypted_code_execution_result"` - `content: array of BetaCodeExecutionOutputBlock` - `type: "code_execution_output"` - `file_id: string` - `encrypted_stdout: string` - `return_code: number` - `stderr: string` - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `beta_bash_code_execution_tool_result_block: object` - `type: "bash_code_execution_tool_result"` - `content: BetaBashCodeExecutionToolResultError or BetaBashCodeExecutionResultBlock` - `beta_bash_code_execution_tool_result_error: object` - `type: "bash_code_execution_tool_result_error"` - `error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or 2 more` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `"output_file_too_large"` - `beta_bash_code_execution_result_block: object` - `type: "bash_code_execution_result"` - `content: array of BetaBashCodeExecutionOutputBlock` - `type: "bash_code_execution_output"` - `file_id: string` - `return_code: number` - `stderr: string` - `stdout: string` - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `beta_text_editor_code_execution_tool_result_block: object` - `type: "text_editor_code_execution_tool_result"` - `content: BetaTextEditorCodeExecutionToolResultError or BetaTextEditorCodeExecutionViewResultBlock or BetaTextEditorCodeExecutionCreateResultBlock or BetaTextEditorCodeExecutionStrReplaceResultBlock` - `beta_text_editor_code_execution_tool_result_error: object` - `type: "text_editor_code_execution_tool_result_error"` - `error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or 2 more` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `"file_not_found"` - `error_message: string` - `beta_text_editor_code_execution_view_result_block: object` - `type: "text_editor_code_execution_view_result"` - `content: string` - `file_type: "text" or "image" or "pdf"` - `"text"` - `"image"` - `"pdf"` - `num_lines: number` - `start_line: number` - `total_lines: number` - `beta_text_editor_code_execution_create_result_block: object` - `type: "text_editor_code_execution_create_result"` - `is_file_update: boolean` - `beta_text_editor_code_execution_str_replace_result_block: object` - `type: "text_editor_code_execution_str_replace_result"` - `lines: array of string` - `new_lines: number` - `new_start: number` - `old_lines: number` - `old_start: number` - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `beta_tool_search_tool_result_block: object` - `type: "tool_search_tool_result"` - `content: BetaToolSearchToolResultError or BetaToolSearchToolSearchResultBlock` - `beta_tool_search_tool_result_error: object` - `type: "tool_search_tool_result_error"` - `error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or "execution_time_exceeded"` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `error_message: string` - `beta_tool_search_tool_search_result_block: object` - `type: "tool_search_tool_search_result"` - `tool_references: array of BetaToolReferenceBlock` - `type: "tool_reference"` - `tool_name: string` minLength: 1, maxLength: 256, pattern: ^[a-zA-Z0-9_-]{1,256}$ - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `beta_mcp_tool_use_block: object` - `type: "mcp_tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: map[unknown]` - `name: string` The name of the MCP tool - `server_name: string` The name of the MCP server - `beta_mcp_tool_result_block: object` - `type: "mcp_tool_result"` - `content: string or array of BetaTextBlock` - `union_member_0: string` - `beta_mcp_tool_result_block_content: array of BetaTextBlock` - `type: "text"` - `citations: array of BetaTextCitation` Citations supporting the text block. The type of citation returned will depend on the type of document being cited. Citing a PDF results in `page_location`, plain text results in `char_location`, and content document results in `content_block_location`. - `text: string` - `is_error: boolean` - `tool_use_id: string` pattern: ^[a-zA-Z0-9_-]+$ - `beta_container_upload_block: object` Response model for a file uploaded to the container. - `type: "container_upload"` - `file_id: string` - `beta_compaction_block: object` A compaction block returned when autocompact is triggered. When content is None, it indicates the compaction failed to produce a valid summary (e.g., malformed output from the model). Clients may round-trip compaction blocks with null content; the server treats them as no-ops. - `type: "compaction"` - `content: string` Summary of compacted content, or null if compaction failed - `encrypted_content: string` Opaque metadata from prior compaction, to be round-tripped verbatim - `signature: optional string` Signature over the summary, to be sent back with the block verbatim - `tool_changes: optional array of BetaResponseToolAdditionBlock or BetaResponseToolRemovalBlock` The tool changes of the compacted range: the `tool_addition` and `tool_removal` blocks that take the request's `tools` to the tool set in effect at the end of the range, or `[]` when the range changed no tool. Absent when the server did not compute them. Send the block back unchanged. - `beta_response_tool_addition_block: object` An entry of a `compaction` block's `tool_changes`: a tool the compacted range made available, as a reference to a `tools` entry or MCP toolset, or as the tool definition in effect at the end of the range, by value. Send it back unchanged. - `type: "tool_addition"` - `tool: BetaResponseToolChangeToolReference or BetaResponseToolChangeMCPToolReference or BetaResponseToolChangeMCPToolsetReference or BetaToolChangeToolDefinition` The tool made available: a reference to a `tools` entry or MCP toolset, or a `tool_definition` carrying the definition by value. - `beta_response_tool_change_tool_reference: object` Reference to a single tool, by the name the model uses to call it, as a `compaction` block's `tool_changes` entry reports it: a tool declared in `tools` or defined by an earlier `tool_addition` block. Send it back unchanged with the block. - `type: "tool_reference"` - `name: string` - `beta_response_tool_change_mcp_tool_reference: object` Reference to a single MCP tool, by its server and its name on that server, as a `compaction` block's `tool_changes` entry reports it. Send it back unchanged with the block. - `type: "mcp_tool_reference"` - `name: string` - `server_name: string` - `beta_response_tool_change_mcp_toolset_reference: object` Reference to every tool in the named MCP server's toolset, as a `compaction` block's `tool_changes` entry reports it. Send it back unchanged with the block. - `type: "mcp_toolset_reference"` - `server_name: string` - `beta_tool_change_tool_definition: object` A tool defined by value, as a `compaction` block's `tool_changes` entry reports it: `definition` is the tool's definition as it was sent, in the form of a `tools` entry, without `cache_control`. Send it back unchanged with the block. - `type: "tool_definition"` - `definition: BetaResponseTool or BetaToolBash20241022 or BetaToolBash20250124 or 25 more` - `beta_response_tool: object` A custom tool definition, as sent. - `type: optional "custom"` - `input_schema: object` [JSON schema](https://json-schema.org/draft/2020-12) for this tool's input. This defines the shape of the `input` that your tool accepts and that the model will produce. - `type: "object"` - `properties: optional map[unknown]` - `required: optional array of string` - `name: string` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. minLength: 1, maxLength: 128, pattern: ^[a-zA-Z0-9_-]{1,128}$ - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `description: optional string` Description of what this tool does. Tool descriptions should be as detailed as possible. The more information that the model has about what the tool is and how to use it, the better it will perform. You can use natural language descriptions to reinforce important aspects of the tool input JSON schema. - `eager_input_streaming: optional boolean` Enable eager input streaming for this tool. When true, tool input parameters will be streamed incrementally as they are generated, and types will be inferred on-the-fly rather than buffering the full JSON output. When false, streaming is disabled for this tool even if the fine-grained-tool-streaming beta is active. When null (default), uses the default behavior based on beta headers. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_bash_20241022: object` - `type: "bash_20241022"` - `name: "bash"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `"5m"` - `"1h"` - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_bash_20250124: object` - `type: "bash_20250124"` - `name: "bash"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_code_execution_tool_20250522: object` - `type: "code_execution_20250522"` - `name: "code_execution"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_code_execution_tool_20250825: object` - `type: "code_execution_20250825"` - `name: "code_execution"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_code_execution_tool_20260120: object` Code execution tool with REPL state persistence (daemon mode + gVisor checkpoint). - `type: "code_execution_20260120"` - `name: "code_execution"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_code_execution_tool_20260521: object` Code execution tool with REPL state persistence. - `type: "code_execution_20260521"` - `name: "code_execution"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_browser_toolset_20260801: object` The browser toolset: a single `tools[]` entry (carrying no `name`) that declares the browser tool family. The model is served the family's tool with any members disabled via `configs` removed from its schema. - `type: "browser_toolset_20260801"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `configs: optional object` Sparse per-member overrides, keyed by member name. Absent, null, and {} are equivalent; a member's defaults apply wherever its key is absent. - `type: optional object` `type`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `close_tab: optional object` `close_tab`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `double_click: optional object` `double_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `file_upload: optional object` `file_upload`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `find: optional object` `find`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `form_input: optional object` `form_input`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `get_page_text: optional object` `get_page_text`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `hold_key: optional object` `hold_key`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `hover: optional object` `hover`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `javascript_exec: optional object` `javascript_exec`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `key: optional object` `key`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_click: optional object` `left_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_click_drag: optional object` `left_click_drag`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_mouse_down: optional object` `left_mouse_down`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_mouse_up: optional object` `left_mouse_up`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `list_tabs: optional object` `list_tabs`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `middle_click: optional object` `middle_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `mouse_move: optional object` `mouse_move`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `navigate: optional object` `navigate`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `new_tab: optional object` `new_tab`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `read_console: optional object` `read_console`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `read_network: optional object` `read_network`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `read_page: optional object` `read_page`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `right_click: optional object` `right_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `screenshot: optional object` `screenshot`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `scroll: optional object` `scroll`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `scroll_to: optional object` `scroll_to`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `switch_tab: optional object` `switch_tab`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `triple_click: optional object` `triple_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `wait: optional object` `wait`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `zoom: optional object` `zoom`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `beta_tool_computer_use_20241022: object` - `type: "computer_20241022"` - `display_height_px: number` The height of the display in pixels. minimum: 1 - `display_width_px: number` The width of the display in pixels. minimum: 1 - `name: "computer"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `display_number: optional number` The X11 display number (e.g. 0, 1) for the display. minimum: 0 - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_memory_tool_20250818: object` - `type: "memory_20250818"` - `name: "memory"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_computer_use_20250124: object` - `type: "computer_20250124"` - `display_height_px: number` The height of the display in pixels. minimum: 1 - `display_width_px: number` The width of the display in pixels. minimum: 1 - `name: "computer"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `display_number: optional number` The X11 display number (e.g. 0, 1) for the display. minimum: 0 - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_text_editor_20241022: object` - `type: "text_editor_20241022"` - `name: "str_replace_editor"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_computer_use_20251124: object` - `type: "computer_20251124"` - `display_height_px: number` The height of the display in pixels. minimum: 1 - `display_width_px: number` The width of the display in pixels. minimum: 1 - `name: "computer"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `display_number: optional number` The X11 display number (e.g. 0, 1) for the display. minimum: 0 - `enable_zoom: optional boolean` Whether to enable an action to take a zoomed-in screenshot of the screen. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_computer_toolset_20260801: object` The computer toolset: a single `tools[]` entry (carrying no `name`) that declares the computer tool family. The model is served the family's tool with any members disabled via `configs` removed from its schema. Every member is enabled by default, zoom included. The single-tool options `display_number` and `enable_zoom` are not fields of a toolset entry — it carries only `type`, `configs`, and `cache_control`; zoom is controlled via `configs.zoom.enabled`. - `type: "computer_toolset_20260801"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `configs: optional object` Sparse per-member overrides, keyed by member name. Absent, null, and {} are equivalent; a member's defaults apply wherever its key is absent. - `type: optional object` `type`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `cursor_position: optional object` `cursor_position`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `double_click: optional object` `double_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `hold_key: optional object` `hold_key`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `key: optional object` `key`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_click: optional object` `left_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_click_drag: optional object` `left_click_drag`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_mouse_down: optional object` `left_mouse_down`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_mouse_up: optional object` `left_mouse_up`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `middle_click: optional object` `middle_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `mouse_move: optional object` `mouse_move`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `right_click: optional object` `right_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `screenshot: optional object` `screenshot`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `scroll: optional object` `scroll`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `triple_click: optional object` `triple_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `wait: optional object` `wait`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `zoom: optional object` `zoom`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `beta_tool_text_editor_20250124: object` - `type: "text_editor_20250124"` - `name: "str_replace_editor"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_text_editor_20250429: object` - `type: "text_editor_20250429"` - `name: "str_replace_based_edit_tool"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_text_editor_20250728: object` - `type: "text_editor_20250728"` - `name: "str_replace_based_edit_tool"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: optional array of map[unknown]` - `max_characters: optional number` Maximum number of characters to display when viewing a file. If not specified, defaults to displaying the full file. minimum: 1 - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_web_search_tool_20250305: object` - `type: "web_search_20250305"` - `name: "web_search"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: optional array of string` If provided, only these domains will be included in results. Cannot be used alongside `blocked_domains`. - `blocked_domains: optional array of string` If provided, these domains will never appear in results. Cannot be used alongside `allowed_domains`. - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `user_location: optional object` Parameters for the user's location. Used to provide more relevant search results. - `type: "approximate"` - `city: optional string` The city of the user. minLength: 1, maxLength: 255 - `country: optional string` The two letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1_alpha-2) of the user. minLength: 2, maxLength: 2 - `region: optional string` The region of the user. minLength: 1, maxLength: 255 - `timezone: optional string` The [IANA timezone](https://nodatime.org/TimeZones) of the user. minLength: 1, maxLength: 255 - `beta_web_fetch_tool_20250910: object` - `type: "web_fetch_20250910"` - `name: "web_fetch"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: optional array of string` List of domains to allow fetching from - `blocked_domains: optional array of string` List of domains to block fetching from - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `citations: optional object` Citations configuration for fetched documents. Citations are disabled by default. - `enabled: optional boolean` - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_content_tokens: optional number` Maximum number of tokens used by including web page text content in the context. The limit is approximate and does not apply to binary content such as PDFs. minimum: 1 - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `url_sources: optional object` Which sources contribute to the set of URLs the tool may fetch. Omitted means every source. - `client_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which client tools' results contribute fetchable URLs: "all", "none", or an only or except list of client tool names from tools[]. - `beta_web_fetch_url_source_all: object` The `url_sources` variant under which a source contributes in full: every result of the tool filter's source, or all user input. - `type: "all"` - `beta_web_fetch_url_source_none: object` The `url_sources` variant under which a source contributes nothing: no result of the tool filter's source, or no user input. - `type: "none"` - `beta_web_fetch_url_source_only: object` The tool filter variant under which only the named tools' results contribute. - `type: "only"` - `tools: array of BetaWebFetchURLSourceToolReference` - `type: "tool_reference"` - `name: string` - `beta_web_fetch_url_source_except: object` The tool filter variant under which every result but the named tools' contributes. - `type: "except"` - `tools: array of BetaWebFetchURLSourceToolReference` - `type: "tool_reference"` - `name: string` - `server_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which server tools' results contribute fetchable URLs: "all", "none", or an only or except list of server tool names from tools[]; only web_search and web_fetch results ever contribute. - `beta_web_fetch_url_source_all: object` The `url_sources` variant under which a source contributes in full: every result of the tool filter's source, or all user input. - `beta_web_fetch_url_source_none: object` The `url_sources` variant under which a source contributes nothing: no result of the tool filter's source, or no user input. - `beta_web_fetch_url_source_only: object` The tool filter variant under which only the named tools' results contribute. - `beta_web_fetch_url_source_except: object` The tool filter variant under which every result but the named tools' contributes. - `user_input: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone` Whether URLs in user messages are fetchable: "all" or "none". - `beta_web_fetch_url_source_all: object` The `url_sources` variant under which a source contributes in full: every result of the tool filter's source, or all user input. - `beta_web_fetch_url_source_none: object` The `url_sources` variant under which a source contributes nothing: no result of the tool filter's source, or no user input. - `beta_web_search_tool_20260209: object` - `type: "web_search_20260209"` - `name: "web_search"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: optional array of string` If provided, only these domains will be included in results. Cannot be used alongside `blocked_domains`. - `blocked_domains: optional array of string` If provided, these domains will never appear in results. Cannot be used alongside `allowed_domains`. - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `user_location: optional object` Parameters for the user's location. Used to provide more relevant search results. - `type: "approximate"` - `city: optional string` The city of the user. minLength: 1, maxLength: 255 - `country: optional string` The two letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1_alpha-2) of the user. minLength: 2, maxLength: 2 - `region: optional string` The region of the user. minLength: 1, maxLength: 255 - `timezone: optional string` The [IANA timezone](https://nodatime.org/TimeZones) of the user. minLength: 1, maxLength: 255 - `beta_web_fetch_tool_20260209: object` - `type: "web_fetch_20260209"` - `name: "web_fetch"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: optional array of string` List of domains to allow fetching from - `blocked_domains: optional array of string` List of domains to block fetching from - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `citations: optional object` Citations configuration for fetched documents. Citations are disabled by default. - `enabled: optional boolean` - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_content_tokens: optional number` Maximum number of tokens used by including web page text content in the context. The limit is approximate and does not apply to binary content such as PDFs. minimum: 1 - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `url_sources: optional object` Which sources contribute to the set of URLs the tool may fetch. Omitted means every source. - `client_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which client tools' results contribute fetchable URLs: "all", "none", or an only or except list of client tool names from tools[]. - `server_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which server tools' results contribute fetchable URLs: "all", "none", or an only or except list of server tool names from tools[]; only web_search and web_fetch results ever contribute. - `user_input: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone` Whether URLs in user messages are fetchable: "all" or "none". - `beta_web_fetch_tool_20260309: object` Web fetch tool with use_cache parameter for bypassing cached content. - `type: "web_fetch_20260309"` - `name: "web_fetch"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: optional array of string` List of domains to allow fetching from - `blocked_domains: optional array of string` List of domains to block fetching from - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `citations: optional object` Citations configuration for fetched documents. Citations are disabled by default. - `enabled: optional boolean` - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_content_tokens: optional number` Maximum number of tokens used by including web page text content in the context. The limit is approximate and does not apply to binary content such as PDFs. minimum: 1 - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `url_sources: optional object` Which sources contribute to the set of URLs the tool may fetch. Omitted means every source. - `client_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which client tools' results contribute fetchable URLs: "all", "none", or an only or except list of client tool names from tools[]. - `server_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which server tools' results contribute fetchable URLs: "all", "none", or an only or except list of server tool names from tools[]; only web_search and web_fetch results ever contribute. - `user_input: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone` Whether URLs in user messages are fetchable: "all" or "none". - `use_cache: optional boolean` Whether to use cached content. Set to false to bypass the cache and fetch fresh content. Only set to false when the user explicitly requests fresh content or when fetching rapidly-changing sources. - `beta_web_search_tool_20260318: object` - `type: "web_search_20260318"` - `name: "web_search"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: optional array of string` If provided, only these domains will be included in results. Cannot be used alongside `blocked_domains`. - `blocked_domains: optional array of string` If provided, these domains will never appear in results. Cannot be used alongside `allowed_domains`. - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `response_inclusion: optional "full" or "excluded"` How this tool's result blocks appear in the API response when the result was consumed by a completed code_execution call in the same turn. 'full' returns the complete content (default). 'excluded' drops the nested server_tool_use and result block pair entirely. Results from direct calls, or from code_execution calls that paused before completing, are always returned in full so they can be sent back on the next turn. - `"full"` - `"excluded"` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `user_location: optional object` Parameters for the user's location. Used to provide more relevant search results. - `type: "approximate"` - `city: optional string` The city of the user. minLength: 1, maxLength: 255 - `country: optional string` The two letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1_alpha-2) of the user. minLength: 2, maxLength: 2 - `region: optional string` The region of the user. minLength: 1, maxLength: 255 - `timezone: optional string` The [IANA timezone](https://nodatime.org/TimeZones) of the user. minLength: 1, maxLength: 255 - `beta_web_fetch_tool_20260318: object` - `type: "web_fetch_20260318"` - `name: "web_fetch"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: optional array of string` List of domains to allow fetching from - `blocked_domains: optional array of string` List of domains to block fetching from - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `citations: optional object` Citations configuration for fetched documents. Citations are disabled by default. - `enabled: optional boolean` - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_content_tokens: optional number` Maximum number of tokens used by including web page text content in the context. The limit is approximate and does not apply to binary content such as PDFs. minimum: 1 - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `response_inclusion: optional "full" or "excluded"` How this tool's result blocks appear in the API response when the result was consumed by a completed code_execution call in the same turn. 'full' returns the complete content (default). 'excluded' drops the nested server_tool_use and result block pair entirely. Results from direct calls, or from code_execution calls that paused before completing, are always returned in full so they can be sent back on the next turn. - `"full"` - `"excluded"` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `url_sources: optional object` Which sources contribute to the set of URLs the tool may fetch. Omitted means every source. - `client_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which client tools' results contribute fetchable URLs: "all", "none", or an only or except list of client tool names from tools[]. - `server_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which server tools' results contribute fetchable URLs: "all", "none", or an only or except list of server tool names from tools[]; only web_search and web_fetch results ever contribute. - `user_input: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone` Whether URLs in user messages are fetchable: "all" or "none". - `use_cache: optional boolean` Whether to use cached content. Set to false to bypass the cache and fetch fresh content. Only set to false when the user explicitly requests fresh content or when fetching rapidly-changing sources. - `beta_advisor_tool_20260301: object` - `type: "advisor_20260301"` - `model: "claude-haiku-5-5" or "claude-sonnet-5-5" or "claude-fable-5-1" or 17 more or string` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-haiku-5-5"` Fastest model for high-volume, real-time tasks - `"claude-sonnet-5-5"` Efficient model for coding and agents - `"claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows - `"claude-opus-5-5"` Powerful intelligence for coding, knowledge work, and long-running agents - `"claude-mythos-5-1"` Our most capable model for cybersecurity and biology research, available through trusted access programs - `"claude-sonnet-5"` Efficient model for coding and agents - `"claude-fable-5"` Next generation of intelligence for the hardest knowledge work and coding problems - `"claude-mythos-5"` Most capable model for cybersecurity and biology research - `"claude-opus-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-8"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-7"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-6"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-6"` Best combination of speed and intelligence - `"claude-haiku-4-5"` - `"claude-haiku-4-5-20251001"` - `"claude-opus-4-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-5-20251101"` Powerful intelligence for long-running agents and coding - `"claude-mythos-preview"` **Deprecated**: Will reach end-of-life on June 30, 2026. Please migrate to claude-mythos-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. New class of intelligence, strongest in coding and cybersecurity - `"claude-sonnet-4-5"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `"claude-sonnet-4-5-20250929"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `name: "advisor"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `caching: optional object` Caching for the advisor's own prompt. When set, each advisor call writes a cache entry at the given TTL so subsequent calls in the same conversation read the stable prefix. When omitted, the advisor prompt is not cached. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_tokens: optional number` Bounds the advisor's total output (thinking + text) per call. When the advisor hits this cap, the returned advisor_result or advisor_redacted_result block carries stop_reason='max_tokens', and a truncation note is appended to the advice text the worker model sees (inside the encrypted blob in redacted mode). When set, the server also emits a remaining-tokens budget block in the advisor's prompt so the advisor self-shapes toward the cap. When omitted, the advisor model's default output cap applies and no budget block is emitted. minimum: 1024 - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_search_tool_bm25_20251119: object` - `type: "tool_search_tool_bm25_20251119" or "tool_search_tool_bm25"` - `"tool_search_tool_bm25_20251119"` - `"tool_search_tool_bm25"` - `name: "tool_search_tool_bm25"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_search_tool_regex_20251119: object` - `type: "tool_search_tool_regex_20251119" or "tool_search_tool_regex"` - `"tool_search_tool_regex_20251119"` - `"tool_search_tool_regex"` - `name: "tool_search_tool_regex"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_mcp_toolset: object` Configuration for a group of tools from an MCP server. Allows configuring enabled status and defer_loading for all tools from an MCP server, with optional per-tool overrides. - `type: "mcp_toolset"` - `mcp_server_name: string` Name of the MCP server to configure tools for minLength: 1, maxLength: 255 - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `configs: optional map[BetaMCPToolConfig]` Configuration overrides for specific tools, keyed by tool name - `defer_loading: optional boolean` - `enabled: optional boolean` - `default_config: optional object` Default configuration applied to all tools from this server - `defer_loading: optional boolean` - `enabled: optional boolean` - `tools: optional array of BetaMCPToolParam` The server's tool listing, pinned: when present, the server is not asked for its tools before sampling and exactly these entries, with `default_config` and `configs` applied, are the toolset's tools. Copy it from the `mcp_tool_listing` block of an earlier response. - `input_schema: map[unknown]` The tool's input schema as the MCP server lists it, verbatim. - `name: string` The tool's name as the MCP server lists it (not prefixed with the server name). minLength: 1 - `description: optional string` The tool's description as the MCP server lists it. - `beta_response_tool_removal_block: object` An entry of a `compaction` block's `tool_changes`: a tool of the request's `tools` (or an MCP tool or toolset) that the compacted range withdrew. Send it back unchanged. - `type: "tool_removal"` - `tool: BetaResponseToolChangeToolReference or BetaResponseToolChangeMCPToolReference or BetaResponseToolChangeMCPToolsetReference` A reference to the withdrawn `tools` entry, MCP tool or MCP toolset. - `beta_response_tool_change_tool_reference: object` Reference to a single tool, by the name the model uses to call it, as a `compaction` block's `tool_changes` entry reports it: a tool declared in `tools` or defined by an earlier `tool_addition` block. Send it back unchanged with the block. - `beta_response_tool_change_mcp_tool_reference: object` Reference to a single MCP tool, by its server and its name on that server, as a `compaction` block's `tool_changes` entry reports it. Send it back unchanged with the block. - `beta_response_tool_change_mcp_toolset_reference: object` Reference to every tool in the named MCP server's toolset, as a `compaction` block's `tool_changes` entry reports it. Send it back unchanged with the block. - `beta_fallback_block: object` Marks the point in `content` where one model's output gives way to the next. One block appears per hop where a preceding model actually ran this turn and declined. A turn where no preceding model ran and declined has no such boundary and carries no block — the signal for whether a fallback model served the response is the presence of a `fallback_message` entry in `usage.iterations`, not this block. The block is treated like a server-tool content block for streaming: it arrives via the standard `content_block_start` / `content_block_stop` pair and carries no deltas. - `type: "fallback"` - `from: object` The model whose output ends at this point — the model that declined at this hop. When the declining hop is the requested model, its `model` echoes the top-level `model` string the caller sent (alias or canonical); when the declining hop is a fallback model, its `model` is that model's canonical id. - `model: "claude-haiku-5-5" or "claude-sonnet-5-5" or "claude-fable-5-1" or 17 more or string` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-haiku-5-5"` Fastest model for high-volume, real-time tasks - `"claude-sonnet-5-5"` Efficient model for coding and agents - `"claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows - `"claude-opus-5-5"` Powerful intelligence for coding, knowledge work, and long-running agents - `"claude-mythos-5-1"` Our most capable model for cybersecurity and biology research, available through trusted access programs - `"claude-sonnet-5"` Efficient model for coding and agents - `"claude-fable-5"` Next generation of intelligence for the hardest knowledge work and coding problems - `"claude-mythos-5"` Most capable model for cybersecurity and biology research - `"claude-opus-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-8"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-7"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-6"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-6"` Best combination of speed and intelligence - `"claude-haiku-4-5"` - `"claude-haiku-4-5-20251001"` - `"claude-opus-4-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-5-20251101"` Powerful intelligence for long-running agents and coding - `"claude-mythos-preview"` **Deprecated**: Will reach end-of-life on June 30, 2026. Please migrate to claude-mythos-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. New class of intelligence, strongest in coding and cybersecurity - `"claude-sonnet-4-5"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `"claude-sonnet-4-5-20250929"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `to: object` The fallback model producing the content that follows this block. Its `model` is always the canonical id. - `model: "claude-haiku-5-5" or "claude-sonnet-5-5" or "claude-fable-5-1" or 17 more or string` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `trigger: object` What caused the `from` model to hand over at this hop. - `type: "refusal"` - `category: "cyber" or "bio" or "frontier_llm" or 2 more` The policy category that triggered the `from` model's refusal at this hop. `null` when the refusal doesn't map to a named category. Same vocabulary as `stop_details.category`. - `"cyber"` The request could enable cyber harm, such as malware or exploit development. Benign cybersecurity work can also trigger this category. - `"bio"` The request could enable biological harm, such as dangerous lab methods. Beneficial life sciences work can also trigger this category. - `"frontier_llm"` The request could assist the development of competing AI models, which is restricted under [Anthropic's commercial terms](https://www.anthropic.com/legal/commercial-terms). Benign machine learning work can also trigger this category. - `"reasoning_extraction"` The request asks the model to reproduce its internal reasoning in the response text. To get reasoning in a structured form instead, use [adaptive thinking](https://platform.claude.com/docs/en/build-with-claude/adaptive-thinking?sdk_languages=cli). - `"general_harms"` The request could be related to an area that was determined as harmful. Benign work might sometimes trigger this category. - `beta_mcp_tool_listing_block: object` The tool listing the server fetched from an MCP server while producing this response. Send the assistant message back unchanged, this block included, so later requests use this listing instead of asking the MCP server again. - `type: "mcp_tool_listing"` - `mcp_server_name: string` - `tools: array of BetaMCPTool` - `input_schema: map[unknown]` - `name: string` - `description: optional string` - `context_management: object` Context management response. Information about context management strategies applied during the request. - `applied_edits: array of BetaClearToolUses20250919EditResponse or BetaClearThinking20251015EditResponse` List of context management edits that were applied. - `beta_clear_tool_uses_20250919_edit_response: object` - `type: "clear_tool_uses_20250919"` The type of context management edit applied. - `cleared_input_tokens: number` Number of input tokens cleared by this edit. minimum: 0 - `cleared_tool_uses: number` Number of tool uses that were cleared. minimum: 0 - `beta_clear_thinking_20251015_edit_response: object` - `type: "clear_thinking_20251015"` The type of context management edit applied. - `cleared_input_tokens: number` Number of input tokens cleared by this edit. minimum: 0 - `cleared_thinking_turns: number` Number of thinking turns that were cleared. minimum: 0 - `diagnostics: object` Request-level diagnostics. `null` when the request did not supply `diagnostics`, or when it did and no prompt-cache divergence was detected. - `cache_miss_reason: BetaCacheMissModelChanged or BetaCacheMissSystemChanged or BetaCacheMissToolsChanged or 3 more` Explains why the prompt cache could not fully reuse the prefix from the request identified by `diagnostics.previous_message_id`. `null` means diagnosis is still pending — the response was serialized before the background comparison completed. - `beta_cache_miss_model_changed: object` - `type: "model_changed"` - `cache_missed_input_tokens: number` Approximate number of input tokens that would have been read from cache had the prefix matched the previous request. - `beta_cache_miss_system_changed: object` - `type: "system_changed"` - `cache_missed_input_tokens: number` Approximate number of input tokens that would have been read from cache had the prefix matched the previous request. - `beta_cache_miss_tools_changed: object` - `type: "tools_changed"` - `cache_missed_input_tokens: number` Approximate number of input tokens that would have been read from cache had the prefix matched the previous request. - `beta_cache_miss_messages_changed: object` - `type: "messages_changed"` - `cache_missed_input_tokens: number` Approximate number of input tokens that would have been read from cache had the prefix matched the previous request. - `beta_cache_miss_previous_message_not_found: object` - `type: "previous_message_not_found"` - `beta_cache_miss_unavailable: object` - `type: "unavailable"` - `model: "claude-haiku-5-5" or "claude-sonnet-5-5" or "claude-fable-5-1" or 17 more or string` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-haiku-5-5"` Fastest model for high-volume, real-time tasks - `"claude-sonnet-5-5"` Efficient model for coding and agents - `"claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows - `"claude-opus-5-5"` Powerful intelligence for coding, knowledge work, and long-running agents - `"claude-mythos-5-1"` Our most capable model for cybersecurity and biology research, available through trusted access programs - `"claude-sonnet-5"` Efficient model for coding and agents - `"claude-fable-5"` Next generation of intelligence for the hardest knowledge work and coding problems - `"claude-mythos-5"` Most capable model for cybersecurity and biology research - `"claude-opus-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-8"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-7"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-6"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-6"` Best combination of speed and intelligence - `"claude-haiku-4-5"` - `"claude-haiku-4-5-20251001"` - `"claude-opus-4-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-5-20251101"` Powerful intelligence for long-running agents and coding - `"claude-mythos-preview"` **Deprecated**: Will reach end-of-life on June 30, 2026. Please migrate to claude-mythos-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. New class of intelligence, strongest in coding and cybersecurity - `"claude-sonnet-4-5"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `"claude-sonnet-4-5-20250929"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `role: "assistant"` Conversational role of the generated message. This will always be `"assistant"`. - `stop_details: object` Structured information about why model output stopped. This is `null` when the `stop_reason` has no additional detail to report. - `type: "refusal"` - `category: "cyber" or "bio" or "frontier_llm" or 2 more` The policy category that triggered the refusal. `null` when the refusal doesn't map to a named category. - `"cyber"` The request could enable cyber harm, such as malware or exploit development. Benign cybersecurity work can also trigger this category. - `"bio"` The request could enable biological harm, such as dangerous lab methods. Beneficial life sciences work can also trigger this category. - `"frontier_llm"` The request could assist the development of competing AI models, which is restricted under [Anthropic's commercial terms](https://www.anthropic.com/legal/commercial-terms). Benign machine learning work can also trigger this category. - `"reasoning_extraction"` The request asks the model to reproduce its internal reasoning in the response text. To get reasoning in a structured form instead, use [adaptive thinking](https://platform.claude.com/docs/en/build-with-claude/adaptive-thinking?sdk_languages=cli). - `"general_harms"` The request could be related to an area that was determined as harmful. Benign work might sometimes trigger this category. - `explanation: string` Human-readable explanation of the refusal. This text is not guaranteed to be stable. `null` when no explanation is available for the category. - `fallback_credit_token: string` Opaque code that refunds the cache-miss cost when retrying this refused request on the fallback model. Pass it as `fallback_credit_token` on the retry request. Expires 5 minutes after the refusal. The retry is sent either with the same request body (`system`, `messages`, `tools`, and other render-shaping fields), or with the same body plus one appended `assistant` message whose content is the partial text (with any trailing whitespace stripped from the final text block) and paired server-tool blocks from this refusal — which also authorizes that appended turn as an assistant-prefill continuation on models that otherwise disallow prefill. A token minted mid-server-tool-loop whose partial content was continuable may only be redeemed the second way — if a same-body retry is rejected with a 400 saying the token must be redeemed by continuing the partial response, retry the second way instead. Either way: same workspace, same platform; a mismatch is a 400. Resending a token for an already-warm prefix is permitted but yields no additional credit. `null` when the refused model isn't eligible for a fallback credit. - `fallback_has_prefill_claim: boolean` Whether the accompanying `fallback_credit_token` may be redeemed with the appended-assistant retry form. Only set when `fallback_credit_token` is present. `true`: retry by resending the same request body plus one appended `assistant` message whose content is this response's `content` with any trailing whitespace stripped from the final text block and unpaired `tool_use` blocks omitted (the same appended-turn shape described on `fallback_credit_token`), with the token attached. `false`: retry by resending the original request body unchanged, with the token attached — the appended-assistant form is not available for this refusal (no continuable partial content, or the request uses `output_format` or a `tool_choice` that forces tool use). One exception: when the request used `output_format` or a forced `tool_choice` and the refusal arrived after server tools (including MCP connector tools) had already executed, the token may not be redeemable by either retry form; if the exact-body retry is then rejected with a 400 saying the token must be redeemed by continuing the partial response, discard the token and retry without it. Advisory: if an appended-assistant retry is rejected with a 400 despite `true`, fall back to resending the original request body with the token. - `recommended_model: string` The server's suggested retry target for this refusal. Populated when a fallback attempt could not be made (the fallback model's rate limit was exhausted, or it was overloaded); names the fallback model the caller can retry directly. Null otherwise. - `stop_reason: "end_turn" or "max_tokens" or "stop_sequence" or 5 more` The reason that we stopped. This may be one the following values: * `"end_turn"`: the model reached a natural stopping point * `"max_tokens"`: we exceeded the requested `max_tokens` or the model's maximum * `"stop_sequence"`: one of your provided custom `stop_sequences` was generated * `"tool_use"`: the model invoked one or more tools * `"pause_turn"`: we paused a long-running turn. You may provide the response back as-is in a subsequent request to let the model continue. * `"refusal"`: when streaming classifiers intervene to handle potential policy violations * `"model_context_window_exceeded"`: we exceeded the model's context window In non-streaming mode this value is always non-null. In streaming mode, it is null in the `message_start` event and non-null otherwise. - `"end_turn"` - `"max_tokens"` - `"stop_sequence"` - `"tool_use"` - `"pause_turn"` - `"compaction"` - `"refusal"` - `"model_context_window_exceeded"` - `stop_sequence: string` Which custom stop sequence was generated, if any. This value will be a non-null string if one of your custom stop sequences was generated. - `usage: object` Billing and rate-limit usage. Anthropic's API bills and rate-limits by token counts, as tokens represent the underlying cost to our systems. Under the hood, the API transforms requests into a format suitable for the model. The model's output then goes through a parsing stage before becoming an API response. As a result, the token counts in `usage` will not match one-to-one with the exact visible content of an API request or response. For example, `output_tokens` will be non-zero, even for an empty string response from Claude. Total input tokens in a request is the summation of `input_tokens`, `cache_creation_input_tokens`, and `cache_read_input_tokens`. - `cache_creation: object` Breakdown of cached tokens by TTL - `ephemeral_1h_input_tokens: number` The number of input tokens used to create the 1 hour cache entry. minimum: 0 - `ephemeral_5m_input_tokens: number` The number of input tokens used to create the 5 minute cache entry. minimum: 0 - `cache_creation_input_tokens: number` The number of input tokens used to create the cache entry. minimum: 0 - `cache_read_input_tokens: number` The number of input tokens read from the cache. minimum: 0 - `fallback_credit: object` Outcome of the `fallback_credit_token` presented on this request. Present on every response to a non-batch request that carried a `fallback_credit_token`, in either redemption mode; absent otherwise (batch items accept and ignore the token and carry no outcome object). - `status: BetaFallbackCreditRedeemed or BetaFallbackCreditNotApplied` Whether the fallback-credit reprice was applied to this response's billing. A union discriminated on `type`. `redeemed`: the retry is billed as if the conversation had been on the retry model all along — including when the resulting shift is zero because there was nothing to move. `not_applied`: no reprice was applied; the arm's `reason` says why. - `beta_fallback_credit_redeemed: object` The reprice was applied: the retry is billed as if the conversation had been on the retry model all along. - `type: "redeemed"` - `beta_fallback_credit_not_applied: object` No reprice was applied; `reason` says why. - `type: "not_applied"` - `reason: "body_mismatch" or "continuation_excluded" or "continuation_only" or 9 more` Why the reprice was not applied. A closed enum; additions to the redemption-check vocabulary arrive as deliberate schema updates. - `"body_mismatch"` - `"continuation_excluded"` - `"continuation_only"` - `"expired"` - `"invalid_target_model"` - `"not_enabled"` - `"reprice_unavailable"` - `"temporarily_unavailable"` - `"variant_fields_present"` - `"wrong_organization"` - `"wrong_platform"` - `"wrong_workspace"` - `remove_to_redeem: optional array of string` Request fields to remove before retrying, so the retry can redeem this token. Present exactly when `reason` is `variant_fields_present` — never null, never an empty array; absent otherwise. Fields are named only from your own request, and only after the sealed variant hash matched. A served best-effort retry has already been billed at normal price; nothing redeems retroactively, but a corrected re-send inside the token's five-minute window can still redeem. - `inference_geo: string` The geographic region where inference was performed for this request. - `input_tokens: number` The number of input tokens which were used. minimum: 0 - `iterations: array of BetaMessageIterationUsage or BetaCompactionIterationUsage or BetaAdvisorMessageIterationUsage or BetaFallbackMessageIterationUsage` Per-iteration token usage breakdown. Each entry represents one sampling iteration, with its own input/output token counts and cache statistics, discriminated by `type`. For `message` entries (model sampling iterations, such as the turns of a server-side tool use loop), this allows you to: - Calculate the context window size from the last `message` entry - Understand token accumulation across server-side tool use loops A `compaction` entry reports the token usage of the compaction operation itself — the server-side request that summarizes the context being closed — NOT the size of the context that was compacted away, and its token counts can be much smaller than that closed context (for example, a compaction that closes a ~200k-token context can report only a few thousand tokens). Do not derive the context window size from a `compaction` entry, even when it is the last entry. A `compaction` entry's tokens are not included in the top-level `usage` fields. When an input-token trigger is in effect (the default — 150,000 tokens unless configured otherwise), each `compaction` entry closes a context that had reached at least that threshold, though the context can exceed it by the final iteration's output and tool results. - `beta_message_iteration_usage: object` Token usage for a sampling iteration. - `type: "message"` Usage for a sampling iteration - `cache_creation: object` Breakdown of cached tokens by TTL - `ephemeral_1h_input_tokens: number` The number of input tokens used to create the 1 hour cache entry. minimum: 0 - `ephemeral_5m_input_tokens: number` The number of input tokens used to create the 5 minute cache entry. minimum: 0 - `cache_creation_input_tokens: number` The number of input tokens used to create the cache entry. minimum: 0 - `cache_read_input_tokens: number` The number of input tokens read from the cache. minimum: 0 - `input_tokens: number` The number of input tokens which were used. minimum: 0 - `model: "claude-haiku-5-5" or "claude-sonnet-5-5" or "claude-fable-5-1" or 17 more or string` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-haiku-5-5"` Fastest model for high-volume, real-time tasks - `"claude-sonnet-5-5"` Efficient model for coding and agents - `"claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows - `"claude-opus-5-5"` Powerful intelligence for coding, knowledge work, and long-running agents - `"claude-mythos-5-1"` Our most capable model for cybersecurity and biology research, available through trusted access programs - `"claude-sonnet-5"` Efficient model for coding and agents - `"claude-fable-5"` Next generation of intelligence for the hardest knowledge work and coding problems - `"claude-mythos-5"` Most capable model for cybersecurity and biology research - `"claude-opus-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-8"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-7"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-6"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-6"` Best combination of speed and intelligence - `"claude-haiku-4-5"` - `"claude-haiku-4-5-20251001"` - `"claude-opus-4-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-5-20251101"` Powerful intelligence for long-running agents and coding - `"claude-mythos-preview"` **Deprecated**: Will reach end-of-life on June 30, 2026. Please migrate to claude-mythos-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. New class of intelligence, strongest in coding and cybersecurity - `"claude-sonnet-4-5"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `"claude-sonnet-4-5-20250929"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `output_tokens: number` The number of output tokens which were used. minimum: 0 - `beta_compaction_iteration_usage: object` Token usage for a compaction iteration. - `type: "compaction"` Usage for a compaction iteration - `cache_creation: object` Breakdown of cached tokens by TTL - `ephemeral_1h_input_tokens: number` The number of input tokens used to create the 1 hour cache entry. minimum: 0 - `ephemeral_5m_input_tokens: number` The number of input tokens used to create the 5 minute cache entry. minimum: 0 - `cache_creation_input_tokens: number` The number of input tokens used to create the cache entry. minimum: 0 - `cache_read_input_tokens: number` The number of input tokens read from the cache. minimum: 0 - `input_tokens: number` The number of input tokens which were used. minimum: 0 - `output_tokens: number` The number of output tokens which were used. minimum: 0 - `beta_advisor_message_iteration_usage: object` Token usage for an advisor sub-inference iteration. - `type: "advisor_message"` Usage for an advisor sub-inference iteration - `cache_creation: object` Breakdown of cached tokens by TTL - `ephemeral_1h_input_tokens: number` The number of input tokens used to create the 1 hour cache entry. minimum: 0 - `ephemeral_5m_input_tokens: number` The number of input tokens used to create the 5 minute cache entry. minimum: 0 - `cache_creation_input_tokens: number` The number of input tokens used to create the cache entry. minimum: 0 - `cache_read_input_tokens: number` The number of input tokens read from the cache. minimum: 0 - `input_tokens: number` The number of input tokens which were used. minimum: 0 - `model: "claude-haiku-5-5" or "claude-sonnet-5-5" or "claude-fable-5-1" or 17 more or string` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-haiku-5-5"` Fastest model for high-volume, real-time tasks - `"claude-sonnet-5-5"` Efficient model for coding and agents - `"claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows - `"claude-opus-5-5"` Powerful intelligence for coding, knowledge work, and long-running agents - `"claude-mythos-5-1"` Our most capable model for cybersecurity and biology research, available through trusted access programs - `"claude-sonnet-5"` Efficient model for coding and agents - `"claude-fable-5"` Next generation of intelligence for the hardest knowledge work and coding problems - `"claude-mythos-5"` Most capable model for cybersecurity and biology research - `"claude-opus-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-8"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-7"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-6"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-6"` Best combination of speed and intelligence - `"claude-haiku-4-5"` - `"claude-haiku-4-5-20251001"` - `"claude-opus-4-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-5-20251101"` Powerful intelligence for long-running agents and coding - `"claude-mythos-preview"` **Deprecated**: Will reach end-of-life on June 30, 2026. Please migrate to claude-mythos-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. New class of intelligence, strongest in coding and cybersecurity - `"claude-sonnet-4-5"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `"claude-sonnet-4-5-20250929"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `output_tokens: number` The number of output tokens which were used. minimum: 0 - `beta_fallback_message_iteration_usage: object` Token usage for the fallback-model attempt of a server-side fallback request. The terminal entry of a fallback-served turn: when a fallback hop's output is the returned message, the entry for the iteration that completed it carries this type in place of `message`. A declined hop and the serving hop's earlier tool-loop iterations produce `message` entries. Whether a fallback model served the response is signalled by the presence of this entry in `usage.iterations`. - `type: "fallback_message"` Usage for the fallback-model attempt that served the response - `cache_creation: object` Breakdown of cached tokens by TTL - `ephemeral_1h_input_tokens: number` The number of input tokens used to create the 1 hour cache entry. minimum: 0 - `ephemeral_5m_input_tokens: number` The number of input tokens used to create the 5 minute cache entry. minimum: 0 - `cache_creation_input_tokens: number` The number of input tokens used to create the cache entry. minimum: 0 - `cache_read_input_tokens: number` The number of input tokens read from the cache. minimum: 0 - `input_tokens: number` The number of input tokens which were used. minimum: 0 - `model: "claude-haiku-5-5" or "claude-sonnet-5-5" or "claude-fable-5-1" or 17 more or string` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-haiku-5-5"` Fastest model for high-volume, real-time tasks - `"claude-sonnet-5-5"` Efficient model for coding and agents - `"claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows - `"claude-opus-5-5"` Powerful intelligence for coding, knowledge work, and long-running agents - `"claude-mythos-5-1"` Our most capable model for cybersecurity and biology research, available through trusted access programs - `"claude-sonnet-5"` Efficient model for coding and agents - `"claude-fable-5"` Next generation of intelligence for the hardest knowledge work and coding problems - `"claude-mythos-5"` Most capable model for cybersecurity and biology research - `"claude-opus-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-8"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-7"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-6"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-6"` Best combination of speed and intelligence - `"claude-haiku-4-5"` - `"claude-haiku-4-5-20251001"` - `"claude-opus-4-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-5-20251101"` Powerful intelligence for long-running agents and coding - `"claude-mythos-preview"` **Deprecated**: Will reach end-of-life on June 30, 2026. Please migrate to claude-mythos-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. New class of intelligence, strongest in coding and cybersecurity - `"claude-sonnet-4-5"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `"claude-sonnet-4-5-20250929"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `output_tokens: number` The number of output tokens which were used. minimum: 0 - `output_tokens: number` The number of output tokens which were used. minimum: 0 - `output_tokens_details: object` Breakdown of output tokens by category. `output_tokens` remains the inclusive, authoritative total used for billing. This object provides a read-only decomposition for observability — for example, how many of the billed output tokens were spent on internal reasoning that may have been summarized before being returned to you. - `thinking_tokens: number` Number of output tokens the model generated as internal reasoning, including the thinking-block delimiter tokens. Reflects the raw reasoning the model produced, not the (possibly shorter) summarized thinking text returned in the response body. Computed by re-tokenizing the raw reasoning text, so it may differ from the model's exact generation count by a small number of tokens. Always ≤ `output_tokens`; `output_tokens - thinking_tokens` approximates the non-reasoning output. minimum: 0 - `server_tool_use: object` The number of server tool requests. - `web_fetch_requests: number` The number of web fetch tool requests. minimum: 0 - `web_search_requests: number` The number of web search tool requests. minimum: 0 - `service_tier: "standard" or "priority" or "batch"` If the request used the priority, standard, or batch tier. - `"standard"` - `"priority"` - `"batch"` - `speed: "standard" or "fast"` The inference speed mode used for this request. - `"standard"` - `"fast"` - `input_transformations: optional array of BetaInputTransformation` Changes the API made to the request's input before showing it to the model, and blocks that failed a binding check but were left unchanged: one entry per block, in request order. Two entry types today. `thinking_dropped` — a `thinking`, `redacted_thinking` or `connector_text` block from the request's `messages` that was removed from the prompt instead of being shown to the model because it failed a binding check. `thinking_mismatch_allowed` — a `thinking` or `redacted_thinking` block that failed the conversation check (the conversation before it differs from the one it was created in, or it carries no record of one on a model that requires it) and was shown to the model all the same, because that check is not enforced for this request. More entry types may be added over time; ignore types you do not recognize. Requires `anthropic-beta: thinking-binding-controls-2026-08-01`. Present on every such response from a model that supports extended thinking, as `[]` when there is no entry to report; without the beta, blocks are removed or left in place all the same but nothing is reported. Removed blocks contribute nothing to `usage.input_tokens`; blocks left in place count as sent. When streaming, the array is final in `message_start`; the final `message_delta` event carries it only when a server-side model fallback happened mid-stream, in which case it holds the serving model's entries and replaces the one in `message_start`. - `beta_thinking_dropped_input_transformation: object` - `type: "thinking_dropped"` Always `thinking_dropped` for this entry type. - `path: string` Where the removed block was in your request, as `messages.{i}.content.{j}`: `i` indexes the `messages` array you sent and `j` that message's `content` array — the same form error messages use. - `reason: "model_binding_mismatch" or "prefix_binding_mismatch" or "organization_binding_mismatch" or "end_user_binding_mismatch"` Which binding check removed the block: `model_binding_mismatch` — it was created by a model whose reasoning the requested model may not read; `prefix_binding_mismatch` — the conversation before it differs from the conversation it was created in (the rest of that turn's consecutive thinking blocks are removed with it, each with this reason); `organization_binding_mismatch` — it was created under a different organization (an Anthropic organization, AWS account or Google Cloud project) and this organization is not one of its additional organizations; `end_user_binding_mismatch` — it was created for a different end user, or was removed by the consumer-organization binding. A block that would fail several checks reports one reason, in this order of precedence: `organization_binding_mismatch`, `end_user_binding_mismatch`, `model_binding_mismatch`, `prefix_binding_mismatch`. - `"model_binding_mismatch"` - `"prefix_binding_mismatch"` - `"organization_binding_mismatch"` - `"end_user_binding_mismatch"` - `beta_thinking_mismatch_allowed_input_transformation: object` - `type: "thinking_mismatch_allowed"` Always `thinking_mismatch_allowed` for this entry type. - `path: string` Where the block is in your request, as `messages.{i}.content.{j}`: `i` indexes the `messages` array you sent and `j` that message's `content` array — the same form error messages use. - `reason: "model_binding_mismatch" or "prefix_binding_mismatch" or "organization_binding_mismatch" or "end_user_binding_mismatch"` Which binding check the block failed; the block was shown to the model all the same. Always `prefix_binding_mismatch` today — the conversation before the block differs from the conversation it was created in, or the block carries no record of one on a model that requires it. Were the check enforced for this request, the block would have been removed or the request rejected (`thinking.block_binding.prefix_mismatch_behavior`). A removal also takes the rest of that turn's consecutive thinking blocks, whereas here each block is checked on its own, so `thinking_mismatch_allowed` entries are a lower bound on what enforcement would remove. - `"model_binding_mismatch"` - `"prefix_binding_mismatch"` - `"organization_binding_mismatch"` - `"end_user_binding_mismatch"` ### Beta Message Delta Usage - `beta_message_delta_usage: object` - `cache_creation_input_tokens: number` The cumulative number of input tokens used to create the cache entry. minimum: 0 - `cache_read_input_tokens: number` The cumulative number of input tokens read from the cache. minimum: 0 - `fallback_credit: object` Outcome of the `fallback_credit_token` presented on this request. Present on every response to a non-batch request that carried a `fallback_credit_token`, in either redemption mode; absent otherwise (batch items accept and ignore the token and carry no outcome object). - `status: BetaFallbackCreditRedeemed or BetaFallbackCreditNotApplied` Whether the fallback-credit reprice was applied to this response's billing. A union discriminated on `type`. `redeemed`: the retry is billed as if the conversation had been on the retry model all along — including when the resulting shift is zero because there was nothing to move. `not_applied`: no reprice was applied; the arm's `reason` says why. - `beta_fallback_credit_redeemed: object` The reprice was applied: the retry is billed as if the conversation had been on the retry model all along. - `type: "redeemed"` - `beta_fallback_credit_not_applied: object` No reprice was applied; `reason` says why. - `type: "not_applied"` - `reason: "body_mismatch" or "continuation_excluded" or "continuation_only" or 9 more` Why the reprice was not applied. A closed enum; additions to the redemption-check vocabulary arrive as deliberate schema updates. - `"body_mismatch"` - `"continuation_excluded"` - `"continuation_only"` - `"expired"` - `"invalid_target_model"` - `"not_enabled"` - `"reprice_unavailable"` - `"temporarily_unavailable"` - `"variant_fields_present"` - `"wrong_organization"` - `"wrong_platform"` - `"wrong_workspace"` - `remove_to_redeem: optional array of string` Request fields to remove before retrying, so the retry can redeem this token. Present exactly when `reason` is `variant_fields_present` — never null, never an empty array; absent otherwise. Fields are named only from your own request, and only after the sealed variant hash matched. A served best-effort retry has already been billed at normal price; nothing redeems retroactively, but a corrected re-send inside the token's five-minute window can still redeem. - `input_tokens: number` The cumulative number of input tokens which were used. minimum: 0 - `iterations: array of BetaMessageIterationUsage or BetaCompactionIterationUsage or BetaAdvisorMessageIterationUsage or BetaFallbackMessageIterationUsage` Per-iteration token usage breakdown. Each entry represents one sampling iteration, with its own input/output token counts and cache statistics, discriminated by `type`. For `message` entries (model sampling iterations, such as the turns of a server-side tool use loop), this allows you to: - Calculate the context window size from the last `message` entry - Understand token accumulation across server-side tool use loops A `compaction` entry reports the token usage of the compaction operation itself — the server-side request that summarizes the context being closed — NOT the size of the context that was compacted away, and its token counts can be much smaller than that closed context (for example, a compaction that closes a ~200k-token context can report only a few thousand tokens). Do not derive the context window size from a `compaction` entry, even when it is the last entry. A `compaction` entry's tokens are not included in the top-level `usage` fields. When an input-token trigger is in effect (the default — 150,000 tokens unless configured otherwise), each `compaction` entry closes a context that had reached at least that threshold, though the context can exceed it by the final iteration's output and tool results. - `beta_message_iteration_usage: object` Token usage for a sampling iteration. - `type: "message"` Usage for a sampling iteration - `cache_creation: object` Breakdown of cached tokens by TTL - `ephemeral_1h_input_tokens: number` The number of input tokens used to create the 1 hour cache entry. minimum: 0 - `ephemeral_5m_input_tokens: number` The number of input tokens used to create the 5 minute cache entry. minimum: 0 - `cache_creation_input_tokens: number` The number of input tokens used to create the cache entry. minimum: 0 - `cache_read_input_tokens: number` The number of input tokens read from the cache. minimum: 0 - `input_tokens: number` The number of input tokens which were used. minimum: 0 - `model: "claude-haiku-5-5" or "claude-sonnet-5-5" or "claude-fable-5-1" or 17 more or string` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-haiku-5-5"` Fastest model for high-volume, real-time tasks - `"claude-sonnet-5-5"` Efficient model for coding and agents - `"claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows - `"claude-opus-5-5"` Powerful intelligence for coding, knowledge work, and long-running agents - `"claude-mythos-5-1"` Our most capable model for cybersecurity and biology research, available through trusted access programs - `"claude-sonnet-5"` Efficient model for coding and agents - `"claude-fable-5"` Next generation of intelligence for the hardest knowledge work and coding problems - `"claude-mythos-5"` Most capable model for cybersecurity and biology research - `"claude-opus-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-8"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-7"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-6"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-6"` Best combination of speed and intelligence - `"claude-haiku-4-5"` - `"claude-haiku-4-5-20251001"` - `"claude-opus-4-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-5-20251101"` Powerful intelligence for long-running agents and coding - `"claude-mythos-preview"` **Deprecated**: Will reach end-of-life on June 30, 2026. Please migrate to claude-mythos-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. New class of intelligence, strongest in coding and cybersecurity - `"claude-sonnet-4-5"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `"claude-sonnet-4-5-20250929"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `output_tokens: number` The number of output tokens which were used. minimum: 0 - `beta_compaction_iteration_usage: object` Token usage for a compaction iteration. - `type: "compaction"` Usage for a compaction iteration - `cache_creation: object` Breakdown of cached tokens by TTL - `ephemeral_1h_input_tokens: number` The number of input tokens used to create the 1 hour cache entry. minimum: 0 - `ephemeral_5m_input_tokens: number` The number of input tokens used to create the 5 minute cache entry. minimum: 0 - `cache_creation_input_tokens: number` The number of input tokens used to create the cache entry. minimum: 0 - `cache_read_input_tokens: number` The number of input tokens read from the cache. minimum: 0 - `input_tokens: number` The number of input tokens which were used. minimum: 0 - `output_tokens: number` The number of output tokens which were used. minimum: 0 - `beta_advisor_message_iteration_usage: object` Token usage for an advisor sub-inference iteration. - `type: "advisor_message"` Usage for an advisor sub-inference iteration - `cache_creation: object` Breakdown of cached tokens by TTL - `ephemeral_1h_input_tokens: number` The number of input tokens used to create the 1 hour cache entry. minimum: 0 - `ephemeral_5m_input_tokens: number` The number of input tokens used to create the 5 minute cache entry. minimum: 0 - `cache_creation_input_tokens: number` The number of input tokens used to create the cache entry. minimum: 0 - `cache_read_input_tokens: number` The number of input tokens read from the cache. minimum: 0 - `input_tokens: number` The number of input tokens which were used. minimum: 0 - `model: "claude-haiku-5-5" or "claude-sonnet-5-5" or "claude-fable-5-1" or 17 more or string` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-haiku-5-5"` Fastest model for high-volume, real-time tasks - `"claude-sonnet-5-5"` Efficient model for coding and agents - `"claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows - `"claude-opus-5-5"` Powerful intelligence for coding, knowledge work, and long-running agents - `"claude-mythos-5-1"` Our most capable model for cybersecurity and biology research, available through trusted access programs - `"claude-sonnet-5"` Efficient model for coding and agents - `"claude-fable-5"` Next generation of intelligence for the hardest knowledge work and coding problems - `"claude-mythos-5"` Most capable model for cybersecurity and biology research - `"claude-opus-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-8"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-7"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-6"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-6"` Best combination of speed and intelligence - `"claude-haiku-4-5"` - `"claude-haiku-4-5-20251001"` - `"claude-opus-4-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-5-20251101"` Powerful intelligence for long-running agents and coding - `"claude-mythos-preview"` **Deprecated**: Will reach end-of-life on June 30, 2026. Please migrate to claude-mythos-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. New class of intelligence, strongest in coding and cybersecurity - `"claude-sonnet-4-5"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `"claude-sonnet-4-5-20250929"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `output_tokens: number` The number of output tokens which were used. minimum: 0 - `beta_fallback_message_iteration_usage: object` Token usage for the fallback-model attempt of a server-side fallback request. The terminal entry of a fallback-served turn: when a fallback hop's output is the returned message, the entry for the iteration that completed it carries this type in place of `message`. A declined hop and the serving hop's earlier tool-loop iterations produce `message` entries. Whether a fallback model served the response is signalled by the presence of this entry in `usage.iterations`. - `type: "fallback_message"` Usage for the fallback-model attempt that served the response - `cache_creation: object` Breakdown of cached tokens by TTL - `ephemeral_1h_input_tokens: number` The number of input tokens used to create the 1 hour cache entry. minimum: 0 - `ephemeral_5m_input_tokens: number` The number of input tokens used to create the 5 minute cache entry. minimum: 0 - `cache_creation_input_tokens: number` The number of input tokens used to create the cache entry. minimum: 0 - `cache_read_input_tokens: number` The number of input tokens read from the cache. minimum: 0 - `input_tokens: number` The number of input tokens which were used. minimum: 0 - `model: "claude-haiku-5-5" or "claude-sonnet-5-5" or "claude-fable-5-1" or 17 more or string` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-haiku-5-5"` Fastest model for high-volume, real-time tasks - `"claude-sonnet-5-5"` Efficient model for coding and agents - `"claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows - `"claude-opus-5-5"` Powerful intelligence for coding, knowledge work, and long-running agents - `"claude-mythos-5-1"` Our most capable model for cybersecurity and biology research, available through trusted access programs - `"claude-sonnet-5"` Efficient model for coding and agents - `"claude-fable-5"` Next generation of intelligence for the hardest knowledge work and coding problems - `"claude-mythos-5"` Most capable model for cybersecurity and biology research - `"claude-opus-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-8"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-7"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-6"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-6"` Best combination of speed and intelligence - `"claude-haiku-4-5"` - `"claude-haiku-4-5-20251001"` - `"claude-opus-4-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-5-20251101"` Powerful intelligence for long-running agents and coding - `"claude-mythos-preview"` **Deprecated**: Will reach end-of-life on June 30, 2026. Please migrate to claude-mythos-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. New class of intelligence, strongest in coding and cybersecurity - `"claude-sonnet-4-5"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `"claude-sonnet-4-5-20250929"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `output_tokens: number` The number of output tokens which were used. minimum: 0 - `output_tokens: number` The cumulative number of output tokens which were used. - `output_tokens_details: object` Breakdown of output tokens by category. `output_tokens` remains the inclusive, authoritative total used for billing. This object provides a read-only decomposition for observability — for example, how many of the billed output tokens were spent on internal reasoning that may have been summarized before being returned to you. - `thinking_tokens: number` Number of output tokens the model generated as internal reasoning, including the thinking-block delimiter tokens. Reflects the raw reasoning the model produced, not the (possibly shorter) summarized thinking text returned in the response body. Computed by re-tokenizing the raw reasoning text, so it may differ from the model's exact generation count by a small number of tokens. Always ≤ `output_tokens`; `output_tokens - thinking_tokens` approximates the non-reasoning output. minimum: 0 - `server_tool_use: object` The number of server tool requests. - `web_fetch_requests: number` The number of web fetch tool requests. minimum: 0 - `web_search_requests: number` The number of web search tool requests. minimum: 0 ### Beta Message Iteration Usage - `beta_message_iteration_usage: object` Token usage for a sampling iteration. - `type: "message"` Usage for a sampling iteration - `cache_creation: object` Breakdown of cached tokens by TTL - `ephemeral_1h_input_tokens: number` The number of input tokens used to create the 1 hour cache entry. minimum: 0 - `ephemeral_5m_input_tokens: number` The number of input tokens used to create the 5 minute cache entry. minimum: 0 - `cache_creation_input_tokens: number` The number of input tokens used to create the cache entry. minimum: 0 - `cache_read_input_tokens: number` The number of input tokens read from the cache. minimum: 0 - `input_tokens: number` The number of input tokens which were used. minimum: 0 - `model: "claude-haiku-5-5" or "claude-sonnet-5-5" or "claude-fable-5-1" or 17 more or string` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-haiku-5-5"` Fastest model for high-volume, real-time tasks - `"claude-sonnet-5-5"` Efficient model for coding and agents - `"claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows - `"claude-opus-5-5"` Powerful intelligence for coding, knowledge work, and long-running agents - `"claude-mythos-5-1"` Our most capable model for cybersecurity and biology research, available through trusted access programs - `"claude-sonnet-5"` Efficient model for coding and agents - `"claude-fable-5"` Next generation of intelligence for the hardest knowledge work and coding problems - `"claude-mythos-5"` Most capable model for cybersecurity and biology research - `"claude-opus-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-8"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-7"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-6"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-6"` Best combination of speed and intelligence - `"claude-haiku-4-5"` - `"claude-haiku-4-5-20251001"` - `"claude-opus-4-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-5-20251101"` Powerful intelligence for long-running agents and coding - `"claude-mythos-preview"` **Deprecated**: Will reach end-of-life on June 30, 2026. Please migrate to claude-mythos-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. New class of intelligence, strongest in coding and cybersecurity - `"claude-sonnet-4-5"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `"claude-sonnet-4-5-20250929"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `output_tokens: number` The number of output tokens which were used. minimum: 0 ### Beta Message Param - `beta_message_param: object` - `content: array of BetaContentBlockParam` - `beta_text_block_param: object` - `type: "text"` - `text: string` minLength: 1 - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `"5m"` - `"1h"` - `citations: optional array of BetaTextCitationParam` - `beta_citation_char_location_param: object` - `type: "char_location"` - `cited_text: string` - `document_index: number` minimum: 0 - `document_title: string` minLength: 1, maxLength: 500 - `end_char_index: number` - `start_char_index: number` minimum: 0 - `beta_citation_page_location_param: object` - `type: "page_location"` - `cited_text: string` - `document_index: number` minimum: 0 - `document_title: string` minLength: 1, maxLength: 500 - `end_page_number: number` - `start_page_number: number` minimum: 1 - `beta_citation_content_block_location_param: object` - `type: "content_block_location"` - `cited_text: string` The full text of the cited block range, concatenated. Always equals the contents of `content[start_block_index:end_block_index]` joined together. The text block is the minimal citable unit; this field is never a substring of a single block. Not counted toward output tokens, and not counted toward input tokens when sent back in subsequent turns. - `document_index: number` minimum: 0 - `document_title: string` minLength: 1, maxLength: 500 - `end_block_index: number` Exclusive 0-based end index of the cited block range in the source's `content` array. Always greater than `start_block_index`; a single-block citation has `end_block_index = start_block_index + 1`. - `start_block_index: number` 0-based index of the first cited block in the source's `content` array. minimum: 0 - `beta_citation_web_search_result_location_param: object` - `type: "web_search_result_location"` - `cited_text: string` - `encrypted_index: string` - `title: string` minLength: 1, maxLength: 512 - `url: string` minLength: 1 - `beta_citation_search_result_location_param: object` - `type: "search_result_location"` - `cited_text: string` The full text of the cited block range, concatenated. Always equals the contents of `content[start_block_index:end_block_index]` joined together. The text block is the minimal citable unit; this field is never a substring of a single block. Not counted toward output tokens, and not counted toward input tokens when sent back in subsequent turns. - `end_block_index: number` Exclusive 0-based end index of the cited block range in the source's `content` array. Always greater than `start_block_index`; a single-block citation has `end_block_index = start_block_index + 1`. - `search_result_index: number` 0-based index of the cited search result among all `search_result` content blocks in the request, in the order they appear across messages and tool results. Counted separately from `document_index`; server-side web search results are not included in this count. minimum: 0 - `source: string` - `start_block_index: number` 0-based index of the first cited block in the source's `content` array. minimum: 0 - `title: string` - `beta_image_block_param: object` - `type: "image"` - `source: BetaBase64ImageSource or BetaURLImageSource or BetaFileImageSource` - `beta_base64_image_source: object` - `type: "base64"` - `data: string` format: byte - `media_type: "image/jpeg" or "image/png" or "image/gif" or "image/webp"` - `"image/jpeg"` - `"image/png"` - `"image/gif"` - `"image/webp"` - `beta_url_image_source: object` - `type: "url"` - `url: string` - `beta_file_image_source: object` - `type: "file"` - `file_id: string` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `transformations: optional object` Configures the transformations the server applies to this image before the model observes it. Each key names a condition the server transforms images for; its value selects the transformation applied. Omitted keys keep their default behavior, and an empty object is equivalent to omitting the field. - `oversized_image: optional "downsize" or "error"` What the server does when this image exceeds the model's maximum image size. `"downsize"` (the default) scales the image down to fit, which changes the dimensions the model observes without telling you. `"error"` instead rejects the request with a 400 error naming the image's dimensions and the largest dimensions that fit, so you can scale the image deliberately — your image is never silently scaled down. - `"downsize"` - `"error"` - `beta_request_document_block: object` - `type: "document"` - `source: BetaBase64PDFSource or BetaPlainTextSource or BetaContentBlockSource or 2 more` - `beta_base64_pdf_source: object` - `type: "base64"` - `data: string` format: byte - `media_type: "application/pdf"` - `beta_plain_text_source: object` - `type: "text"` - `data: string` - `media_type: "text/plain"` - `beta_content_block_source: object` - `type: "content"` - `content: string or array of BetaContentBlockSourceContent` - `union_member_0: string` - `beta_content_block_source_content: array of BetaContentBlockSourceContent` - `beta_text_block_param: object` - `type: "text"` - `text: string` minLength: 1 - `cache_control: optional object` Create a cache control breakpoint at this content block. - `citations: optional array of BetaTextCitationParam` - `beta_image_block_param: object` - `type: "image"` - `source: BetaBase64ImageSource or BetaURLImageSource or BetaFileImageSource` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `transformations: optional object` Configures the transformations the server applies to this image before the model observes it. Each key names a condition the server transforms images for; its value selects the transformation applied. Omitted keys keep their default behavior, and an empty object is equivalent to omitting the field. - `beta_url_pdf_source: object` - `type: "url"` - `url: string` - `beta_file_document_source: object` - `type: "file"` - `file_id: string` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `citations: optional object` - `enabled: optional boolean` - `context: optional string` minLength: 1 - `title: optional string` minLength: 1, maxLength: 500 - `beta_search_result_block_param: object` - `type: "search_result"` - `content: array of BetaTextBlockParam` - `type: "text"` - `text: string` minLength: 1 - `cache_control: optional object` Create a cache control breakpoint at this content block. - `citations: optional array of BetaTextCitationParam` - `source: string` - `title: string` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `citations: optional object` - `enabled: optional boolean` - `beta_thinking_block_param: object` - `type: "thinking"` - `signature: string` The `signature` value of this thinking block, exactly as returned by the API in a previous response. Used to verify that the block was generated by Claude. Thinking blocks must be passed back unmodified and in their original order; a modified block results in a 400 `invalid_request_error`. - `thinking: string` The `thinking` text of this block as returned by the API. - `beta_redacted_thinking_block_param: object` - `type: "redacted_thinking"` - `data: string` The `data` value of this redacted thinking block, exactly as returned by the API in a previous response. Opaque and encrypted; pass it back unchanged. - `beta_tool_use_block_param: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: map[unknown]` - `name: string` minLength: 1, maxLength: 200 - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` - `beta_direct_caller: object` Tool invocation directly from the model. - `type: "direct"` - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `type: "code_execution_20250825"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `beta_server_tool_caller_20260120: object` - `type: "code_execution_20260120"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `toolset_name: optional string` For a toolset member tool_use, the toolset family this member belongs to. minLength: 1, maxLength: 64, pattern: ^[a-zA-Z0-9_-]+$ - `beta_tool_result_block_param: object` - `type: "tool_result"` - `tool_use_id: string` pattern: ^[a-zA-Z0-9_-]+$ - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `content: optional array of BetaTextBlockParam or BetaImageBlockParam or BetaSearchResultBlockParam or 3 more` - `beta_text_block_param: object` - `type: "text"` - `text: string` minLength: 1 - `cache_control: optional object` Create a cache control breakpoint at this content block. - `citations: optional array of BetaTextCitationParam` - `beta_image_block_param: object` - `type: "image"` - `source: BetaBase64ImageSource or BetaURLImageSource or BetaFileImageSource` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `transformations: optional object` Configures the transformations the server applies to this image before the model observes it. Each key names a condition the server transforms images for; its value selects the transformation applied. Omitted keys keep their default behavior, and an empty object is equivalent to omitting the field. - `beta_search_result_block_param: object` - `type: "search_result"` - `content: array of BetaTextBlockParam` - `source: string` - `title: string` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `citations: optional object` - `beta_request_document_block: object` - `type: "document"` - `source: BetaBase64PDFSource or BetaPlainTextSource or BetaContentBlockSource or 2 more` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `citations: optional object` - `context: optional string` minLength: 1 - `title: optional string` minLength: 1, maxLength: 500 - `beta_tool_reference_block_param: object` Tool reference block that can be included in tool_result content. - `type: "tool_reference"` - `tool_name: string` minLength: 1, maxLength: 256, pattern: ^[a-zA-Z0-9_-]{1,256}$ - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `beta_browser_state_block_param: object` The caller's browser state after a browser toolset member call — the full inventory of open tabs, which tab is active, and any side effects (tabs opened, download state changes) the call produced. At most one per `tool_result`, only on a non-error result answering a browser toolset member `tool_use`. The server renders the model-visible text from it; the model never sees the raw fields. - `type: "browser_state"` - `tabs: array of BetaBrowserStateTabEntry` All tabs open in the browser after this call — the full inventory, not a delta. May be empty. Whenever non-empty, exactly one entry carries `active: true`. maxItems: 100 - `tab_id: string` The caller-assigned identifier for this tab, unique within the inventory. minLength: 1, maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `title: string` The title of the page the tab is showing. May be empty. maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `url: string` The URL of the page the tab is showing. May be empty. maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `active: optional boolean` Whether this tab is the active tab after this call. Whenever `tabs` is non-empty, exactly one entry is marked `active: true`. - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `state_changes: optional array of BetaBrowserStateChange` Tabs opened and download state changes during this call. "Nothing to report" is expressed by omitting the field, never by an empty list. minItems: 1, maxItems: 200 - `beta_browser_state_change_tab_opened: object` A tab this call's execution opened that remains open at its end — the creation delta of the `tabs` inventory, not an event log. Carries only the `tab_id`; the tab's `title` and `url` live on its `tabs` entry, which must include the same `tab_id`. A tab opened during a failed call gets no deferred `tab_opened`; it simply appears in the next result's `tabs` inventory. - `type: "tab_opened"` - `tab_id: string` The `tab_id` of the opened tab, present in `tabs`. minLength: 1, maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `beta_browser_state_change_download_started: object` A file download that started during this call. - `type: "download_started"` - `download_id: string` The caller-assigned identifier for this download, stable across the state changes reporting it. minLength: 1, maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `url: string` The final post-redirect URL the download was served from. maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `beta_browser_state_change_download_completed: object` A file download that finished during this call, reported with the same `download_id` as its `download_started` — or without a prior `download_started`, when the download finished during the call that started it (at most one state change per `download_id` per result). - `type: "download_completed"` - `download_id: string` The caller-assigned identifier for this download, stable across the state changes reporting it. minLength: 1, maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `url: string` The final post-redirect URL the download was served from. maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `path: optional string` Where the executor saved the file, on the executor's filesystem. Only included when another tool in the same environment can read the file at that path. maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `size_bytes: optional number` The completed download's size. minimum: 0 - `beta_browser_state_change_download_failed: object` A file download that failed — or was cancelled — during this call. - `type: "download_failed"` - `download_id: string` The caller-assigned identifier for this download, stable across the state changes reporting it. minLength: 1, maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `url: string` The final post-redirect URL the download was served from. maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `error: optional string` The failure or cancellation detail, when known. maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `is_error: optional boolean` - `toolset_name: optional string` For a toolset member tool_result, the toolset family of the paired tool_use. minLength: 1, maxLength: 64, pattern: ^[a-zA-Z0-9_-]+$ - `beta_server_tool_use_block_param: object` - `type: "server_tool_use"` - `id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `input: map[unknown]` - `name: "advisor" or "web_search" or "web_fetch" or 5 more` - `"advisor"` - `"web_search"` - `"web_fetch"` - `"code_execution"` - `"bash_code_execution"` - `"text_editor_code_execution"` - `"tool_search_tool_regex"` - `"tool_search_tool_bm25"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` - `beta_direct_caller: object` Tool invocation directly from the model. - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `beta_server_tool_caller_20260120: object` - `beta_web_search_tool_result_block_param: object` - `type: "web_search_tool_result"` - `content: array of BetaWebSearchResultBlockParam or BetaWebSearchToolRequestError` - `Result Block: array of BetaWebSearchResultBlockParam` - `type: "web_search_result"` - `encrypted_content: string` - `title: string` - `url: string` - `page_age: optional string` - `beta_web_search_tool_request_error: object` - `type: "web_search_tool_result_error"` - `error_code: "invalid_tool_input" or "unavailable" or "max_uses_exceeded" or 3 more` - `"invalid_tool_input"` - `"unavailable"` - `"max_uses_exceeded"` - `"too_many_requests"` - `"query_too_long"` - `"request_too_large"` - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` - `beta_direct_caller: object` Tool invocation directly from the model. - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `beta_server_tool_caller_20260120: object` - `beta_web_fetch_tool_result_block_param: object` - `type: "web_fetch_tool_result"` - `content: BetaWebFetchToolResultErrorBlockParam or BetaWebFetchBlockParam` - `beta_web_fetch_tool_result_error_block_param: object` - `type: "web_fetch_tool_result_error"` - `error_code: "invalid_tool_input" or "url_too_long" or "url_not_allowed" or 7 more` - `"invalid_tool_input"` - `"url_too_long"` - `"url_not_allowed"` - `"url_not_in_prior_context"` - `"url_not_accessible"` - `"unsupported_content_type"` - `"too_many_requests"` - `"max_uses_exceeded"` - `"unavailable"` - `"content_too_large"` - `beta_web_fetch_block_param: object` - `type: "web_fetch_result"` - `content: object` - `type: "document"` - `source: BetaBase64PDFSource or BetaPlainTextSource or BetaContentBlockSource or 2 more` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `citations: optional object` - `context: optional string` minLength: 1 - `title: optional string` minLength: 1, maxLength: 500 - `url: string` Fetched content URL - `retrieved_at: optional string` ISO 8601 timestamp when the content was retrieved - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` - `beta_direct_caller: object` Tool invocation directly from the model. - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `beta_server_tool_caller_20260120: object` - `beta_advisor_tool_result_block_param: object` - `type: "advisor_tool_result"` - `content: BetaAdvisorToolResultErrorParam or BetaAdvisorResultBlockParam or BetaAdvisorRedactedResultBlockParam` - `beta_advisor_tool_result_error_param: object` - `type: "advisor_tool_result_error"` - `error_code: "max_uses_exceeded" or "prompt_too_long" or "too_many_requests" or 4 more` - `"max_uses_exceeded"` - `"prompt_too_long"` - `"too_many_requests"` - `"overloaded"` - `"unavailable"` - `"execution_time_exceeded"` - `"model_not_found"` - `beta_advisor_result_block_param: object` - `type: "advisor_result"` - `text: string` - `stop_reason: optional string` - `beta_advisor_redacted_result_block_param: object` - `type: "advisor_redacted_result"` - `encrypted_content: string` Opaque blob produced by a prior response; must be round-tripped verbatim. - `stop_reason: optional string` - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `beta_code_execution_tool_result_block_param: object` - `type: "code_execution_tool_result"` - `content: BetaCodeExecutionToolResultErrorParam or BetaCodeExecutionResultBlockParam or BetaEncryptedCodeExecutionResultBlockParam` - `beta_code_execution_tool_result_error_param: object` - `type: "code_execution_tool_result_error"` - `error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or "execution_time_exceeded"` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `beta_code_execution_result_block_param: object` - `type: "code_execution_result"` - `content: array of BetaCodeExecutionOutputBlockParam` - `type: "code_execution_output"` - `file_id: string` - `return_code: number` - `stderr: string` - `stdout: string` - `beta_encrypted_code_execution_result_block_param: object` Code execution result with encrypted stdout for PFC + web_search results. - `type: "encrypted_code_execution_result"` - `content: array of BetaCodeExecutionOutputBlockParam` - `type: "code_execution_output"` - `file_id: string` - `encrypted_stdout: string` - `return_code: number` - `stderr: string` - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `beta_bash_code_execution_tool_result_block_param: object` - `type: "bash_code_execution_tool_result"` - `content: BetaBashCodeExecutionToolResultErrorParam or BetaBashCodeExecutionResultBlockParam` - `beta_bash_code_execution_tool_result_error_param: object` - `type: "bash_code_execution_tool_result_error"` - `error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or 2 more` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `"output_file_too_large"` - `beta_bash_code_execution_result_block_param: object` - `type: "bash_code_execution_result"` - `content: array of BetaBashCodeExecutionOutputBlockParam` - `type: "bash_code_execution_output"` - `file_id: string` - `return_code: number` - `stderr: string` - `stdout: string` - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `beta_text_editor_code_execution_tool_result_block_param: object` - `type: "text_editor_code_execution_tool_result"` - `content: BetaTextEditorCodeExecutionToolResultErrorParam or BetaTextEditorCodeExecutionViewResultBlockParam or BetaTextEditorCodeExecutionCreateResultBlockParam or BetaTextEditorCodeExecutionStrReplaceResultBlockParam` - `beta_text_editor_code_execution_tool_result_error_param: object` - `type: "text_editor_code_execution_tool_result_error"` - `error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or 2 more` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `"file_not_found"` - `error_message: optional string` - `beta_text_editor_code_execution_view_result_block_param: object` - `type: "text_editor_code_execution_view_result"` - `content: string` - `file_type: "text" or "image" or "pdf"` - `"text"` - `"image"` - `"pdf"` - `num_lines: optional number` - `start_line: optional number` - `total_lines: optional number` - `beta_text_editor_code_execution_create_result_block_param: object` - `type: "text_editor_code_execution_create_result"` - `is_file_update: boolean` - `beta_text_editor_code_execution_str_replace_result_block_param: object` - `type: "text_editor_code_execution_str_replace_result"` - `lines: optional array of string` - `new_lines: optional number` - `new_start: optional number` - `old_lines: optional number` - `old_start: optional number` - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `beta_tool_search_tool_result_block_param: object` - `type: "tool_search_tool_result"` - `content: BetaToolSearchToolResultErrorParam or BetaToolSearchToolSearchResultBlockParam` - `beta_tool_search_tool_result_error_param: object` - `type: "tool_search_tool_result_error"` - `error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or "execution_time_exceeded"` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `error_message: optional string` - `beta_tool_search_tool_search_result_block_param: object` - `type: "tool_search_tool_search_result"` - `tool_references: array of BetaToolReferenceBlockParam` - `type: "tool_reference"` - `tool_name: string` minLength: 1, maxLength: 256, pattern: ^[a-zA-Z0-9_-]{1,256}$ - `cache_control: optional object` Create a cache control breakpoint at this content block. - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `beta_mcp_tool_use_block_param: object` - `type: "mcp_tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: map[unknown]` - `name: string` - `server_name: string` The name of the MCP server - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `beta_request_mcp_tool_result_block_param: object` - `type: "mcp_tool_result"` - `tool_use_id: string` pattern: ^[a-zA-Z0-9_-]+$ - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `content: optional string or array of BetaTextBlockParam` - `union_member_0: string` - `beta_mcp_tool_result_block_param_content: array of BetaTextBlockParam` - `type: "text"` - `text: string` minLength: 1 - `cache_control: optional object` Create a cache control breakpoint at this content block. - `citations: optional array of BetaTextCitationParam` - `is_error: optional boolean` - `beta_container_upload_block_param: object` A content block that represents a file to be uploaded to the container Files uploaded via this block will be available in the container's input directory. - `type: "container_upload"` - `file_id: string` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `beta_compaction_block_param: object` A compaction block containing summary of previous context. Users should round-trip these blocks from responses to subsequent requests to maintain context across compaction boundaries. When content is None, the block represents a failed compaction. The server treats these as no-ops. Empty string content is not allowed. - `type: "compaction"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `content: optional string` Summary of previously compacted content, or null if compaction failed - `encrypted_content: optional string` Opaque metadata from prior compaction, to be round-tripped verbatim - `signature: optional string` The block's signature as returned, to be sent back verbatim - `tool_changes: optional array of BetaRequestToolAdditionBlock or BetaRequestToolRemovalBlock` The tool changes of the compacted range, as the server returned them on this block: the `tool_addition` and `tool_removal` entries that take the request's `tools` to the tool set in effect at the end of the range. Send them back unchanged with the block. - `beta_request_tool_addition_block: object` Mid-conversation directive to make a tool available. `tool` is a reference to a tool (or MCP toolset) declared in the request's `tools`. Under the `inline-tools-2026-09-15` beta it may instead be a reference to a tool defined earlier in `messages`, or a `tool_definition` object that carries an inline tool definition in `definition` (the same object a `tools` entry holds). An `mcp_toolset` definition also requires the `mcp-client-2026-09-15` beta. The tool is offered to the model from this point in the conversation onward. - `type: "tool_addition"` - `tool: BetaToolChangeToolReference or BetaToolChangeMCPToolReference or BetaToolChangeMCPToolsetReference or BetaToolChangeToolDefinitionParam` - `beta_tool_change_tool_reference: object` Reference to a single tool, by the name the model uses to call it: a tool declared in `tools` or defined by an earlier `tool_addition` block. Does not accept the composed `{server}_{name}` form the server assigns to MCP-resolved tools; use `mcp_tool_reference` or `mcp_toolset_reference` for those. - `type: "tool_reference"` - `name: string` pattern: ^[a-zA-Z0-9_-]{1,128}$ - `beta_tool_change_mcp_tool_reference: object` Reference to a single MCP tool by its server and remote name; the same `server_name`/`name` pair `mcp_tool_use` carries. - `type: "mcp_tool_reference"` - `name: string` - `server_name: string` - `beta_tool_change_mcp_toolset_reference: object` Reference to every tool in the named MCP server's toolset. - `type: "mcp_toolset_reference"` - `server_name: string` - `beta_tool_change_tool_definition_param: object` A tool defined by value: `definition` is a `tools` entry (any kind `tools` accepts, an MCP toolset included). An `mcp_toolset` given here also requires the `mcp-client-2026-09-15` beta. - `type: "tool_definition"` - `definition: BetaTool or BetaToolBash20241022 or BetaToolBash20250124 or 25 more` - `beta_tool: object` - `type: optional "custom"` - `input_schema: object` [JSON schema](https://json-schema.org/draft/2020-12) for this tool's input. This defines the shape of the `input` that your tool accepts and that the model will produce. - `type: "object"` - `properties: optional map[unknown]` - `required: optional array of string` - `name: string` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. minLength: 1, maxLength: 128, pattern: ^[a-zA-Z0-9_-]{1,128}$ - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `description: optional string` Description of what this tool does. Tool descriptions should be as detailed as possible. The more information that the model has about what the tool is and how to use it, the better it will perform. You can use natural language descriptions to reinforce important aspects of the tool input JSON schema. - `eager_input_streaming: optional boolean` Enable eager input streaming for this tool. When true, tool input parameters will be streamed incrementally as they are generated, and types will be inferred on-the-fly rather than buffering the full JSON output. When false, streaming is disabled for this tool even if the fine-grained-tool-streaming beta is active. When null (default), uses the default behavior based on beta headers. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_bash_20241022: object` - `type: "bash_20241022"` - `name: "bash"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_bash_20250124: object` - `type: "bash_20250124"` - `name: "bash"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_code_execution_tool_20250522: object` - `type: "code_execution_20250522"` - `name: "code_execution"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_code_execution_tool_20250825: object` - `type: "code_execution_20250825"` - `name: "code_execution"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_code_execution_tool_20260120: object` Code execution tool with REPL state persistence (daemon mode + gVisor checkpoint). - `type: "code_execution_20260120"` - `name: "code_execution"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_code_execution_tool_20260521: object` Code execution tool with REPL state persistence. - `type: "code_execution_20260521"` - `name: "code_execution"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_browser_toolset_20260801: object` The browser toolset: a single `tools[]` entry (carrying no `name`) that declares the browser tool family. The model is served the family's tool with any members disabled via `configs` removed from its schema. - `type: "browser_toolset_20260801"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `configs: optional object` Sparse per-member overrides, keyed by member name. Absent, null, and {} are equivalent; a member's defaults apply wherever its key is absent. - `type: optional object` `type`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `close_tab: optional object` `close_tab`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `double_click: optional object` `double_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `file_upload: optional object` `file_upload`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `find: optional object` `find`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `form_input: optional object` `form_input`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `get_page_text: optional object` `get_page_text`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `hold_key: optional object` `hold_key`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `hover: optional object` `hover`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `javascript_exec: optional object` `javascript_exec`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `key: optional object` `key`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_click: optional object` `left_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_click_drag: optional object` `left_click_drag`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_mouse_down: optional object` `left_mouse_down`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_mouse_up: optional object` `left_mouse_up`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `list_tabs: optional object` `list_tabs`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `middle_click: optional object` `middle_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `mouse_move: optional object` `mouse_move`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `navigate: optional object` `navigate`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `new_tab: optional object` `new_tab`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `read_console: optional object` `read_console`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `read_network: optional object` `read_network`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `read_page: optional object` `read_page`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `right_click: optional object` `right_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `screenshot: optional object` `screenshot`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `scroll: optional object` `scroll`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `scroll_to: optional object` `scroll_to`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `switch_tab: optional object` `switch_tab`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `triple_click: optional object` `triple_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `wait: optional object` `wait`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `zoom: optional object` `zoom`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `beta_tool_computer_use_20241022: object` - `type: "computer_20241022"` - `display_height_px: number` The height of the display in pixels. minimum: 1 - `display_width_px: number` The width of the display in pixels. minimum: 1 - `name: "computer"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `display_number: optional number` The X11 display number (e.g. 0, 1) for the display. minimum: 0 - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_memory_tool_20250818: object` - `type: "memory_20250818"` - `name: "memory"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_computer_use_20250124: object` - `type: "computer_20250124"` - `display_height_px: number` The height of the display in pixels. minimum: 1 - `display_width_px: number` The width of the display in pixels. minimum: 1 - `name: "computer"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `display_number: optional number` The X11 display number (e.g. 0, 1) for the display. minimum: 0 - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_text_editor_20241022: object` - `type: "text_editor_20241022"` - `name: "str_replace_editor"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_computer_use_20251124: object` - `type: "computer_20251124"` - `display_height_px: number` The height of the display in pixels. minimum: 1 - `display_width_px: number` The width of the display in pixels. minimum: 1 - `name: "computer"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `display_number: optional number` The X11 display number (e.g. 0, 1) for the display. minimum: 0 - `enable_zoom: optional boolean` Whether to enable an action to take a zoomed-in screenshot of the screen. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_computer_toolset_20260801: object` The computer toolset: a single `tools[]` entry (carrying no `name`) that declares the computer tool family. The model is served the family's tool with any members disabled via `configs` removed from its schema. Every member is enabled by default, zoom included. The single-tool options `display_number` and `enable_zoom` are not fields of a toolset entry — it carries only `type`, `configs`, and `cache_control`; zoom is controlled via `configs.zoom.enabled`. - `type: "computer_toolset_20260801"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `configs: optional object` Sparse per-member overrides, keyed by member name. Absent, null, and {} are equivalent; a member's defaults apply wherever its key is absent. - `type: optional object` `type`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `cursor_position: optional object` `cursor_position`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `double_click: optional object` `double_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `hold_key: optional object` `hold_key`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `key: optional object` `key`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_click: optional object` `left_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_click_drag: optional object` `left_click_drag`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_mouse_down: optional object` `left_mouse_down`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_mouse_up: optional object` `left_mouse_up`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `middle_click: optional object` `middle_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `mouse_move: optional object` `mouse_move`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `right_click: optional object` `right_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `screenshot: optional object` `screenshot`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `scroll: optional object` `scroll`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `triple_click: optional object` `triple_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `wait: optional object` `wait`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `zoom: optional object` `zoom`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `beta_tool_text_editor_20250124: object` - `type: "text_editor_20250124"` - `name: "str_replace_editor"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_text_editor_20250429: object` - `type: "text_editor_20250429"` - `name: "str_replace_based_edit_tool"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_text_editor_20250728: object` - `type: "text_editor_20250728"` - `name: "str_replace_based_edit_tool"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: optional array of map[unknown]` - `max_characters: optional number` Maximum number of characters to display when viewing a file. If not specified, defaults to displaying the full file. minimum: 1 - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_web_search_tool_20250305: object` - `type: "web_search_20250305"` - `name: "web_search"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: optional array of string` If provided, only these domains will be included in results. Cannot be used alongside `blocked_domains`. - `blocked_domains: optional array of string` If provided, these domains will never appear in results. Cannot be used alongside `allowed_domains`. - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `user_location: optional object` Parameters for the user's location. Used to provide more relevant search results. - `type: "approximate"` - `city: optional string` The city of the user. minLength: 1, maxLength: 255 - `country: optional string` The two letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1_alpha-2) of the user. minLength: 2, maxLength: 2 - `region: optional string` The region of the user. minLength: 1, maxLength: 255 - `timezone: optional string` The [IANA timezone](https://nodatime.org/TimeZones) of the user. minLength: 1, maxLength: 255 - `beta_web_fetch_tool_20250910: object` - `type: "web_fetch_20250910"` - `name: "web_fetch"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: optional array of string` List of domains to allow fetching from - `blocked_domains: optional array of string` List of domains to block fetching from - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `citations: optional object` Citations configuration for fetched documents. Citations are disabled by default. - `enabled: optional boolean` - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_content_tokens: optional number` Maximum number of tokens used by including web page text content in the context. The limit is approximate and does not apply to binary content such as PDFs. minimum: 1 - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `url_sources: optional object` Which sources contribute to the set of URLs the tool may fetch. Omitted means every source. - `client_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which client tools' results contribute fetchable URLs: "all", "none", or an only or except list of client tool names from tools[]. - `beta_web_fetch_url_source_all: object` The `url_sources` variant under which a source contributes in full: every result of the tool filter's source, or all user input. - `type: "all"` - `beta_web_fetch_url_source_none: object` The `url_sources` variant under which a source contributes nothing: no result of the tool filter's source, or no user input. - `type: "none"` - `beta_web_fetch_url_source_only: object` The tool filter variant under which only the named tools' results contribute. - `type: "only"` - `tools: array of BetaWebFetchURLSourceToolReference` - `type: "tool_reference"` - `name: string` - `beta_web_fetch_url_source_except: object` The tool filter variant under which every result but the named tools' contributes. - `type: "except"` - `tools: array of BetaWebFetchURLSourceToolReference` - `type: "tool_reference"` - `name: string` - `server_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which server tools' results contribute fetchable URLs: "all", "none", or an only or except list of server tool names from tools[]; only web_search and web_fetch results ever contribute. - `beta_web_fetch_url_source_all: object` The `url_sources` variant under which a source contributes in full: every result of the tool filter's source, or all user input. - `beta_web_fetch_url_source_none: object` The `url_sources` variant under which a source contributes nothing: no result of the tool filter's source, or no user input. - `beta_web_fetch_url_source_only: object` The tool filter variant under which only the named tools' results contribute. - `beta_web_fetch_url_source_except: object` The tool filter variant under which every result but the named tools' contributes. - `user_input: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone` Whether URLs in user messages are fetchable: "all" or "none". - `beta_web_fetch_url_source_all: object` The `url_sources` variant under which a source contributes in full: every result of the tool filter's source, or all user input. - `beta_web_fetch_url_source_none: object` The `url_sources` variant under which a source contributes nothing: no result of the tool filter's source, or no user input. - `beta_web_search_tool_20260209: object` - `type: "web_search_20260209"` - `name: "web_search"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: optional array of string` If provided, only these domains will be included in results. Cannot be used alongside `blocked_domains`. - `blocked_domains: optional array of string` If provided, these domains will never appear in results. Cannot be used alongside `allowed_domains`. - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `user_location: optional object` Parameters for the user's location. Used to provide more relevant search results. - `type: "approximate"` - `city: optional string` The city of the user. minLength: 1, maxLength: 255 - `country: optional string` The two letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1_alpha-2) of the user. minLength: 2, maxLength: 2 - `region: optional string` The region of the user. minLength: 1, maxLength: 255 - `timezone: optional string` The [IANA timezone](https://nodatime.org/TimeZones) of the user. minLength: 1, maxLength: 255 - `beta_web_fetch_tool_20260209: object` - `type: "web_fetch_20260209"` - `name: "web_fetch"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: optional array of string` List of domains to allow fetching from - `blocked_domains: optional array of string` List of domains to block fetching from - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `citations: optional object` Citations configuration for fetched documents. Citations are disabled by default. - `enabled: optional boolean` - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_content_tokens: optional number` Maximum number of tokens used by including web page text content in the context. The limit is approximate and does not apply to binary content such as PDFs. minimum: 1 - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `url_sources: optional object` Which sources contribute to the set of URLs the tool may fetch. Omitted means every source. - `client_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which client tools' results contribute fetchable URLs: "all", "none", or an only or except list of client tool names from tools[]. - `server_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which server tools' results contribute fetchable URLs: "all", "none", or an only or except list of server tool names from tools[]; only web_search and web_fetch results ever contribute. - `user_input: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone` Whether URLs in user messages are fetchable: "all" or "none". - `beta_web_fetch_tool_20260309: object` Web fetch tool with use_cache parameter for bypassing cached content. - `type: "web_fetch_20260309"` - `name: "web_fetch"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: optional array of string` List of domains to allow fetching from - `blocked_domains: optional array of string` List of domains to block fetching from - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `citations: optional object` Citations configuration for fetched documents. Citations are disabled by default. - `enabled: optional boolean` - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_content_tokens: optional number` Maximum number of tokens used by including web page text content in the context. The limit is approximate and does not apply to binary content such as PDFs. minimum: 1 - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `url_sources: optional object` Which sources contribute to the set of URLs the tool may fetch. Omitted means every source. - `client_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which client tools' results contribute fetchable URLs: "all", "none", or an only or except list of client tool names from tools[]. - `server_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which server tools' results contribute fetchable URLs: "all", "none", or an only or except list of server tool names from tools[]; only web_search and web_fetch results ever contribute. - `user_input: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone` Whether URLs in user messages are fetchable: "all" or "none". - `use_cache: optional boolean` Whether to use cached content. Set to false to bypass the cache and fetch fresh content. Only set to false when the user explicitly requests fresh content or when fetching rapidly-changing sources. - `beta_web_search_tool_20260318: object` - `type: "web_search_20260318"` - `name: "web_search"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: optional array of string` If provided, only these domains will be included in results. Cannot be used alongside `blocked_domains`. - `blocked_domains: optional array of string` If provided, these domains will never appear in results. Cannot be used alongside `allowed_domains`. - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `response_inclusion: optional "full" or "excluded"` How this tool's result blocks appear in the API response when the result was consumed by a completed code_execution call in the same turn. 'full' returns the complete content (default). 'excluded' drops the nested server_tool_use and result block pair entirely. Results from direct calls, or from code_execution calls that paused before completing, are always returned in full so they can be sent back on the next turn. - `"full"` - `"excluded"` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `user_location: optional object` Parameters for the user's location. Used to provide more relevant search results. - `type: "approximate"` - `city: optional string` The city of the user. minLength: 1, maxLength: 255 - `country: optional string` The two letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1_alpha-2) of the user. minLength: 2, maxLength: 2 - `region: optional string` The region of the user. minLength: 1, maxLength: 255 - `timezone: optional string` The [IANA timezone](https://nodatime.org/TimeZones) of the user. minLength: 1, maxLength: 255 - `beta_web_fetch_tool_20260318: object` - `type: "web_fetch_20260318"` - `name: "web_fetch"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: optional array of string` List of domains to allow fetching from - `blocked_domains: optional array of string` List of domains to block fetching from - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `citations: optional object` Citations configuration for fetched documents. Citations are disabled by default. - `enabled: optional boolean` - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_content_tokens: optional number` Maximum number of tokens used by including web page text content in the context. The limit is approximate and does not apply to binary content such as PDFs. minimum: 1 - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `response_inclusion: optional "full" or "excluded"` How this tool's result blocks appear in the API response when the result was consumed by a completed code_execution call in the same turn. 'full' returns the complete content (default). 'excluded' drops the nested server_tool_use and result block pair entirely. Results from direct calls, or from code_execution calls that paused before completing, are always returned in full so they can be sent back on the next turn. - `"full"` - `"excluded"` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `url_sources: optional object` Which sources contribute to the set of URLs the tool may fetch. Omitted means every source. - `client_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which client tools' results contribute fetchable URLs: "all", "none", or an only or except list of client tool names from tools[]. - `server_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which server tools' results contribute fetchable URLs: "all", "none", or an only or except list of server tool names from tools[]; only web_search and web_fetch results ever contribute. - `user_input: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone` Whether URLs in user messages are fetchable: "all" or "none". - `use_cache: optional boolean` Whether to use cached content. Set to false to bypass the cache and fetch fresh content. Only set to false when the user explicitly requests fresh content or when fetching rapidly-changing sources. - `beta_advisor_tool_20260301: object` - `type: "advisor_20260301"` - `model: "claude-haiku-5-5" or "claude-sonnet-5-5" or "claude-fable-5-1" or 17 more or string` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-haiku-5-5"` Fastest model for high-volume, real-time tasks - `"claude-sonnet-5-5"` Efficient model for coding and agents - `"claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows - `"claude-opus-5-5"` Powerful intelligence for coding, knowledge work, and long-running agents - `"claude-mythos-5-1"` Our most capable model for cybersecurity and biology research, available through trusted access programs - `"claude-sonnet-5"` Efficient model for coding and agents - `"claude-fable-5"` Next generation of intelligence for the hardest knowledge work and coding problems - `"claude-mythos-5"` Most capable model for cybersecurity and biology research - `"claude-opus-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-8"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-7"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-6"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-6"` Best combination of speed and intelligence - `"claude-haiku-4-5"` - `"claude-haiku-4-5-20251001"` - `"claude-opus-4-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-5-20251101"` Powerful intelligence for long-running agents and coding - `"claude-mythos-preview"` **Deprecated**: Will reach end-of-life on June 30, 2026. Please migrate to claude-mythos-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. New class of intelligence, strongest in coding and cybersecurity - `"claude-sonnet-4-5"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `"claude-sonnet-4-5-20250929"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `name: "advisor"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `caching: optional object` Caching for the advisor's own prompt. When set, each advisor call writes a cache entry at the given TTL so subsequent calls in the same conversation read the stable prefix. When omitted, the advisor prompt is not cached. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_tokens: optional number` Bounds the advisor's total output (thinking + text) per call. When the advisor hits this cap, the returned advisor_result or advisor_redacted_result block carries stop_reason='max_tokens', and a truncation note is appended to the advice text the worker model sees (inside the encrypted blob in redacted mode). When set, the server also emits a remaining-tokens budget block in the advisor's prompt so the advisor self-shapes toward the cap. When omitted, the advisor model's default output cap applies and no budget block is emitted. minimum: 1024 - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_search_tool_bm25_20251119: object` - `type: "tool_search_tool_bm25_20251119" or "tool_search_tool_bm25"` - `"tool_search_tool_bm25_20251119"` - `"tool_search_tool_bm25"` - `name: "tool_search_tool_bm25"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_search_tool_regex_20251119: object` - `type: "tool_search_tool_regex_20251119" or "tool_search_tool_regex"` - `"tool_search_tool_regex_20251119"` - `"tool_search_tool_regex"` - `name: "tool_search_tool_regex"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_mcp_toolset: object` Configuration for a group of tools from an MCP server. Allows configuring enabled status and defer_loading for all tools from an MCP server, with optional per-tool overrides. - `type: "mcp_toolset"` - `mcp_server_name: string` Name of the MCP server to configure tools for minLength: 1, maxLength: 255 - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `configs: optional map[BetaMCPToolConfig]` Configuration overrides for specific tools, keyed by tool name - `defer_loading: optional boolean` - `enabled: optional boolean` - `default_config: optional object` Default configuration applied to all tools from this server - `defer_loading: optional boolean` - `enabled: optional boolean` - `tools: optional array of BetaMCPToolParam` The server's tool listing, pinned: when present, the server is not asked for its tools before sampling and exactly these entries, with `default_config` and `configs` applied, are the toolset's tools. Copy it from the `mcp_tool_listing` block of an earlier response. - `input_schema: map[unknown]` The tool's input schema as the MCP server lists it, verbatim. - `name: string` The tool's name as the MCP server lists it (not prefixed with the server name). minLength: 1 - `description: optional string` The tool's description as the MCP server lists it. - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `beta_request_tool_removal_block: object` Mid-conversation directive to withdraw a tool. `tool` references a tool (or MCP toolset) by name: one declared in the request's `tools` or defined earlier in `messages`. It is no longer offered to the model from this point in the conversation onward. - `type: "tool_removal"` - `tool: BetaToolChangeToolReference or BetaToolChangeMCPToolReference or BetaToolChangeMCPToolsetReference` - `beta_tool_change_tool_reference: object` Reference to a single tool, by the name the model uses to call it: a tool declared in `tools` or defined by an earlier `tool_addition` block. Does not accept the composed `{server}_{name}` form the server assigns to MCP-resolved tools; use `mcp_tool_reference` or `mcp_toolset_reference` for those. - `beta_tool_change_mcp_tool_reference: object` Reference to a single MCP tool by its server and remote name; the same `server_name`/`name` pair `mcp_tool_use` carries. - `beta_tool_change_mcp_toolset_reference: object` Reference to every tool in the named MCP server's toolset. - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `beta_request_tool_addition_block: object` Mid-conversation directive to make a tool available. `tool` is a reference to a tool (or MCP toolset) declared in the request's `tools`. Under the `inline-tools-2026-09-15` beta it may instead be a reference to a tool defined earlier in `messages`, or a `tool_definition` object that carries an inline tool definition in `definition` (the same object a `tools` entry holds). An `mcp_toolset` definition also requires the `mcp-client-2026-09-15` beta. The tool is offered to the model from this point in the conversation onward. - `type: "tool_addition"` - `tool: BetaToolChangeToolReference or BetaToolChangeMCPToolReference or BetaToolChangeMCPToolsetReference or BetaToolChangeToolDefinitionParam` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `beta_request_tool_removal_block: object` Mid-conversation directive to withdraw a tool. `tool` references a tool (or MCP toolset) by name: one declared in the request's `tools` or defined earlier in `messages`. It is no longer offered to the model from this point in the conversation onward. - `type: "tool_removal"` - `tool: BetaToolChangeToolReference or BetaToolChangeMCPToolReference or BetaToolChangeMCPToolsetReference` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `beta_mcp_tool_listing_block_param: object` The tool listing an MCP server returned while an earlier response was produced, as that response carried it. Send the assistant message back unchanged, this block included, and the server uses this listing for the matching `mcp_toolset` instead of asking the MCP server again. - `type: "mcp_tool_listing"` - `mcp_server_name: string` The name of the MCP server this listing came from, as `mcp_servers` declares it. minLength: 1, maxLength: 255 - `tools: array of BetaMCPToolParam` The server's tools, exactly as the response listed them. - `input_schema: map[unknown]` The tool's input schema as the MCP server lists it, verbatim. - `name: string` The tool's name as the MCP server lists it (not prefixed with the server name). minLength: 1 - `description: optional string` The tool's description as the MCP server lists it. - `beta_fallback_block_param: object` A `fallback` block echoed back from a prior response. Accepted in `messages[].content` and not rendered into the prompt; not validated against the request's `fallbacks` chain or top-level `model`. Echo the assistant turn back verbatim, including this block in its original position. The block marks the boundary between content produced before and after a fallback hop, and the server relies on that boundary to validate the turn: when thinking runs flank the boundary, omitting the block merges them into one span the server cannot validate (the request is rejected), and moving it into the middle of a single run is likewise rejected; between non-thinking blocks the block's placement has no validation effect. - `type: "fallback"` - `from: object` Identifies one hop of a fallback transition. - `model: "claude-haiku-5-5" or "claude-sonnet-5-5" or "claude-fable-5-1" or 17 more or string` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-haiku-5-5"` Fastest model for high-volume, real-time tasks - `"claude-sonnet-5-5"` Efficient model for coding and agents - `"claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows - `"claude-opus-5-5"` Powerful intelligence for coding, knowledge work, and long-running agents - `"claude-mythos-5-1"` Our most capable model for cybersecurity and biology research, available through trusted access programs - `"claude-sonnet-5"` Efficient model for coding and agents - `"claude-fable-5"` Next generation of intelligence for the hardest knowledge work and coding problems - `"claude-mythos-5"` Most capable model for cybersecurity and biology research - `"claude-opus-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-8"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-7"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-6"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-6"` Best combination of speed and intelligence - `"claude-haiku-4-5"` - `"claude-haiku-4-5-20251001"` - `"claude-opus-4-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-5-20251101"` Powerful intelligence for long-running agents and coding - `"claude-mythos-preview"` **Deprecated**: Will reach end-of-life on June 30, 2026. Please migrate to claude-mythos-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. New class of intelligence, strongest in coding and cybersecurity - `"claude-sonnet-4-5"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `"claude-sonnet-4-5-20250929"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `to: object` Identifies one hop of a fallback transition. - `model: "claude-haiku-5-5" or "claude-sonnet-5-5" or "claude-fable-5-1" or 17 more or string` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `trigger: optional unknown` The response block's `trigger`, echoed verbatim. Accepted and ignored by the server; any object or `null` is allowed. - `role: "user" or "assistant" or "system"` - `"user"` - `"assistant"` - `"system"` - `clear_at: optional "next_user_message" or "never"` How long this system message's text stays in front of the model. `"never"` (the default) renders it on every request that includes it. `"next_user_message"` renders it only for the user turn it follows: once a later `role: "user"` message exists in `messages` the message stays in the array (send it unchanged) but is no longer shown to the model. Only permitted on `role: "system"` messages. - `"next_user_message"` - `"never"` - `output_config: optional object` Per-message output configuration on a role:"system" input message. Fields here apply per-turn; `format` remains top-level only. An empty `{}` is accepted on a message that carries content; a message with neither content nor output_config fields is rejected. - `effort: optional "low" or "medium" or "high" or 2 more` How much effort the model should put into its response. Higher effort levels may result in more thorough analysis but take longer. Valid values are `low`, `medium`, `high`, `xhigh`, or `max`. - `"low"` - `"medium"` - `"high"` - `"xhigh"` - `"max"` ### Beta Message Tokens Count - `beta_message_tokens_count: object` - `context_management: object` Information about context management applied to the message. - `original_input_tokens: number` The original token count before context management was applied - `input_tokens: number` The total number of tokens across the provided list of messages, system prompt, and tools. ### Beta Metadata - `beta_metadata: object` - `user_id: optional string` An external identifier for the user who is associated with the request. This should be a uuid, hash value, or other opaque identifier. Anthropic may use this id to help detect abuse. Do not include any identifying information such as name, email address, or phone number. maxLength: 512 ### Beta Output Config - `beta_output_config: object` - `effort: optional "low" or "medium" or "high" or 2 more` How much effort the model should put into its response. Higher effort levels may result in more thorough analysis but take longer. Valid values are `low`, `medium`, `high`, `xhigh`, or `max`. - `"low"` - `"medium"` - `"high"` - `"xhigh"` - `"max"` - `format: optional object` A schema to specify Claude's output format in responses. See [structured outputs](https://platform.claude.com/docs/en/build-with-claude/structured-outputs?sdk_languages=cli) - `type: "json_schema"` - `schema: map[unknown]` The JSON schema of the format - `task_budget: optional object` Configuration for token budget tracking across contexts. - `type: "tokens"` The budget type. Currently only 'tokens' is supported. - `total: number` Total token budget across all contexts in the session. minimum: 1024 - `remaining: optional number` Remaining tokens in the budget. Use this to track usage across contexts when implementing compaction client-side. Defaults to total if not provided. minimum: 0 ### Beta Output Tokens Details - `beta_output_tokens_details: object` - `thinking_tokens: number` Number of output tokens the model generated as internal reasoning, including the thinking-block delimiter tokens. Reflects the raw reasoning the model produced, not the (possibly shorter) summarized thinking text returned in the response body. Computed by re-tokenizing the raw reasoning text, so it may differ from the model's exact generation count by a small number of tokens. Always ≤ `output_tokens`; `output_tokens - thinking_tokens` approximates the non-reasoning output. minimum: 0 ### Beta Plain Text Source - `beta_plain_text_source: object` - `type: "text"` - `data: string` - `media_type: "text/plain"` ### Beta Raw Content Block Delta - `beta_raw_content_block_delta: BetaTextDelta or BetaInputJSONDelta or BetaCitationsDelta or 3 more` - `beta_text_delta: object` - `type: "text_delta"` - `text: string` - `beta_input_json_delta: object` - `type: "input_json_delta"` - `partial_json: string` - `beta_citations_delta: object` - `type: "citations_delta"` - `citation: BetaCitationCharLocation or BetaCitationPageLocation or BetaCitationContentBlockLocation or 2 more` - `beta_citation_char_location: object` - `type: "char_location"` - `cited_text: string` - `document_index: number` minimum: 0 - `document_title: string` - `end_char_index: number` - `file_id: string` - `start_char_index: number` minimum: 0 - `beta_citation_page_location: object` - `type: "page_location"` - `cited_text: string` - `document_index: number` minimum: 0 - `document_title: string` - `end_page_number: number` - `file_id: string` - `start_page_number: number` minimum: 1 - `beta_citation_content_block_location: object` - `type: "content_block_location"` - `cited_text: string` The full text of the cited block range, concatenated. Always equals the contents of `content[start_block_index:end_block_index]` joined together. The text block is the minimal citable unit; this field is never a substring of a single block. Not counted toward output tokens, and not counted toward input tokens when sent back in subsequent turns. - `document_index: number` minimum: 0 - `document_title: string` - `end_block_index: number` Exclusive 0-based end index of the cited block range in the source's `content` array. Always greater than `start_block_index`; a single-block citation has `end_block_index = start_block_index + 1`. - `file_id: string` - `start_block_index: number` 0-based index of the first cited block in the source's `content` array. minimum: 0 - `beta_citations_web_search_result_location: object` - `type: "web_search_result_location"` - `cited_text: string` - `encrypted_index: string` - `title: string` maxLength: 512 - `url: string` - `beta_citation_search_result_location: object` - `type: "search_result_location"` - `cited_text: string` The full text of the cited block range, concatenated. Always equals the contents of `content[start_block_index:end_block_index]` joined together. The text block is the minimal citable unit; this field is never a substring of a single block. Not counted toward output tokens, and not counted toward input tokens when sent back in subsequent turns. - `end_block_index: number` Exclusive 0-based end index of the cited block range in the source's `content` array. Always greater than `start_block_index`; a single-block citation has `end_block_index = start_block_index + 1`. - `search_result_index: number` 0-based index of the cited search result among all `search_result` content blocks in the request, in the order they appear across messages and tool results. Counted separately from `document_index`; server-side web search results are not included in this count. minimum: 0 - `source: string` - `start_block_index: number` 0-based index of the first cited block in the source's `content` array. minimum: 0 - `title: string` - `beta_thinking_delta: object` - `type: "thinking_delta"` - `estimated_tokens: number` Per-frame increment of a coarse, running estimate of the tokens this thinking block has produced so far. Present whenever the `thinking-token-count-2026-05-13` beta is set; `null` unless `thinking.display` resolves to `"omitted"` and a count is due this frame. Sum the increments across `thinking_delta` frames on this block for a progress indicator. Each increment is a non-negative multiple of a fixed quantum and the cadence is rate-limited, so this is a deliberately lossy display hint, not a billable count; `usage.output_tokens` remains authoritative. - `thinking: string` The incremental `thinking` text for this content block. Concatenate the `thinking` values of successive `thinking_delta` events to assemble the block's full `thinking` value. - `beta_signature_delta: object` - `type: "signature_delta"` - `signature: string` The `signature` for this thinking block: an opaque value used to verify that the block was generated by Claude when it is passed back to the API. Delivered in a `signature_delta` event just before the block's `content_block_stop` event. - `beta_compaction_content_block_delta: object` - `type: "compaction_delta"` - `content: string` - `encrypted_content: string` Opaque metadata from prior compaction, to be round-tripped verbatim ### Beta Raw Content Block Delta Event - `beta_raw_content_block_delta_event: object` - `type: "content_block_delta"` - `delta: BetaTextDelta or BetaInputJSONDelta or BetaCitationsDelta or 3 more` - `beta_text_delta: object` - `type: "text_delta"` - `text: string` - `beta_input_json_delta: object` - `type: "input_json_delta"` - `partial_json: string` - `beta_citations_delta: object` - `type: "citations_delta"` - `citation: BetaCitationCharLocation or BetaCitationPageLocation or BetaCitationContentBlockLocation or 2 more` - `beta_citation_char_location: object` - `type: "char_location"` - `cited_text: string` - `document_index: number` minimum: 0 - `document_title: string` - `end_char_index: number` - `file_id: string` - `start_char_index: number` minimum: 0 - `beta_citation_page_location: object` - `type: "page_location"` - `cited_text: string` - `document_index: number` minimum: 0 - `document_title: string` - `end_page_number: number` - `file_id: string` - `start_page_number: number` minimum: 1 - `beta_citation_content_block_location: object` - `type: "content_block_location"` - `cited_text: string` The full text of the cited block range, concatenated. Always equals the contents of `content[start_block_index:end_block_index]` joined together. The text block is the minimal citable unit; this field is never a substring of a single block. Not counted toward output tokens, and not counted toward input tokens when sent back in subsequent turns. - `document_index: number` minimum: 0 - `document_title: string` - `end_block_index: number` Exclusive 0-based end index of the cited block range in the source's `content` array. Always greater than `start_block_index`; a single-block citation has `end_block_index = start_block_index + 1`. - `file_id: string` - `start_block_index: number` 0-based index of the first cited block in the source's `content` array. minimum: 0 - `beta_citations_web_search_result_location: object` - `type: "web_search_result_location"` - `cited_text: string` - `encrypted_index: string` - `title: string` maxLength: 512 - `url: string` - `beta_citation_search_result_location: object` - `type: "search_result_location"` - `cited_text: string` The full text of the cited block range, concatenated. Always equals the contents of `content[start_block_index:end_block_index]` joined together. The text block is the minimal citable unit; this field is never a substring of a single block. Not counted toward output tokens, and not counted toward input tokens when sent back in subsequent turns. - `end_block_index: number` Exclusive 0-based end index of the cited block range in the source's `content` array. Always greater than `start_block_index`; a single-block citation has `end_block_index = start_block_index + 1`. - `search_result_index: number` 0-based index of the cited search result among all `search_result` content blocks in the request, in the order they appear across messages and tool results. Counted separately from `document_index`; server-side web search results are not included in this count. minimum: 0 - `source: string` - `start_block_index: number` 0-based index of the first cited block in the source's `content` array. minimum: 0 - `title: string` - `beta_thinking_delta: object` - `type: "thinking_delta"` - `estimated_tokens: number` Per-frame increment of a coarse, running estimate of the tokens this thinking block has produced so far. Present whenever the `thinking-token-count-2026-05-13` beta is set; `null` unless `thinking.display` resolves to `"omitted"` and a count is due this frame. Sum the increments across `thinking_delta` frames on this block for a progress indicator. Each increment is a non-negative multiple of a fixed quantum and the cadence is rate-limited, so this is a deliberately lossy display hint, not a billable count; `usage.output_tokens` remains authoritative. - `thinking: string` The incremental `thinking` text for this content block. Concatenate the `thinking` values of successive `thinking_delta` events to assemble the block's full `thinking` value. - `beta_signature_delta: object` - `type: "signature_delta"` - `signature: string` The `signature` for this thinking block: an opaque value used to verify that the block was generated by Claude when it is passed back to the API. Delivered in a `signature_delta` event just before the block's `content_block_stop` event. - `beta_compaction_content_block_delta: object` - `type: "compaction_delta"` - `content: string` - `encrypted_content: string` Opaque metadata from prior compaction, to be round-tripped verbatim - `index: number` ### Beta Raw Content Block Start Event - `beta_raw_content_block_start_event: object` - `type: "content_block_start"` - `content_block: BetaTextBlock or BetaThinkingBlock or BetaRedactedThinkingBlock or 15 more` - `beta_text_block: object` - `type: "text"` - `citations: array of BetaTextCitation` Citations supporting the text block. The type of citation returned will depend on the type of document being cited. Citing a PDF results in `page_location`, plain text results in `char_location`, and content document results in `content_block_location`. - `beta_citation_char_location: object` - `type: "char_location"` - `cited_text: string` - `document_index: number` minimum: 0 - `document_title: string` - `end_char_index: number` - `file_id: string` - `start_char_index: number` minimum: 0 - `beta_citation_page_location: object` - `type: "page_location"` - `cited_text: string` - `document_index: number` minimum: 0 - `document_title: string` - `end_page_number: number` - `file_id: string` - `start_page_number: number` minimum: 1 - `beta_citation_content_block_location: object` - `type: "content_block_location"` - `cited_text: string` The full text of the cited block range, concatenated. Always equals the contents of `content[start_block_index:end_block_index]` joined together. The text block is the minimal citable unit; this field is never a substring of a single block. Not counted toward output tokens, and not counted toward input tokens when sent back in subsequent turns. - `document_index: number` minimum: 0 - `document_title: string` - `end_block_index: number` Exclusive 0-based end index of the cited block range in the source's `content` array. Always greater than `start_block_index`; a single-block citation has `end_block_index = start_block_index + 1`. - `file_id: string` - `start_block_index: number` 0-based index of the first cited block in the source's `content` array. minimum: 0 - `beta_citations_web_search_result_location: object` - `type: "web_search_result_location"` - `cited_text: string` - `encrypted_index: string` - `title: string` maxLength: 512 - `url: string` - `beta_citation_search_result_location: object` - `type: "search_result_location"` - `cited_text: string` The full text of the cited block range, concatenated. Always equals the contents of `content[start_block_index:end_block_index]` joined together. The text block is the minimal citable unit; this field is never a substring of a single block. Not counted toward output tokens, and not counted toward input tokens when sent back in subsequent turns. - `end_block_index: number` Exclusive 0-based end index of the cited block range in the source's `content` array. Always greater than `start_block_index`; a single-block citation has `end_block_index = start_block_index + 1`. - `search_result_index: number` 0-based index of the cited search result among all `search_result` content blocks in the request, in the order they appear across messages and tool results. Counted separately from `document_index`; server-side web search results are not included in this count. minimum: 0 - `source: string` - `start_block_index: number` 0-based index of the first cited block in the source's `content` array. minimum: 0 - `title: string` - `text: string` - `beta_thinking_block: object` - `type: "thinking"` - `signature: string` A value used to verify that this thinking block was generated by Claude when it is passed back to the API. This is an opaque field and should not be interpreted or parsed. When passing thinking blocks back to the API (required when using tools with extended thinking), pass them back exactly as received, with this field intact. See [extended thinking](https://platform.claude.com/docs/en/build-with-claude/extended-thinking?sdk_languages=cli) for details. - `thinking: string` The text of Claude's thinking process for this block. - `beta_redacted_thinking_block: object` - `type: "redacted_thinking"` - `data: string` The contents of this redacted thinking block, returned when portions of the model's thinking were safety-redacted. This field is opaque and encrypted, with no readable content. Pass `redacted_thinking` blocks back to the API unchanged when continuing a multi-turn conversation. See [extended thinking](https://platform.claude.com/docs/en/build-with-claude/extended-thinking?sdk_languages=cli#redacted-thinking-blocks) for details. - `beta_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: map[unknown]` - `name: string` minLength: 1 - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` - `beta_direct_caller: object` Tool invocation directly from the model. - `type: "direct"` - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `type: "code_execution_20250825"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `beta_server_tool_caller_20260120: object` - `type: "code_execution_20260120"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `toolset_name: optional string` For a toolset member tool_use, the toolset family. minLength: 1, maxLength: 64, pattern: ^[a-zA-Z0-9_-]+$ - `beta_server_tool_use_block: object` - `type: "server_tool_use"` - `id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `input: map[unknown]` - `name: "advisor" or "web_search" or "web_fetch" or 5 more` - `"advisor"` - `"web_search"` - `"web_fetch"` - `"code_execution"` - `"bash_code_execution"` - `"text_editor_code_execution"` - `"tool_search_tool_regex"` - `"tool_search_tool_bm25"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` - `beta_direct_caller: object` Tool invocation directly from the model. - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `beta_server_tool_caller_20260120: object` - `beta_web_search_tool_result_block: object` - `type: "web_search_tool_result"` - `content: BetaWebSearchToolResultError or array of BetaWebSearchResultBlock` - `beta_web_search_tool_result_error: object` - `type: "web_search_tool_result_error"` - `error_code: "invalid_tool_input" or "unavailable" or "max_uses_exceeded" or 3 more` - `"invalid_tool_input"` - `"unavailable"` - `"max_uses_exceeded"` - `"too_many_requests"` - `"query_too_long"` - `"request_too_large"` - `union_member_1: array of BetaWebSearchResultBlock` - `type: "web_search_result"` - `encrypted_content: string` - `page_age: string` - `title: string` - `url: string` - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` - `beta_direct_caller: object` Tool invocation directly from the model. - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `beta_server_tool_caller_20260120: object` - `beta_web_fetch_tool_result_block: object` - `type: "web_fetch_tool_result"` - `content: BetaWebFetchToolResultErrorBlock or BetaWebFetchBlock` - `beta_web_fetch_tool_result_error_block: object` - `type: "web_fetch_tool_result_error"` - `error_code: "invalid_tool_input" or "url_too_long" or "url_not_allowed" or 7 more` - `"invalid_tool_input"` - `"url_too_long"` - `"url_not_allowed"` - `"url_not_in_prior_context"` - `"url_not_accessible"` - `"unsupported_content_type"` - `"too_many_requests"` - `"max_uses_exceeded"` - `"unavailable"` - `"content_too_large"` - `beta_web_fetch_block: object` - `type: "web_fetch_result"` - `content: object` - `type: "document"` - `citations: object` Citation configuration for the document - `enabled: boolean` - `source: BetaBase64PDFSource or BetaPlainTextSource` - `beta_base64_pdf_source: object` - `type: "base64"` - `data: string` format: byte - `media_type: "application/pdf"` - `beta_plain_text_source: object` - `type: "text"` - `data: string` - `media_type: "text/plain"` - `title: string` The title of the document - `retrieved_at: string` ISO 8601 timestamp when the content was retrieved - `url: string` Fetched content URL - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` - `beta_direct_caller: object` Tool invocation directly from the model. - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `beta_server_tool_caller_20260120: object` - `beta_advisor_tool_result_block: object` - `type: "advisor_tool_result"` - `content: BetaAdvisorToolResultError or BetaAdvisorResultBlock or BetaAdvisorRedactedResultBlock` - `beta_advisor_tool_result_error: object` - `type: "advisor_tool_result_error"` - `error_code: "max_uses_exceeded" or "prompt_too_long" or "too_many_requests" or 4 more` - `"max_uses_exceeded"` - `"prompt_too_long"` - `"too_many_requests"` - `"overloaded"` - `"unavailable"` - `"execution_time_exceeded"` - `"model_not_found"` - `beta_advisor_result_block: object` - `type: "advisor_result"` - `stop_reason: string` The advisor sub-inference's stop reason (same values as the top-level message `stop_reason`). `max_tokens` indicates the advisor's output was truncated at the tool's `max_tokens` value or the advisor model's policy cap. - `text: string` - `beta_advisor_redacted_result_block: object` - `type: "advisor_redacted_result"` - `encrypted_content: string` Opaque blob containing the advisor's output. Round-trip verbatim; do not inspect or modify. - `stop_reason: string` The advisor sub-inference's stop reason (same values as the top-level message `stop_reason`). - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `beta_code_execution_tool_result_block: object` - `type: "code_execution_tool_result"` - `content: BetaCodeExecutionToolResultError or BetaCodeExecutionResultBlock or BetaEncryptedCodeExecutionResultBlock` - `beta_code_execution_tool_result_error: object` - `type: "code_execution_tool_result_error"` - `error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or "execution_time_exceeded"` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `beta_code_execution_result_block: object` - `type: "code_execution_result"` - `content: array of BetaCodeExecutionOutputBlock` - `type: "code_execution_output"` - `file_id: string` - `return_code: number` - `stderr: string` - `stdout: string` - `beta_encrypted_code_execution_result_block: object` Code execution result with encrypted stdout for PFC + web_search results. - `type: "encrypted_code_execution_result"` - `content: array of BetaCodeExecutionOutputBlock` - `type: "code_execution_output"` - `file_id: string` - `encrypted_stdout: string` - `return_code: number` - `stderr: string` - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `beta_bash_code_execution_tool_result_block: object` - `type: "bash_code_execution_tool_result"` - `content: BetaBashCodeExecutionToolResultError or BetaBashCodeExecutionResultBlock` - `beta_bash_code_execution_tool_result_error: object` - `type: "bash_code_execution_tool_result_error"` - `error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or 2 more` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `"output_file_too_large"` - `beta_bash_code_execution_result_block: object` - `type: "bash_code_execution_result"` - `content: array of BetaBashCodeExecutionOutputBlock` - `type: "bash_code_execution_output"` - `file_id: string` - `return_code: number` - `stderr: string` - `stdout: string` - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `beta_text_editor_code_execution_tool_result_block: object` - `type: "text_editor_code_execution_tool_result"` - `content: BetaTextEditorCodeExecutionToolResultError or BetaTextEditorCodeExecutionViewResultBlock or BetaTextEditorCodeExecutionCreateResultBlock or BetaTextEditorCodeExecutionStrReplaceResultBlock` - `beta_text_editor_code_execution_tool_result_error: object` - `type: "text_editor_code_execution_tool_result_error"` - `error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or 2 more` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `"file_not_found"` - `error_message: string` - `beta_text_editor_code_execution_view_result_block: object` - `type: "text_editor_code_execution_view_result"` - `content: string` - `file_type: "text" or "image" or "pdf"` - `"text"` - `"image"` - `"pdf"` - `num_lines: number` - `start_line: number` - `total_lines: number` - `beta_text_editor_code_execution_create_result_block: object` - `type: "text_editor_code_execution_create_result"` - `is_file_update: boolean` - `beta_text_editor_code_execution_str_replace_result_block: object` - `type: "text_editor_code_execution_str_replace_result"` - `lines: array of string` - `new_lines: number` - `new_start: number` - `old_lines: number` - `old_start: number` - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `beta_tool_search_tool_result_block: object` - `type: "tool_search_tool_result"` - `content: BetaToolSearchToolResultError or BetaToolSearchToolSearchResultBlock` - `beta_tool_search_tool_result_error: object` - `type: "tool_search_tool_result_error"` - `error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or "execution_time_exceeded"` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `error_message: string` - `beta_tool_search_tool_search_result_block: object` - `type: "tool_search_tool_search_result"` - `tool_references: array of BetaToolReferenceBlock` - `type: "tool_reference"` - `tool_name: string` minLength: 1, maxLength: 256, pattern: ^[a-zA-Z0-9_-]{1,256}$ - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `beta_mcp_tool_use_block: object` - `type: "mcp_tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: map[unknown]` - `name: string` The name of the MCP tool - `server_name: string` The name of the MCP server - `beta_mcp_tool_result_block: object` - `type: "mcp_tool_result"` - `content: string or array of BetaTextBlock` - `union_member_0: string` - `beta_mcp_tool_result_block_content: array of BetaTextBlock` - `type: "text"` - `citations: array of BetaTextCitation` Citations supporting the text block. The type of citation returned will depend on the type of document being cited. Citing a PDF results in `page_location`, plain text results in `char_location`, and content document results in `content_block_location`. - `text: string` - `is_error: boolean` - `tool_use_id: string` pattern: ^[a-zA-Z0-9_-]+$ - `beta_container_upload_block: object` Response model for a file uploaded to the container. - `type: "container_upload"` - `file_id: string` - `beta_compaction_block: object` A compaction block returned when autocompact is triggered. When content is None, it indicates the compaction failed to produce a valid summary (e.g., malformed output from the model). Clients may round-trip compaction blocks with null content; the server treats them as no-ops. - `type: "compaction"` - `content: string` Summary of compacted content, or null if compaction failed - `encrypted_content: string` Opaque metadata from prior compaction, to be round-tripped verbatim - `signature: optional string` Signature over the summary, to be sent back with the block verbatim - `tool_changes: optional array of BetaResponseToolAdditionBlock or BetaResponseToolRemovalBlock` The tool changes of the compacted range: the `tool_addition` and `tool_removal` blocks that take the request's `tools` to the tool set in effect at the end of the range, or `[]` when the range changed no tool. Absent when the server did not compute them. Send the block back unchanged. - `beta_response_tool_addition_block: object` An entry of a `compaction` block's `tool_changes`: a tool the compacted range made available, as a reference to a `tools` entry or MCP toolset, or as the tool definition in effect at the end of the range, by value. Send it back unchanged. - `type: "tool_addition"` - `tool: BetaResponseToolChangeToolReference or BetaResponseToolChangeMCPToolReference or BetaResponseToolChangeMCPToolsetReference or BetaToolChangeToolDefinition` The tool made available: a reference to a `tools` entry or MCP toolset, or a `tool_definition` carrying the definition by value. - `beta_response_tool_change_tool_reference: object` Reference to a single tool, by the name the model uses to call it, as a `compaction` block's `tool_changes` entry reports it: a tool declared in `tools` or defined by an earlier `tool_addition` block. Send it back unchanged with the block. - `type: "tool_reference"` - `name: string` - `beta_response_tool_change_mcp_tool_reference: object` Reference to a single MCP tool, by its server and its name on that server, as a `compaction` block's `tool_changes` entry reports it. Send it back unchanged with the block. - `type: "mcp_tool_reference"` - `name: string` - `server_name: string` - `beta_response_tool_change_mcp_toolset_reference: object` Reference to every tool in the named MCP server's toolset, as a `compaction` block's `tool_changes` entry reports it. Send it back unchanged with the block. - `type: "mcp_toolset_reference"` - `server_name: string` - `beta_tool_change_tool_definition: object` A tool defined by value, as a `compaction` block's `tool_changes` entry reports it: `definition` is the tool's definition as it was sent, in the form of a `tools` entry, without `cache_control`. Send it back unchanged with the block. - `type: "tool_definition"` - `definition: BetaResponseTool or BetaToolBash20241022 or BetaToolBash20250124 or 25 more` - `beta_response_tool: object` A custom tool definition, as sent. - `type: optional "custom"` - `input_schema: object` [JSON schema](https://json-schema.org/draft/2020-12) for this tool's input. This defines the shape of the `input` that your tool accepts and that the model will produce. - `type: "object"` - `properties: optional map[unknown]` - `required: optional array of string` - `name: string` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. minLength: 1, maxLength: 128, pattern: ^[a-zA-Z0-9_-]{1,128}$ - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `description: optional string` Description of what this tool does. Tool descriptions should be as detailed as possible. The more information that the model has about what the tool is and how to use it, the better it will perform. You can use natural language descriptions to reinforce important aspects of the tool input JSON schema. - `eager_input_streaming: optional boolean` Enable eager input streaming for this tool. When true, tool input parameters will be streamed incrementally as they are generated, and types will be inferred on-the-fly rather than buffering the full JSON output. When false, streaming is disabled for this tool even if the fine-grained-tool-streaming beta is active. When null (default), uses the default behavior based on beta headers. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_bash_20241022: object` - `type: "bash_20241022"` - `name: "bash"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `"5m"` - `"1h"` - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_bash_20250124: object` - `type: "bash_20250124"` - `name: "bash"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_code_execution_tool_20250522: object` - `type: "code_execution_20250522"` - `name: "code_execution"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_code_execution_tool_20250825: object` - `type: "code_execution_20250825"` - `name: "code_execution"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_code_execution_tool_20260120: object` Code execution tool with REPL state persistence (daemon mode + gVisor checkpoint). - `type: "code_execution_20260120"` - `name: "code_execution"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_code_execution_tool_20260521: object` Code execution tool with REPL state persistence. - `type: "code_execution_20260521"` - `name: "code_execution"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_browser_toolset_20260801: object` The browser toolset: a single `tools[]` entry (carrying no `name`) that declares the browser tool family. The model is served the family's tool with any members disabled via `configs` removed from its schema. - `type: "browser_toolset_20260801"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `configs: optional object` Sparse per-member overrides, keyed by member name. Absent, null, and {} are equivalent; a member's defaults apply wherever its key is absent. - `type: optional object` `type`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `close_tab: optional object` `close_tab`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `double_click: optional object` `double_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `file_upload: optional object` `file_upload`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `find: optional object` `find`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `form_input: optional object` `form_input`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `get_page_text: optional object` `get_page_text`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `hold_key: optional object` `hold_key`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `hover: optional object` `hover`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `javascript_exec: optional object` `javascript_exec`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `key: optional object` `key`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_click: optional object` `left_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_click_drag: optional object` `left_click_drag`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_mouse_down: optional object` `left_mouse_down`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_mouse_up: optional object` `left_mouse_up`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `list_tabs: optional object` `list_tabs`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `middle_click: optional object` `middle_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `mouse_move: optional object` `mouse_move`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `navigate: optional object` `navigate`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `new_tab: optional object` `new_tab`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `read_console: optional object` `read_console`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `read_network: optional object` `read_network`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `read_page: optional object` `read_page`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `right_click: optional object` `right_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `screenshot: optional object` `screenshot`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `scroll: optional object` `scroll`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `scroll_to: optional object` `scroll_to`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `switch_tab: optional object` `switch_tab`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `triple_click: optional object` `triple_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `wait: optional object` `wait`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `zoom: optional object` `zoom`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `beta_tool_computer_use_20241022: object` - `type: "computer_20241022"` - `display_height_px: number` The height of the display in pixels. minimum: 1 - `display_width_px: number` The width of the display in pixels. minimum: 1 - `name: "computer"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `display_number: optional number` The X11 display number (e.g. 0, 1) for the display. minimum: 0 - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_memory_tool_20250818: object` - `type: "memory_20250818"` - `name: "memory"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_computer_use_20250124: object` - `type: "computer_20250124"` - `display_height_px: number` The height of the display in pixels. minimum: 1 - `display_width_px: number` The width of the display in pixels. minimum: 1 - `name: "computer"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `display_number: optional number` The X11 display number (e.g. 0, 1) for the display. minimum: 0 - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_text_editor_20241022: object` - `type: "text_editor_20241022"` - `name: "str_replace_editor"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_computer_use_20251124: object` - `type: "computer_20251124"` - `display_height_px: number` The height of the display in pixels. minimum: 1 - `display_width_px: number` The width of the display in pixels. minimum: 1 - `name: "computer"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `display_number: optional number` The X11 display number (e.g. 0, 1) for the display. minimum: 0 - `enable_zoom: optional boolean` Whether to enable an action to take a zoomed-in screenshot of the screen. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_computer_toolset_20260801: object` The computer toolset: a single `tools[]` entry (carrying no `name`) that declares the computer tool family. The model is served the family's tool with any members disabled via `configs` removed from its schema. Every member is enabled by default, zoom included. The single-tool options `display_number` and `enable_zoom` are not fields of a toolset entry — it carries only `type`, `configs`, and `cache_control`; zoom is controlled via `configs.zoom.enabled`. - `type: "computer_toolset_20260801"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `configs: optional object` Sparse per-member overrides, keyed by member name. Absent, null, and {} are equivalent; a member's defaults apply wherever its key is absent. - `type: optional object` `type`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `cursor_position: optional object` `cursor_position`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `double_click: optional object` `double_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `hold_key: optional object` `hold_key`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `key: optional object` `key`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_click: optional object` `left_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_click_drag: optional object` `left_click_drag`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_mouse_down: optional object` `left_mouse_down`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_mouse_up: optional object` `left_mouse_up`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `middle_click: optional object` `middle_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `mouse_move: optional object` `mouse_move`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `right_click: optional object` `right_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `screenshot: optional object` `screenshot`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `scroll: optional object` `scroll`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `triple_click: optional object` `triple_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `wait: optional object` `wait`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `zoom: optional object` `zoom`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `beta_tool_text_editor_20250124: object` - `type: "text_editor_20250124"` - `name: "str_replace_editor"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_text_editor_20250429: object` - `type: "text_editor_20250429"` - `name: "str_replace_based_edit_tool"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_text_editor_20250728: object` - `type: "text_editor_20250728"` - `name: "str_replace_based_edit_tool"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: optional array of map[unknown]` - `max_characters: optional number` Maximum number of characters to display when viewing a file. If not specified, defaults to displaying the full file. minimum: 1 - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_web_search_tool_20250305: object` - `type: "web_search_20250305"` - `name: "web_search"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: optional array of string` If provided, only these domains will be included in results. Cannot be used alongside `blocked_domains`. - `blocked_domains: optional array of string` If provided, these domains will never appear in results. Cannot be used alongside `allowed_domains`. - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `user_location: optional object` Parameters for the user's location. Used to provide more relevant search results. - `type: "approximate"` - `city: optional string` The city of the user. minLength: 1, maxLength: 255 - `country: optional string` The two letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1_alpha-2) of the user. minLength: 2, maxLength: 2 - `region: optional string` The region of the user. minLength: 1, maxLength: 255 - `timezone: optional string` The [IANA timezone](https://nodatime.org/TimeZones) of the user. minLength: 1, maxLength: 255 - `beta_web_fetch_tool_20250910: object` - `type: "web_fetch_20250910"` - `name: "web_fetch"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: optional array of string` List of domains to allow fetching from - `blocked_domains: optional array of string` List of domains to block fetching from - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `citations: optional object` Citations configuration for fetched documents. Citations are disabled by default. - `enabled: optional boolean` - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_content_tokens: optional number` Maximum number of tokens used by including web page text content in the context. The limit is approximate and does not apply to binary content such as PDFs. minimum: 1 - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `url_sources: optional object` Which sources contribute to the set of URLs the tool may fetch. Omitted means every source. - `client_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which client tools' results contribute fetchable URLs: "all", "none", or an only or except list of client tool names from tools[]. - `beta_web_fetch_url_source_all: object` The `url_sources` variant under which a source contributes in full: every result of the tool filter's source, or all user input. - `type: "all"` - `beta_web_fetch_url_source_none: object` The `url_sources` variant under which a source contributes nothing: no result of the tool filter's source, or no user input. - `type: "none"` - `beta_web_fetch_url_source_only: object` The tool filter variant under which only the named tools' results contribute. - `type: "only"` - `tools: array of BetaWebFetchURLSourceToolReference` - `type: "tool_reference"` - `name: string` - `beta_web_fetch_url_source_except: object` The tool filter variant under which every result but the named tools' contributes. - `type: "except"` - `tools: array of BetaWebFetchURLSourceToolReference` - `type: "tool_reference"` - `name: string` - `server_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which server tools' results contribute fetchable URLs: "all", "none", or an only or except list of server tool names from tools[]; only web_search and web_fetch results ever contribute. - `beta_web_fetch_url_source_all: object` The `url_sources` variant under which a source contributes in full: every result of the tool filter's source, or all user input. - `beta_web_fetch_url_source_none: object` The `url_sources` variant under which a source contributes nothing: no result of the tool filter's source, or no user input. - `beta_web_fetch_url_source_only: object` The tool filter variant under which only the named tools' results contribute. - `beta_web_fetch_url_source_except: object` The tool filter variant under which every result but the named tools' contributes. - `user_input: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone` Whether URLs in user messages are fetchable: "all" or "none". - `beta_web_fetch_url_source_all: object` The `url_sources` variant under which a source contributes in full: every result of the tool filter's source, or all user input. - `beta_web_fetch_url_source_none: object` The `url_sources` variant under which a source contributes nothing: no result of the tool filter's source, or no user input. - `beta_web_search_tool_20260209: object` - `type: "web_search_20260209"` - `name: "web_search"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: optional array of string` If provided, only these domains will be included in results. Cannot be used alongside `blocked_domains`. - `blocked_domains: optional array of string` If provided, these domains will never appear in results. Cannot be used alongside `allowed_domains`. - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `user_location: optional object` Parameters for the user's location. Used to provide more relevant search results. - `type: "approximate"` - `city: optional string` The city of the user. minLength: 1, maxLength: 255 - `country: optional string` The two letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1_alpha-2) of the user. minLength: 2, maxLength: 2 - `region: optional string` The region of the user. minLength: 1, maxLength: 255 - `timezone: optional string` The [IANA timezone](https://nodatime.org/TimeZones) of the user. minLength: 1, maxLength: 255 - `beta_web_fetch_tool_20260209: object` - `type: "web_fetch_20260209"` - `name: "web_fetch"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: optional array of string` List of domains to allow fetching from - `blocked_domains: optional array of string` List of domains to block fetching from - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `citations: optional object` Citations configuration for fetched documents. Citations are disabled by default. - `enabled: optional boolean` - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_content_tokens: optional number` Maximum number of tokens used by including web page text content in the context. The limit is approximate and does not apply to binary content such as PDFs. minimum: 1 - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `url_sources: optional object` Which sources contribute to the set of URLs the tool may fetch. Omitted means every source. - `client_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which client tools' results contribute fetchable URLs: "all", "none", or an only or except list of client tool names from tools[]. - `server_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which server tools' results contribute fetchable URLs: "all", "none", or an only or except list of server tool names from tools[]; only web_search and web_fetch results ever contribute. - `user_input: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone` Whether URLs in user messages are fetchable: "all" or "none". - `beta_web_fetch_tool_20260309: object` Web fetch tool with use_cache parameter for bypassing cached content. - `type: "web_fetch_20260309"` - `name: "web_fetch"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: optional array of string` List of domains to allow fetching from - `blocked_domains: optional array of string` List of domains to block fetching from - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `citations: optional object` Citations configuration for fetched documents. Citations are disabled by default. - `enabled: optional boolean` - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_content_tokens: optional number` Maximum number of tokens used by including web page text content in the context. The limit is approximate and does not apply to binary content such as PDFs. minimum: 1 - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `url_sources: optional object` Which sources contribute to the set of URLs the tool may fetch. Omitted means every source. - `client_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which client tools' results contribute fetchable URLs: "all", "none", or an only or except list of client tool names from tools[]. - `server_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which server tools' results contribute fetchable URLs: "all", "none", or an only or except list of server tool names from tools[]; only web_search and web_fetch results ever contribute. - `user_input: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone` Whether URLs in user messages are fetchable: "all" or "none". - `use_cache: optional boolean` Whether to use cached content. Set to false to bypass the cache and fetch fresh content. Only set to false when the user explicitly requests fresh content or when fetching rapidly-changing sources. - `beta_web_search_tool_20260318: object` - `type: "web_search_20260318"` - `name: "web_search"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: optional array of string` If provided, only these domains will be included in results. Cannot be used alongside `blocked_domains`. - `blocked_domains: optional array of string` If provided, these domains will never appear in results. Cannot be used alongside `allowed_domains`. - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `response_inclusion: optional "full" or "excluded"` How this tool's result blocks appear in the API response when the result was consumed by a completed code_execution call in the same turn. 'full' returns the complete content (default). 'excluded' drops the nested server_tool_use and result block pair entirely. Results from direct calls, or from code_execution calls that paused before completing, are always returned in full so they can be sent back on the next turn. - `"full"` - `"excluded"` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `user_location: optional object` Parameters for the user's location. Used to provide more relevant search results. - `type: "approximate"` - `city: optional string` The city of the user. minLength: 1, maxLength: 255 - `country: optional string` The two letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1_alpha-2) of the user. minLength: 2, maxLength: 2 - `region: optional string` The region of the user. minLength: 1, maxLength: 255 - `timezone: optional string` The [IANA timezone](https://nodatime.org/TimeZones) of the user. minLength: 1, maxLength: 255 - `beta_web_fetch_tool_20260318: object` - `type: "web_fetch_20260318"` - `name: "web_fetch"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: optional array of string` List of domains to allow fetching from - `blocked_domains: optional array of string` List of domains to block fetching from - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `citations: optional object` Citations configuration for fetched documents. Citations are disabled by default. - `enabled: optional boolean` - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_content_tokens: optional number` Maximum number of tokens used by including web page text content in the context. The limit is approximate and does not apply to binary content such as PDFs. minimum: 1 - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `response_inclusion: optional "full" or "excluded"` How this tool's result blocks appear in the API response when the result was consumed by a completed code_execution call in the same turn. 'full' returns the complete content (default). 'excluded' drops the nested server_tool_use and result block pair entirely. Results from direct calls, or from code_execution calls that paused before completing, are always returned in full so they can be sent back on the next turn. - `"full"` - `"excluded"` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `url_sources: optional object` Which sources contribute to the set of URLs the tool may fetch. Omitted means every source. - `client_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which client tools' results contribute fetchable URLs: "all", "none", or an only or except list of client tool names from tools[]. - `server_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which server tools' results contribute fetchable URLs: "all", "none", or an only or except list of server tool names from tools[]; only web_search and web_fetch results ever contribute. - `user_input: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone` Whether URLs in user messages are fetchable: "all" or "none". - `use_cache: optional boolean` Whether to use cached content. Set to false to bypass the cache and fetch fresh content. Only set to false when the user explicitly requests fresh content or when fetching rapidly-changing sources. - `beta_advisor_tool_20260301: object` - `type: "advisor_20260301"` - `model: "claude-haiku-5-5" or "claude-sonnet-5-5" or "claude-fable-5-1" or 17 more or string` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-haiku-5-5"` Fastest model for high-volume, real-time tasks - `"claude-sonnet-5-5"` Efficient model for coding and agents - `"claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows - `"claude-opus-5-5"` Powerful intelligence for coding, knowledge work, and long-running agents - `"claude-mythos-5-1"` Our most capable model for cybersecurity and biology research, available through trusted access programs - `"claude-sonnet-5"` Efficient model for coding and agents - `"claude-fable-5"` Next generation of intelligence for the hardest knowledge work and coding problems - `"claude-mythos-5"` Most capable model for cybersecurity and biology research - `"claude-opus-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-8"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-7"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-6"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-6"` Best combination of speed and intelligence - `"claude-haiku-4-5"` - `"claude-haiku-4-5-20251001"` - `"claude-opus-4-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-5-20251101"` Powerful intelligence for long-running agents and coding - `"claude-mythos-preview"` **Deprecated**: Will reach end-of-life on June 30, 2026. Please migrate to claude-mythos-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. New class of intelligence, strongest in coding and cybersecurity - `"claude-sonnet-4-5"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `"claude-sonnet-4-5-20250929"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `name: "advisor"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `caching: optional object` Caching for the advisor's own prompt. When set, each advisor call writes a cache entry at the given TTL so subsequent calls in the same conversation read the stable prefix. When omitted, the advisor prompt is not cached. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_tokens: optional number` Bounds the advisor's total output (thinking + text) per call. When the advisor hits this cap, the returned advisor_result or advisor_redacted_result block carries stop_reason='max_tokens', and a truncation note is appended to the advice text the worker model sees (inside the encrypted blob in redacted mode). When set, the server also emits a remaining-tokens budget block in the advisor's prompt so the advisor self-shapes toward the cap. When omitted, the advisor model's default output cap applies and no budget block is emitted. minimum: 1024 - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_search_tool_bm25_20251119: object` - `type: "tool_search_tool_bm25_20251119" or "tool_search_tool_bm25"` - `"tool_search_tool_bm25_20251119"` - `"tool_search_tool_bm25"` - `name: "tool_search_tool_bm25"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_search_tool_regex_20251119: object` - `type: "tool_search_tool_regex_20251119" or "tool_search_tool_regex"` - `"tool_search_tool_regex_20251119"` - `"tool_search_tool_regex"` - `name: "tool_search_tool_regex"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_mcp_toolset: object` Configuration for a group of tools from an MCP server. Allows configuring enabled status and defer_loading for all tools from an MCP server, with optional per-tool overrides. - `type: "mcp_toolset"` - `mcp_server_name: string` Name of the MCP server to configure tools for minLength: 1, maxLength: 255 - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `configs: optional map[BetaMCPToolConfig]` Configuration overrides for specific tools, keyed by tool name - `defer_loading: optional boolean` - `enabled: optional boolean` - `default_config: optional object` Default configuration applied to all tools from this server - `defer_loading: optional boolean` - `enabled: optional boolean` - `tools: optional array of BetaMCPToolParam` The server's tool listing, pinned: when present, the server is not asked for its tools before sampling and exactly these entries, with `default_config` and `configs` applied, are the toolset's tools. Copy it from the `mcp_tool_listing` block of an earlier response. - `input_schema: map[unknown]` The tool's input schema as the MCP server lists it, verbatim. - `name: string` The tool's name as the MCP server lists it (not prefixed with the server name). minLength: 1 - `description: optional string` The tool's description as the MCP server lists it. - `beta_response_tool_removal_block: object` An entry of a `compaction` block's `tool_changes`: a tool of the request's `tools` (or an MCP tool or toolset) that the compacted range withdrew. Send it back unchanged. - `type: "tool_removal"` - `tool: BetaResponseToolChangeToolReference or BetaResponseToolChangeMCPToolReference or BetaResponseToolChangeMCPToolsetReference` A reference to the withdrawn `tools` entry, MCP tool or MCP toolset. - `beta_response_tool_change_tool_reference: object` Reference to a single tool, by the name the model uses to call it, as a `compaction` block's `tool_changes` entry reports it: a tool declared in `tools` or defined by an earlier `tool_addition` block. Send it back unchanged with the block. - `beta_response_tool_change_mcp_tool_reference: object` Reference to a single MCP tool, by its server and its name on that server, as a `compaction` block's `tool_changes` entry reports it. Send it back unchanged with the block. - `beta_response_tool_change_mcp_toolset_reference: object` Reference to every tool in the named MCP server's toolset, as a `compaction` block's `tool_changes` entry reports it. Send it back unchanged with the block. - `beta_fallback_block: object` Marks the point in `content` where one model's output gives way to the next. One block appears per hop where a preceding model actually ran this turn and declined. A turn where no preceding model ran and declined has no such boundary and carries no block — the signal for whether a fallback model served the response is the presence of a `fallback_message` entry in `usage.iterations`, not this block. The block is treated like a server-tool content block for streaming: it arrives via the standard `content_block_start` / `content_block_stop` pair and carries no deltas. - `type: "fallback"` - `from: object` The model whose output ends at this point — the model that declined at this hop. When the declining hop is the requested model, its `model` echoes the top-level `model` string the caller sent (alias or canonical); when the declining hop is a fallback model, its `model` is that model's canonical id. - `model: "claude-haiku-5-5" or "claude-sonnet-5-5" or "claude-fable-5-1" or 17 more or string` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-haiku-5-5"` Fastest model for high-volume, real-time tasks - `"claude-sonnet-5-5"` Efficient model for coding and agents - `"claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows - `"claude-opus-5-5"` Powerful intelligence for coding, knowledge work, and long-running agents - `"claude-mythos-5-1"` Our most capable model for cybersecurity and biology research, available through trusted access programs - `"claude-sonnet-5"` Efficient model for coding and agents - `"claude-fable-5"` Next generation of intelligence for the hardest knowledge work and coding problems - `"claude-mythos-5"` Most capable model for cybersecurity and biology research - `"claude-opus-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-8"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-7"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-6"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-6"` Best combination of speed and intelligence - `"claude-haiku-4-5"` - `"claude-haiku-4-5-20251001"` - `"claude-opus-4-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-5-20251101"` Powerful intelligence for long-running agents and coding - `"claude-mythos-preview"` **Deprecated**: Will reach end-of-life on June 30, 2026. Please migrate to claude-mythos-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. New class of intelligence, strongest in coding and cybersecurity - `"claude-sonnet-4-5"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `"claude-sonnet-4-5-20250929"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `to: object` The fallback model producing the content that follows this block. Its `model` is always the canonical id. - `model: "claude-haiku-5-5" or "claude-sonnet-5-5" or "claude-fable-5-1" or 17 more or string` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `trigger: object` What caused the `from` model to hand over at this hop. - `type: "refusal"` - `category: "cyber" or "bio" or "frontier_llm" or 2 more` The policy category that triggered the `from` model's refusal at this hop. `null` when the refusal doesn't map to a named category. Same vocabulary as `stop_details.category`. - `"cyber"` The request could enable cyber harm, such as malware or exploit development. Benign cybersecurity work can also trigger this category. - `"bio"` The request could enable biological harm, such as dangerous lab methods. Beneficial life sciences work can also trigger this category. - `"frontier_llm"` The request could assist the development of competing AI models, which is restricted under [Anthropic's commercial terms](https://www.anthropic.com/legal/commercial-terms). Benign machine learning work can also trigger this category. - `"reasoning_extraction"` The request asks the model to reproduce its internal reasoning in the response text. To get reasoning in a structured form instead, use [adaptive thinking](https://platform.claude.com/docs/en/build-with-claude/adaptive-thinking?sdk_languages=cli). - `"general_harms"` The request could be related to an area that was determined as harmful. Benign work might sometimes trigger this category. - `beta_mcp_tool_listing_block: object` The tool listing the server fetched from an MCP server while producing this response. Send the assistant message back unchanged, this block included, so later requests use this listing instead of asking the MCP server again. - `type: "mcp_tool_listing"` - `mcp_server_name: string` - `tools: array of BetaMCPTool` - `input_schema: map[unknown]` - `name: string` - `description: optional string` - `index: number` ### Beta Raw Content Block Stop Event - `beta_raw_content_block_stop_event: object` - `type: "content_block_stop"` - `index: number` ### Beta Raw Message Delta Event - `beta_raw_message_delta_event: object` - `type: "message_delta"` - `context_management: object` Information about context management strategies applied during the request - `applied_edits: array of BetaClearToolUses20250919EditResponse or BetaClearThinking20251015EditResponse` List of context management edits that were applied. - `beta_clear_tool_uses_20250919_edit_response: object` - `type: "clear_tool_uses_20250919"` The type of context management edit applied. - `cleared_input_tokens: number` Number of input tokens cleared by this edit. minimum: 0 - `cleared_tool_uses: number` Number of tool uses that were cleared. minimum: 0 - `beta_clear_thinking_20251015_edit_response: object` - `type: "clear_thinking_20251015"` The type of context management edit applied. - `cleared_input_tokens: number` Number of input tokens cleared by this edit. minimum: 0 - `cleared_thinking_turns: number` Number of thinking turns that were cleared. minimum: 0 - `delta: object` - `container: object` Information about the container used in this request. This will be non-null if a container tool (e.g. code execution) was used. - `id: string` Identifier for the container used in this request - `expires_at: string` The time at which the container will expire. format: date-time - `skills: array of BetaContainerSkill` Skills loaded in the container - `type: "anthropic" or "custom"` Type of skill - either 'anthropic' (built-in) or 'custom' (user-defined) - `"anthropic"` - `"custom"` - `skill_id: string` Skill ID minLength: 1, maxLength: 64 - `version: string` The resolved version: a skill version ID for custom skills. minLength: 1, maxLength: 64 - `stop_details: object` Structured information about why model output stopped. This is `null` when the `stop_reason` has no additional detail to report. - `type: "refusal"` - `category: "cyber" or "bio" or "frontier_llm" or 2 more` The policy category that triggered the refusal. `null` when the refusal doesn't map to a named category. - `"cyber"` The request could enable cyber harm, such as malware or exploit development. Benign cybersecurity work can also trigger this category. - `"bio"` The request could enable biological harm, such as dangerous lab methods. Beneficial life sciences work can also trigger this category. - `"frontier_llm"` The request could assist the development of competing AI models, which is restricted under [Anthropic's commercial terms](https://www.anthropic.com/legal/commercial-terms). Benign machine learning work can also trigger this category. - `"reasoning_extraction"` The request asks the model to reproduce its internal reasoning in the response text. To get reasoning in a structured form instead, use [adaptive thinking](https://platform.claude.com/docs/en/build-with-claude/adaptive-thinking?sdk_languages=cli). - `"general_harms"` The request could be related to an area that was determined as harmful. Benign work might sometimes trigger this category. - `explanation: string` Human-readable explanation of the refusal. This text is not guaranteed to be stable. `null` when no explanation is available for the category. - `fallback_credit_token: string` Opaque code that refunds the cache-miss cost when retrying this refused request on the fallback model. Pass it as `fallback_credit_token` on the retry request. Expires 5 minutes after the refusal. The retry is sent either with the same request body (`system`, `messages`, `tools`, and other render-shaping fields), or with the same body plus one appended `assistant` message whose content is the partial text (with any trailing whitespace stripped from the final text block) and paired server-tool blocks from this refusal — which also authorizes that appended turn as an assistant-prefill continuation on models that otherwise disallow prefill. A token minted mid-server-tool-loop whose partial content was continuable may only be redeemed the second way — if a same-body retry is rejected with a 400 saying the token must be redeemed by continuing the partial response, retry the second way instead. Either way: same workspace, same platform; a mismatch is a 400. Resending a token for an already-warm prefix is permitted but yields no additional credit. `null` when the refused model isn't eligible for a fallback credit. - `fallback_has_prefill_claim: boolean` Whether the accompanying `fallback_credit_token` may be redeemed with the appended-assistant retry form. Only set when `fallback_credit_token` is present. `true`: retry by resending the same request body plus one appended `assistant` message whose content is this response's `content` with any trailing whitespace stripped from the final text block and unpaired `tool_use` blocks omitted (the same appended-turn shape described on `fallback_credit_token`), with the token attached. `false`: retry by resending the original request body unchanged, with the token attached — the appended-assistant form is not available for this refusal (no continuable partial content, or the request uses `output_format` or a `tool_choice` that forces tool use). One exception: when the request used `output_format` or a forced `tool_choice` and the refusal arrived after server tools (including MCP connector tools) had already executed, the token may not be redeemable by either retry form; if the exact-body retry is then rejected with a 400 saying the token must be redeemed by continuing the partial response, discard the token and retry without it. Advisory: if an appended-assistant retry is rejected with a 400 despite `true`, fall back to resending the original request body with the token. - `recommended_model: string` The server's suggested retry target for this refusal. Populated when a fallback attempt could not be made (the fallback model's rate limit was exhausted, or it was overloaded); names the fallback model the caller can retry directly. Null otherwise. - `stop_reason: "end_turn" or "max_tokens" or "stop_sequence" or 5 more` - `"end_turn"` - `"max_tokens"` - `"stop_sequence"` - `"tool_use"` - `"pause_turn"` - `"compaction"` - `"refusal"` - `"model_context_window_exceeded"` - `stop_sequence: string` - `usage: object` Billing and rate-limit usage. Anthropic's API bills and rate-limits by token counts, as tokens represent the underlying cost to our systems. Under the hood, the API transforms requests into a format suitable for the model. The model's output then goes through a parsing stage before becoming an API response. As a result, the token counts in `usage` will not match one-to-one with the exact visible content of an API request or response. For example, `output_tokens` will be non-zero, even for an empty string response from Claude. Total input tokens in a request is the summation of `input_tokens`, `cache_creation_input_tokens`, and `cache_read_input_tokens`. - `cache_creation_input_tokens: number` The cumulative number of input tokens used to create the cache entry. minimum: 0 - `cache_read_input_tokens: number` The cumulative number of input tokens read from the cache. minimum: 0 - `fallback_credit: object` Outcome of the `fallback_credit_token` presented on this request. Present on every response to a non-batch request that carried a `fallback_credit_token`, in either redemption mode; absent otherwise (batch items accept and ignore the token and carry no outcome object). - `status: BetaFallbackCreditRedeemed or BetaFallbackCreditNotApplied` Whether the fallback-credit reprice was applied to this response's billing. A union discriminated on `type`. `redeemed`: the retry is billed as if the conversation had been on the retry model all along — including when the resulting shift is zero because there was nothing to move. `not_applied`: no reprice was applied; the arm's `reason` says why. - `beta_fallback_credit_redeemed: object` The reprice was applied: the retry is billed as if the conversation had been on the retry model all along. - `type: "redeemed"` - `beta_fallback_credit_not_applied: object` No reprice was applied; `reason` says why. - `type: "not_applied"` - `reason: "body_mismatch" or "continuation_excluded" or "continuation_only" or 9 more` Why the reprice was not applied. A closed enum; additions to the redemption-check vocabulary arrive as deliberate schema updates. - `"body_mismatch"` - `"continuation_excluded"` - `"continuation_only"` - `"expired"` - `"invalid_target_model"` - `"not_enabled"` - `"reprice_unavailable"` - `"temporarily_unavailable"` - `"variant_fields_present"` - `"wrong_organization"` - `"wrong_platform"` - `"wrong_workspace"` - `remove_to_redeem: optional array of string` Request fields to remove before retrying, so the retry can redeem this token. Present exactly when `reason` is `variant_fields_present` — never null, never an empty array; absent otherwise. Fields are named only from your own request, and only after the sealed variant hash matched. A served best-effort retry has already been billed at normal price; nothing redeems retroactively, but a corrected re-send inside the token's five-minute window can still redeem. - `input_tokens: number` The cumulative number of input tokens which were used. minimum: 0 - `iterations: array of BetaMessageIterationUsage or BetaCompactionIterationUsage or BetaAdvisorMessageIterationUsage or BetaFallbackMessageIterationUsage` Per-iteration token usage breakdown. Each entry represents one sampling iteration, with its own input/output token counts and cache statistics, discriminated by `type`. For `message` entries (model sampling iterations, such as the turns of a server-side tool use loop), this allows you to: - Calculate the context window size from the last `message` entry - Understand token accumulation across server-side tool use loops A `compaction` entry reports the token usage of the compaction operation itself — the server-side request that summarizes the context being closed — NOT the size of the context that was compacted away, and its token counts can be much smaller than that closed context (for example, a compaction that closes a ~200k-token context can report only a few thousand tokens). Do not derive the context window size from a `compaction` entry, even when it is the last entry. A `compaction` entry's tokens are not included in the top-level `usage` fields. When an input-token trigger is in effect (the default — 150,000 tokens unless configured otherwise), each `compaction` entry closes a context that had reached at least that threshold, though the context can exceed it by the final iteration's output and tool results. - `beta_message_iteration_usage: object` Token usage for a sampling iteration. - `type: "message"` Usage for a sampling iteration - `cache_creation: object` Breakdown of cached tokens by TTL - `ephemeral_1h_input_tokens: number` The number of input tokens used to create the 1 hour cache entry. minimum: 0 - `ephemeral_5m_input_tokens: number` The number of input tokens used to create the 5 minute cache entry. minimum: 0 - `cache_creation_input_tokens: number` The number of input tokens used to create the cache entry. minimum: 0 - `cache_read_input_tokens: number` The number of input tokens read from the cache. minimum: 0 - `input_tokens: number` The number of input tokens which were used. minimum: 0 - `model: "claude-haiku-5-5" or "claude-sonnet-5-5" or "claude-fable-5-1" or 17 more or string` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-haiku-5-5"` Fastest model for high-volume, real-time tasks - `"claude-sonnet-5-5"` Efficient model for coding and agents - `"claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows - `"claude-opus-5-5"` Powerful intelligence for coding, knowledge work, and long-running agents - `"claude-mythos-5-1"` Our most capable model for cybersecurity and biology research, available through trusted access programs - `"claude-sonnet-5"` Efficient model for coding and agents - `"claude-fable-5"` Next generation of intelligence for the hardest knowledge work and coding problems - `"claude-mythos-5"` Most capable model for cybersecurity and biology research - `"claude-opus-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-8"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-7"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-6"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-6"` Best combination of speed and intelligence - `"claude-haiku-4-5"` - `"claude-haiku-4-5-20251001"` - `"claude-opus-4-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-5-20251101"` Powerful intelligence for long-running agents and coding - `"claude-mythos-preview"` **Deprecated**: Will reach end-of-life on June 30, 2026. Please migrate to claude-mythos-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. New class of intelligence, strongest in coding and cybersecurity - `"claude-sonnet-4-5"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `"claude-sonnet-4-5-20250929"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `output_tokens: number` The number of output tokens which were used. minimum: 0 - `beta_compaction_iteration_usage: object` Token usage for a compaction iteration. - `type: "compaction"` Usage for a compaction iteration - `cache_creation: object` Breakdown of cached tokens by TTL - `ephemeral_1h_input_tokens: number` The number of input tokens used to create the 1 hour cache entry. minimum: 0 - `ephemeral_5m_input_tokens: number` The number of input tokens used to create the 5 minute cache entry. minimum: 0 - `cache_creation_input_tokens: number` The number of input tokens used to create the cache entry. minimum: 0 - `cache_read_input_tokens: number` The number of input tokens read from the cache. minimum: 0 - `input_tokens: number` The number of input tokens which were used. minimum: 0 - `output_tokens: number` The number of output tokens which were used. minimum: 0 - `beta_advisor_message_iteration_usage: object` Token usage for an advisor sub-inference iteration. - `type: "advisor_message"` Usage for an advisor sub-inference iteration - `cache_creation: object` Breakdown of cached tokens by TTL - `ephemeral_1h_input_tokens: number` The number of input tokens used to create the 1 hour cache entry. minimum: 0 - `ephemeral_5m_input_tokens: number` The number of input tokens used to create the 5 minute cache entry. minimum: 0 - `cache_creation_input_tokens: number` The number of input tokens used to create the cache entry. minimum: 0 - `cache_read_input_tokens: number` The number of input tokens read from the cache. minimum: 0 - `input_tokens: number` The number of input tokens which were used. minimum: 0 - `model: "claude-haiku-5-5" or "claude-sonnet-5-5" or "claude-fable-5-1" or 17 more or string` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-haiku-5-5"` Fastest model for high-volume, real-time tasks - `"claude-sonnet-5-5"` Efficient model for coding and agents - `"claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows - `"claude-opus-5-5"` Powerful intelligence for coding, knowledge work, and long-running agents - `"claude-mythos-5-1"` Our most capable model for cybersecurity and biology research, available through trusted access programs - `"claude-sonnet-5"` Efficient model for coding and agents - `"claude-fable-5"` Next generation of intelligence for the hardest knowledge work and coding problems - `"claude-mythos-5"` Most capable model for cybersecurity and biology research - `"claude-opus-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-8"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-7"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-6"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-6"` Best combination of speed and intelligence - `"claude-haiku-4-5"` - `"claude-haiku-4-5-20251001"` - `"claude-opus-4-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-5-20251101"` Powerful intelligence for long-running agents and coding - `"claude-mythos-preview"` **Deprecated**: Will reach end-of-life on June 30, 2026. Please migrate to claude-mythos-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. New class of intelligence, strongest in coding and cybersecurity - `"claude-sonnet-4-5"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `"claude-sonnet-4-5-20250929"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `output_tokens: number` The number of output tokens which were used. minimum: 0 - `beta_fallback_message_iteration_usage: object` Token usage for the fallback-model attempt of a server-side fallback request. The terminal entry of a fallback-served turn: when a fallback hop's output is the returned message, the entry for the iteration that completed it carries this type in place of `message`. A declined hop and the serving hop's earlier tool-loop iterations produce `message` entries. Whether a fallback model served the response is signalled by the presence of this entry in `usage.iterations`. - `type: "fallback_message"` Usage for the fallback-model attempt that served the response - `cache_creation: object` Breakdown of cached tokens by TTL - `ephemeral_1h_input_tokens: number` The number of input tokens used to create the 1 hour cache entry. minimum: 0 - `ephemeral_5m_input_tokens: number` The number of input tokens used to create the 5 minute cache entry. minimum: 0 - `cache_creation_input_tokens: number` The number of input tokens used to create the cache entry. minimum: 0 - `cache_read_input_tokens: number` The number of input tokens read from the cache. minimum: 0 - `input_tokens: number` The number of input tokens which were used. minimum: 0 - `model: "claude-haiku-5-5" or "claude-sonnet-5-5" or "claude-fable-5-1" or 17 more or string` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-haiku-5-5"` Fastest model for high-volume, real-time tasks - `"claude-sonnet-5-5"` Efficient model for coding and agents - `"claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows - `"claude-opus-5-5"` Powerful intelligence for coding, knowledge work, and long-running agents - `"claude-mythos-5-1"` Our most capable model for cybersecurity and biology research, available through trusted access programs - `"claude-sonnet-5"` Efficient model for coding and agents - `"claude-fable-5"` Next generation of intelligence for the hardest knowledge work and coding problems - `"claude-mythos-5"` Most capable model for cybersecurity and biology research - `"claude-opus-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-8"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-7"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-6"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-6"` Best combination of speed and intelligence - `"claude-haiku-4-5"` - `"claude-haiku-4-5-20251001"` - `"claude-opus-4-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-5-20251101"` Powerful intelligence for long-running agents and coding - `"claude-mythos-preview"` **Deprecated**: Will reach end-of-life on June 30, 2026. Please migrate to claude-mythos-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. New class of intelligence, strongest in coding and cybersecurity - `"claude-sonnet-4-5"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `"claude-sonnet-4-5-20250929"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `output_tokens: number` The number of output tokens which were used. minimum: 0 - `output_tokens: number` The cumulative number of output tokens which were used. - `output_tokens_details: object` Breakdown of output tokens by category. `output_tokens` remains the inclusive, authoritative total used for billing. This object provides a read-only decomposition for observability — for example, how many of the billed output tokens were spent on internal reasoning that may have been summarized before being returned to you. - `thinking_tokens: number` Number of output tokens the model generated as internal reasoning, including the thinking-block delimiter tokens. Reflects the raw reasoning the model produced, not the (possibly shorter) summarized thinking text returned in the response body. Computed by re-tokenizing the raw reasoning text, so it may differ from the model's exact generation count by a small number of tokens. Always ≤ `output_tokens`; `output_tokens - thinking_tokens` approximates the non-reasoning output. minimum: 0 - `server_tool_use: object` The number of server tool requests. - `web_fetch_requests: number` The number of web fetch tool requests. minimum: 0 - `web_search_requests: number` The number of web search tool requests. minimum: 0 - `input_transformations: optional array of BetaInputTransformation` Changes the API made to the request's input before showing it to the model, and blocks that failed a binding check but were left unchanged: one entry per block, in request order. Two entry types today. `thinking_dropped` — a `thinking`, `redacted_thinking` or `connector_text` block from the request's `messages` that was removed from the prompt instead of being shown to the model because it failed a binding check. `thinking_mismatch_allowed` — a `thinking` or `redacted_thinking` block that failed the conversation check (the conversation before it differs from the one it was created in, or it carries no record of one on a model that requires it) and was shown to the model all the same, because that check is not enforced for this request. More entry types may be added over time; ignore types you do not recognize. Requires `anthropic-beta: thinking-binding-controls-2026-08-01`. Present on every such response from a model that supports extended thinking, as `[]` when there is no entry to report; without the beta, blocks are removed or left in place all the same but nothing is reported. Removed blocks contribute nothing to `usage.input_tokens`; blocks left in place count as sent. When streaming, the array is final in `message_start`; the final `message_delta` event carries it only when a server-side model fallback happened mid-stream, in which case it holds the serving model's entries and replaces the one in `message_start`. - `beta_thinking_dropped_input_transformation: object` - `type: "thinking_dropped"` Always `thinking_dropped` for this entry type. - `path: string` Where the removed block was in your request, as `messages.{i}.content.{j}`: `i` indexes the `messages` array you sent and `j` that message's `content` array — the same form error messages use. - `reason: "model_binding_mismatch" or "prefix_binding_mismatch" or "organization_binding_mismatch" or "end_user_binding_mismatch"` Which binding check removed the block: `model_binding_mismatch` — it was created by a model whose reasoning the requested model may not read; `prefix_binding_mismatch` — the conversation before it differs from the conversation it was created in (the rest of that turn's consecutive thinking blocks are removed with it, each with this reason); `organization_binding_mismatch` — it was created under a different organization (an Anthropic organization, AWS account or Google Cloud project) and this organization is not one of its additional organizations; `end_user_binding_mismatch` — it was created for a different end user, or was removed by the consumer-organization binding. A block that would fail several checks reports one reason, in this order of precedence: `organization_binding_mismatch`, `end_user_binding_mismatch`, `model_binding_mismatch`, `prefix_binding_mismatch`. - `"model_binding_mismatch"` - `"prefix_binding_mismatch"` - `"organization_binding_mismatch"` - `"end_user_binding_mismatch"` - `beta_thinking_mismatch_allowed_input_transformation: object` - `type: "thinking_mismatch_allowed"` Always `thinking_mismatch_allowed` for this entry type. - `path: string` Where the block is in your request, as `messages.{i}.content.{j}`: `i` indexes the `messages` array you sent and `j` that message's `content` array — the same form error messages use. - `reason: "model_binding_mismatch" or "prefix_binding_mismatch" or "organization_binding_mismatch" or "end_user_binding_mismatch"` Which binding check the block failed; the block was shown to the model all the same. Always `prefix_binding_mismatch` today — the conversation before the block differs from the conversation it was created in, or the block carries no record of one on a model that requires it. Were the check enforced for this request, the block would have been removed or the request rejected (`thinking.block_binding.prefix_mismatch_behavior`). A removal also takes the rest of that turn's consecutive thinking blocks, whereas here each block is checked on its own, so `thinking_mismatch_allowed` entries are a lower bound on what enforcement would remove. - `"model_binding_mismatch"` - `"prefix_binding_mismatch"` - `"organization_binding_mismatch"` - `"end_user_binding_mismatch"` ### Beta Raw Message Start Event - `beta_raw_message_start_event: object` - `type: "message_start"` - `message: object` - `type: "message"` Object type. For Messages, this is always `"message"`. - `id: string` Unique object identifier. The format and length of IDs may change over time. - `container: object` Information about the container used in this request. This will be non-null if a container tool (e.g. code execution) was used. - `id: string` Identifier for the container used in this request - `expires_at: string` The time at which the container will expire. format: date-time - `skills: array of BetaContainerSkill` Skills loaded in the container - `type: "anthropic" or "custom"` Type of skill - either 'anthropic' (built-in) or 'custom' (user-defined) - `"anthropic"` - `"custom"` - `skill_id: string` Skill ID minLength: 1, maxLength: 64 - `version: string` The resolved version: a skill version ID for custom skills. minLength: 1, maxLength: 64 - `content: array of BetaContentBlock` Content generated by the model. This is an array of content blocks, each of which has a `type` that determines its shape. Example: ```json [{"type": "text", "text": "Hi, I'm Claude."}] ``` If the request input `messages` ended with an `assistant` turn, then the response `content` will continue directly from that last turn. You can use this to constrain the model's output. For example, if the input `messages` were: ```json [ {"role": "user", "content": "What's the Greek name for Sun? (A) Sol (B) Helios (C) Sun"}, {"role": "assistant", "content": "The best answer is ("} ] ``` Then the response `content` might be: ```json [{"type": "text", "text": "B)"}] ``` - `beta_text_block: object` - `type: "text"` - `citations: array of BetaTextCitation` Citations supporting the text block. The type of citation returned will depend on the type of document being cited. Citing a PDF results in `page_location`, plain text results in `char_location`, and content document results in `content_block_location`. - `beta_citation_char_location: object` - `type: "char_location"` - `cited_text: string` - `document_index: number` minimum: 0 - `document_title: string` - `end_char_index: number` - `file_id: string` - `start_char_index: number` minimum: 0 - `beta_citation_page_location: object` - `type: "page_location"` - `cited_text: string` - `document_index: number` minimum: 0 - `document_title: string` - `end_page_number: number` - `file_id: string` - `start_page_number: number` minimum: 1 - `beta_citation_content_block_location: object` - `type: "content_block_location"` - `cited_text: string` The full text of the cited block range, concatenated. Always equals the contents of `content[start_block_index:end_block_index]` joined together. The text block is the minimal citable unit; this field is never a substring of a single block. Not counted toward output tokens, and not counted toward input tokens when sent back in subsequent turns. - `document_index: number` minimum: 0 - `document_title: string` - `end_block_index: number` Exclusive 0-based end index of the cited block range in the source's `content` array. Always greater than `start_block_index`; a single-block citation has `end_block_index = start_block_index + 1`. - `file_id: string` - `start_block_index: number` 0-based index of the first cited block in the source's `content` array. minimum: 0 - `beta_citations_web_search_result_location: object` - `type: "web_search_result_location"` - `cited_text: string` - `encrypted_index: string` - `title: string` maxLength: 512 - `url: string` - `beta_citation_search_result_location: object` - `type: "search_result_location"` - `cited_text: string` The full text of the cited block range, concatenated. Always equals the contents of `content[start_block_index:end_block_index]` joined together. The text block is the minimal citable unit; this field is never a substring of a single block. Not counted toward output tokens, and not counted toward input tokens when sent back in subsequent turns. - `end_block_index: number` Exclusive 0-based end index of the cited block range in the source's `content` array. Always greater than `start_block_index`; a single-block citation has `end_block_index = start_block_index + 1`. - `search_result_index: number` 0-based index of the cited search result among all `search_result` content blocks in the request, in the order they appear across messages and tool results. Counted separately from `document_index`; server-side web search results are not included in this count. minimum: 0 - `source: string` - `start_block_index: number` 0-based index of the first cited block in the source's `content` array. minimum: 0 - `title: string` - `text: string` - `beta_thinking_block: object` - `type: "thinking"` - `signature: string` A value used to verify that this thinking block was generated by Claude when it is passed back to the API. This is an opaque field and should not be interpreted or parsed. When passing thinking blocks back to the API (required when using tools with extended thinking), pass them back exactly as received, with this field intact. See [extended thinking](https://platform.claude.com/docs/en/build-with-claude/extended-thinking?sdk_languages=cli) for details. - `thinking: string` The text of Claude's thinking process for this block. - `beta_redacted_thinking_block: object` - `type: "redacted_thinking"` - `data: string` The contents of this redacted thinking block, returned when portions of the model's thinking were safety-redacted. This field is opaque and encrypted, with no readable content. Pass `redacted_thinking` blocks back to the API unchanged when continuing a multi-turn conversation. See [extended thinking](https://platform.claude.com/docs/en/build-with-claude/extended-thinking?sdk_languages=cli#redacted-thinking-blocks) for details. - `beta_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: map[unknown]` - `name: string` minLength: 1 - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` - `beta_direct_caller: object` Tool invocation directly from the model. - `type: "direct"` - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `type: "code_execution_20250825"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `beta_server_tool_caller_20260120: object` - `type: "code_execution_20260120"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `toolset_name: optional string` For a toolset member tool_use, the toolset family. minLength: 1, maxLength: 64, pattern: ^[a-zA-Z0-9_-]+$ - `beta_server_tool_use_block: object` - `type: "server_tool_use"` - `id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `input: map[unknown]` - `name: "advisor" or "web_search" or "web_fetch" or 5 more` - `"advisor"` - `"web_search"` - `"web_fetch"` - `"code_execution"` - `"bash_code_execution"` - `"text_editor_code_execution"` - `"tool_search_tool_regex"` - `"tool_search_tool_bm25"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` - `beta_direct_caller: object` Tool invocation directly from the model. - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `beta_server_tool_caller_20260120: object` - `beta_web_search_tool_result_block: object` - `type: "web_search_tool_result"` - `content: BetaWebSearchToolResultError or array of BetaWebSearchResultBlock` - `beta_web_search_tool_result_error: object` - `type: "web_search_tool_result_error"` - `error_code: "invalid_tool_input" or "unavailable" or "max_uses_exceeded" or 3 more` - `"invalid_tool_input"` - `"unavailable"` - `"max_uses_exceeded"` - `"too_many_requests"` - `"query_too_long"` - `"request_too_large"` - `union_member_1: array of BetaWebSearchResultBlock` - `type: "web_search_result"` - `encrypted_content: string` - `page_age: string` - `title: string` - `url: string` - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` - `beta_direct_caller: object` Tool invocation directly from the model. - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `beta_server_tool_caller_20260120: object` - `beta_web_fetch_tool_result_block: object` - `type: "web_fetch_tool_result"` - `content: BetaWebFetchToolResultErrorBlock or BetaWebFetchBlock` - `beta_web_fetch_tool_result_error_block: object` - `type: "web_fetch_tool_result_error"` - `error_code: "invalid_tool_input" or "url_too_long" or "url_not_allowed" or 7 more` - `"invalid_tool_input"` - `"url_too_long"` - `"url_not_allowed"` - `"url_not_in_prior_context"` - `"url_not_accessible"` - `"unsupported_content_type"` - `"too_many_requests"` - `"max_uses_exceeded"` - `"unavailable"` - `"content_too_large"` - `beta_web_fetch_block: object` - `type: "web_fetch_result"` - `content: object` - `type: "document"` - `citations: object` Citation configuration for the document - `enabled: boolean` - `source: BetaBase64PDFSource or BetaPlainTextSource` - `beta_base64_pdf_source: object` - `type: "base64"` - `data: string` format: byte - `media_type: "application/pdf"` - `beta_plain_text_source: object` - `type: "text"` - `data: string` - `media_type: "text/plain"` - `title: string` The title of the document - `retrieved_at: string` ISO 8601 timestamp when the content was retrieved - `url: string` Fetched content URL - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` - `beta_direct_caller: object` Tool invocation directly from the model. - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `beta_server_tool_caller_20260120: object` - `beta_advisor_tool_result_block: object` - `type: "advisor_tool_result"` - `content: BetaAdvisorToolResultError or BetaAdvisorResultBlock or BetaAdvisorRedactedResultBlock` - `beta_advisor_tool_result_error: object` - `type: "advisor_tool_result_error"` - `error_code: "max_uses_exceeded" or "prompt_too_long" or "too_many_requests" or 4 more` - `"max_uses_exceeded"` - `"prompt_too_long"` - `"too_many_requests"` - `"overloaded"` - `"unavailable"` - `"execution_time_exceeded"` - `"model_not_found"` - `beta_advisor_result_block: object` - `type: "advisor_result"` - `stop_reason: string` The advisor sub-inference's stop reason (same values as the top-level message `stop_reason`). `max_tokens` indicates the advisor's output was truncated at the tool's `max_tokens` value or the advisor model's policy cap. - `text: string` - `beta_advisor_redacted_result_block: object` - `type: "advisor_redacted_result"` - `encrypted_content: string` Opaque blob containing the advisor's output. Round-trip verbatim; do not inspect or modify. - `stop_reason: string` The advisor sub-inference's stop reason (same values as the top-level message `stop_reason`). - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `beta_code_execution_tool_result_block: object` - `type: "code_execution_tool_result"` - `content: BetaCodeExecutionToolResultError or BetaCodeExecutionResultBlock or BetaEncryptedCodeExecutionResultBlock` - `beta_code_execution_tool_result_error: object` - `type: "code_execution_tool_result_error"` - `error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or "execution_time_exceeded"` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `beta_code_execution_result_block: object` - `type: "code_execution_result"` - `content: array of BetaCodeExecutionOutputBlock` - `type: "code_execution_output"` - `file_id: string` - `return_code: number` - `stderr: string` - `stdout: string` - `beta_encrypted_code_execution_result_block: object` Code execution result with encrypted stdout for PFC + web_search results. - `type: "encrypted_code_execution_result"` - `content: array of BetaCodeExecutionOutputBlock` - `type: "code_execution_output"` - `file_id: string` - `encrypted_stdout: string` - `return_code: number` - `stderr: string` - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `beta_bash_code_execution_tool_result_block: object` - `type: "bash_code_execution_tool_result"` - `content: BetaBashCodeExecutionToolResultError or BetaBashCodeExecutionResultBlock` - `beta_bash_code_execution_tool_result_error: object` - `type: "bash_code_execution_tool_result_error"` - `error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or 2 more` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `"output_file_too_large"` - `beta_bash_code_execution_result_block: object` - `type: "bash_code_execution_result"` - `content: array of BetaBashCodeExecutionOutputBlock` - `type: "bash_code_execution_output"` - `file_id: string` - `return_code: number` - `stderr: string` - `stdout: string` - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `beta_text_editor_code_execution_tool_result_block: object` - `type: "text_editor_code_execution_tool_result"` - `content: BetaTextEditorCodeExecutionToolResultError or BetaTextEditorCodeExecutionViewResultBlock or BetaTextEditorCodeExecutionCreateResultBlock or BetaTextEditorCodeExecutionStrReplaceResultBlock` - `beta_text_editor_code_execution_tool_result_error: object` - `type: "text_editor_code_execution_tool_result_error"` - `error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or 2 more` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `"file_not_found"` - `error_message: string` - `beta_text_editor_code_execution_view_result_block: object` - `type: "text_editor_code_execution_view_result"` - `content: string` - `file_type: "text" or "image" or "pdf"` - `"text"` - `"image"` - `"pdf"` - `num_lines: number` - `start_line: number` - `total_lines: number` - `beta_text_editor_code_execution_create_result_block: object` - `type: "text_editor_code_execution_create_result"` - `is_file_update: boolean` - `beta_text_editor_code_execution_str_replace_result_block: object` - `type: "text_editor_code_execution_str_replace_result"` - `lines: array of string` - `new_lines: number` - `new_start: number` - `old_lines: number` - `old_start: number` - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `beta_tool_search_tool_result_block: object` - `type: "tool_search_tool_result"` - `content: BetaToolSearchToolResultError or BetaToolSearchToolSearchResultBlock` - `beta_tool_search_tool_result_error: object` - `type: "tool_search_tool_result_error"` - `error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or "execution_time_exceeded"` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `error_message: string` - `beta_tool_search_tool_search_result_block: object` - `type: "tool_search_tool_search_result"` - `tool_references: array of BetaToolReferenceBlock` - `type: "tool_reference"` - `tool_name: string` minLength: 1, maxLength: 256, pattern: ^[a-zA-Z0-9_-]{1,256}$ - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `beta_mcp_tool_use_block: object` - `type: "mcp_tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: map[unknown]` - `name: string` The name of the MCP tool - `server_name: string` The name of the MCP server - `beta_mcp_tool_result_block: object` - `type: "mcp_tool_result"` - `content: string or array of BetaTextBlock` - `union_member_0: string` - `beta_mcp_tool_result_block_content: array of BetaTextBlock` - `type: "text"` - `citations: array of BetaTextCitation` Citations supporting the text block. The type of citation returned will depend on the type of document being cited. Citing a PDF results in `page_location`, plain text results in `char_location`, and content document results in `content_block_location`. - `text: string` - `is_error: boolean` - `tool_use_id: string` pattern: ^[a-zA-Z0-9_-]+$ - `beta_container_upload_block: object` Response model for a file uploaded to the container. - `type: "container_upload"` - `file_id: string` - `beta_compaction_block: object` A compaction block returned when autocompact is triggered. When content is None, it indicates the compaction failed to produce a valid summary (e.g., malformed output from the model). Clients may round-trip compaction blocks with null content; the server treats them as no-ops. - `type: "compaction"` - `content: string` Summary of compacted content, or null if compaction failed - `encrypted_content: string` Opaque metadata from prior compaction, to be round-tripped verbatim - `signature: optional string` Signature over the summary, to be sent back with the block verbatim - `tool_changes: optional array of BetaResponseToolAdditionBlock or BetaResponseToolRemovalBlock` The tool changes of the compacted range: the `tool_addition` and `tool_removal` blocks that take the request's `tools` to the tool set in effect at the end of the range, or `[]` when the range changed no tool. Absent when the server did not compute them. Send the block back unchanged. - `beta_response_tool_addition_block: object` An entry of a `compaction` block's `tool_changes`: a tool the compacted range made available, as a reference to a `tools` entry or MCP toolset, or as the tool definition in effect at the end of the range, by value. Send it back unchanged. - `type: "tool_addition"` - `tool: BetaResponseToolChangeToolReference or BetaResponseToolChangeMCPToolReference or BetaResponseToolChangeMCPToolsetReference or BetaToolChangeToolDefinition` The tool made available: a reference to a `tools` entry or MCP toolset, or a `tool_definition` carrying the definition by value. - `beta_response_tool_change_tool_reference: object` Reference to a single tool, by the name the model uses to call it, as a `compaction` block's `tool_changes` entry reports it: a tool declared in `tools` or defined by an earlier `tool_addition` block. Send it back unchanged with the block. - `type: "tool_reference"` - `name: string` - `beta_response_tool_change_mcp_tool_reference: object` Reference to a single MCP tool, by its server and its name on that server, as a `compaction` block's `tool_changes` entry reports it. Send it back unchanged with the block. - `type: "mcp_tool_reference"` - `name: string` - `server_name: string` - `beta_response_tool_change_mcp_toolset_reference: object` Reference to every tool in the named MCP server's toolset, as a `compaction` block's `tool_changes` entry reports it. Send it back unchanged with the block. - `type: "mcp_toolset_reference"` - `server_name: string` - `beta_tool_change_tool_definition: object` A tool defined by value, as a `compaction` block's `tool_changes` entry reports it: `definition` is the tool's definition as it was sent, in the form of a `tools` entry, without `cache_control`. Send it back unchanged with the block. - `type: "tool_definition"` - `definition: BetaResponseTool or BetaToolBash20241022 or BetaToolBash20250124 or 25 more` - `beta_response_tool: object` A custom tool definition, as sent. - `type: optional "custom"` - `input_schema: object` [JSON schema](https://json-schema.org/draft/2020-12) for this tool's input. This defines the shape of the `input` that your tool accepts and that the model will produce. - `type: "object"` - `properties: optional map[unknown]` - `required: optional array of string` - `name: string` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. minLength: 1, maxLength: 128, pattern: ^[a-zA-Z0-9_-]{1,128}$ - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `description: optional string` Description of what this tool does. Tool descriptions should be as detailed as possible. The more information that the model has about what the tool is and how to use it, the better it will perform. You can use natural language descriptions to reinforce important aspects of the tool input JSON schema. - `eager_input_streaming: optional boolean` Enable eager input streaming for this tool. When true, tool input parameters will be streamed incrementally as they are generated, and types will be inferred on-the-fly rather than buffering the full JSON output. When false, streaming is disabled for this tool even if the fine-grained-tool-streaming beta is active. When null (default), uses the default behavior based on beta headers. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_bash_20241022: object` - `type: "bash_20241022"` - `name: "bash"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `"5m"` - `"1h"` - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_bash_20250124: object` - `type: "bash_20250124"` - `name: "bash"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_code_execution_tool_20250522: object` - `type: "code_execution_20250522"` - `name: "code_execution"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_code_execution_tool_20250825: object` - `type: "code_execution_20250825"` - `name: "code_execution"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_code_execution_tool_20260120: object` Code execution tool with REPL state persistence (daemon mode + gVisor checkpoint). - `type: "code_execution_20260120"` - `name: "code_execution"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_code_execution_tool_20260521: object` Code execution tool with REPL state persistence. - `type: "code_execution_20260521"` - `name: "code_execution"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_browser_toolset_20260801: object` The browser toolset: a single `tools[]` entry (carrying no `name`) that declares the browser tool family. The model is served the family's tool with any members disabled via `configs` removed from its schema. - `type: "browser_toolset_20260801"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `configs: optional object` Sparse per-member overrides, keyed by member name. Absent, null, and {} are equivalent; a member's defaults apply wherever its key is absent. - `type: optional object` `type`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `close_tab: optional object` `close_tab`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `double_click: optional object` `double_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `file_upload: optional object` `file_upload`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `find: optional object` `find`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `form_input: optional object` `form_input`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `get_page_text: optional object` `get_page_text`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `hold_key: optional object` `hold_key`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `hover: optional object` `hover`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `javascript_exec: optional object` `javascript_exec`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `key: optional object` `key`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_click: optional object` `left_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_click_drag: optional object` `left_click_drag`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_mouse_down: optional object` `left_mouse_down`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_mouse_up: optional object` `left_mouse_up`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `list_tabs: optional object` `list_tabs`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `middle_click: optional object` `middle_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `mouse_move: optional object` `mouse_move`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `navigate: optional object` `navigate`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `new_tab: optional object` `new_tab`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `read_console: optional object` `read_console`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `read_network: optional object` `read_network`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `read_page: optional object` `read_page`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `right_click: optional object` `right_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `screenshot: optional object` `screenshot`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `scroll: optional object` `scroll`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `scroll_to: optional object` `scroll_to`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `switch_tab: optional object` `switch_tab`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `triple_click: optional object` `triple_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `wait: optional object` `wait`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `zoom: optional object` `zoom`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `beta_tool_computer_use_20241022: object` - `type: "computer_20241022"` - `display_height_px: number` The height of the display in pixels. minimum: 1 - `display_width_px: number` The width of the display in pixels. minimum: 1 - `name: "computer"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `display_number: optional number` The X11 display number (e.g. 0, 1) for the display. minimum: 0 - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_memory_tool_20250818: object` - `type: "memory_20250818"` - `name: "memory"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_computer_use_20250124: object` - `type: "computer_20250124"` - `display_height_px: number` The height of the display in pixels. minimum: 1 - `display_width_px: number` The width of the display in pixels. minimum: 1 - `name: "computer"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `display_number: optional number` The X11 display number (e.g. 0, 1) for the display. minimum: 0 - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_text_editor_20241022: object` - `type: "text_editor_20241022"` - `name: "str_replace_editor"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_computer_use_20251124: object` - `type: "computer_20251124"` - `display_height_px: number` The height of the display in pixels. minimum: 1 - `display_width_px: number` The width of the display in pixels. minimum: 1 - `name: "computer"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `display_number: optional number` The X11 display number (e.g. 0, 1) for the display. minimum: 0 - `enable_zoom: optional boolean` Whether to enable an action to take a zoomed-in screenshot of the screen. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_computer_toolset_20260801: object` The computer toolset: a single `tools[]` entry (carrying no `name`) that declares the computer tool family. The model is served the family's tool with any members disabled via `configs` removed from its schema. Every member is enabled by default, zoom included. The single-tool options `display_number` and `enable_zoom` are not fields of a toolset entry — it carries only `type`, `configs`, and `cache_control`; zoom is controlled via `configs.zoom.enabled`. - `type: "computer_toolset_20260801"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `configs: optional object` Sparse per-member overrides, keyed by member name. Absent, null, and {} are equivalent; a member's defaults apply wherever its key is absent. - `type: optional object` `type`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `cursor_position: optional object` `cursor_position`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `double_click: optional object` `double_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `hold_key: optional object` `hold_key`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `key: optional object` `key`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_click: optional object` `left_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_click_drag: optional object` `left_click_drag`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_mouse_down: optional object` `left_mouse_down`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_mouse_up: optional object` `left_mouse_up`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `middle_click: optional object` `middle_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `mouse_move: optional object` `mouse_move`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `right_click: optional object` `right_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `screenshot: optional object` `screenshot`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `scroll: optional object` `scroll`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `triple_click: optional object` `triple_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `wait: optional object` `wait`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `zoom: optional object` `zoom`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `beta_tool_text_editor_20250124: object` - `type: "text_editor_20250124"` - `name: "str_replace_editor"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_text_editor_20250429: object` - `type: "text_editor_20250429"` - `name: "str_replace_based_edit_tool"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_text_editor_20250728: object` - `type: "text_editor_20250728"` - `name: "str_replace_based_edit_tool"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: optional array of map[unknown]` - `max_characters: optional number` Maximum number of characters to display when viewing a file. If not specified, defaults to displaying the full file. minimum: 1 - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_web_search_tool_20250305: object` - `type: "web_search_20250305"` - `name: "web_search"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: optional array of string` If provided, only these domains will be included in results. Cannot be used alongside `blocked_domains`. - `blocked_domains: optional array of string` If provided, these domains will never appear in results. Cannot be used alongside `allowed_domains`. - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `user_location: optional object` Parameters for the user's location. Used to provide more relevant search results. - `type: "approximate"` - `city: optional string` The city of the user. minLength: 1, maxLength: 255 - `country: optional string` The two letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1_alpha-2) of the user. minLength: 2, maxLength: 2 - `region: optional string` The region of the user. minLength: 1, maxLength: 255 - `timezone: optional string` The [IANA timezone](https://nodatime.org/TimeZones) of the user. minLength: 1, maxLength: 255 - `beta_web_fetch_tool_20250910: object` - `type: "web_fetch_20250910"` - `name: "web_fetch"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: optional array of string` List of domains to allow fetching from - `blocked_domains: optional array of string` List of domains to block fetching from - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `citations: optional object` Citations configuration for fetched documents. Citations are disabled by default. - `enabled: optional boolean` - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_content_tokens: optional number` Maximum number of tokens used by including web page text content in the context. The limit is approximate and does not apply to binary content such as PDFs. minimum: 1 - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `url_sources: optional object` Which sources contribute to the set of URLs the tool may fetch. Omitted means every source. - `client_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which client tools' results contribute fetchable URLs: "all", "none", or an only or except list of client tool names from tools[]. - `beta_web_fetch_url_source_all: object` The `url_sources` variant under which a source contributes in full: every result of the tool filter's source, or all user input. - `type: "all"` - `beta_web_fetch_url_source_none: object` The `url_sources` variant under which a source contributes nothing: no result of the tool filter's source, or no user input. - `type: "none"` - `beta_web_fetch_url_source_only: object` The tool filter variant under which only the named tools' results contribute. - `type: "only"` - `tools: array of BetaWebFetchURLSourceToolReference` - `type: "tool_reference"` - `name: string` - `beta_web_fetch_url_source_except: object` The tool filter variant under which every result but the named tools' contributes. - `type: "except"` - `tools: array of BetaWebFetchURLSourceToolReference` - `type: "tool_reference"` - `name: string` - `server_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which server tools' results contribute fetchable URLs: "all", "none", or an only or except list of server tool names from tools[]; only web_search and web_fetch results ever contribute. - `beta_web_fetch_url_source_all: object` The `url_sources` variant under which a source contributes in full: every result of the tool filter's source, or all user input. - `beta_web_fetch_url_source_none: object` The `url_sources` variant under which a source contributes nothing: no result of the tool filter's source, or no user input. - `beta_web_fetch_url_source_only: object` The tool filter variant under which only the named tools' results contribute. - `beta_web_fetch_url_source_except: object` The tool filter variant under which every result but the named tools' contributes. - `user_input: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone` Whether URLs in user messages are fetchable: "all" or "none". - `beta_web_fetch_url_source_all: object` The `url_sources` variant under which a source contributes in full: every result of the tool filter's source, or all user input. - `beta_web_fetch_url_source_none: object` The `url_sources` variant under which a source contributes nothing: no result of the tool filter's source, or no user input. - `beta_web_search_tool_20260209: object` - `type: "web_search_20260209"` - `name: "web_search"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: optional array of string` If provided, only these domains will be included in results. Cannot be used alongside `blocked_domains`. - `blocked_domains: optional array of string` If provided, these domains will never appear in results. Cannot be used alongside `allowed_domains`. - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `user_location: optional object` Parameters for the user's location. Used to provide more relevant search results. - `type: "approximate"` - `city: optional string` The city of the user. minLength: 1, maxLength: 255 - `country: optional string` The two letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1_alpha-2) of the user. minLength: 2, maxLength: 2 - `region: optional string` The region of the user. minLength: 1, maxLength: 255 - `timezone: optional string` The [IANA timezone](https://nodatime.org/TimeZones) of the user. minLength: 1, maxLength: 255 - `beta_web_fetch_tool_20260209: object` - `type: "web_fetch_20260209"` - `name: "web_fetch"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: optional array of string` List of domains to allow fetching from - `blocked_domains: optional array of string` List of domains to block fetching from - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `citations: optional object` Citations configuration for fetched documents. Citations are disabled by default. - `enabled: optional boolean` - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_content_tokens: optional number` Maximum number of tokens used by including web page text content in the context. The limit is approximate and does not apply to binary content such as PDFs. minimum: 1 - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `url_sources: optional object` Which sources contribute to the set of URLs the tool may fetch. Omitted means every source. - `client_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which client tools' results contribute fetchable URLs: "all", "none", or an only or except list of client tool names from tools[]. - `server_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which server tools' results contribute fetchable URLs: "all", "none", or an only or except list of server tool names from tools[]; only web_search and web_fetch results ever contribute. - `user_input: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone` Whether URLs in user messages are fetchable: "all" or "none". - `beta_web_fetch_tool_20260309: object` Web fetch tool with use_cache parameter for bypassing cached content. - `type: "web_fetch_20260309"` - `name: "web_fetch"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: optional array of string` List of domains to allow fetching from - `blocked_domains: optional array of string` List of domains to block fetching from - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `citations: optional object` Citations configuration for fetched documents. Citations are disabled by default. - `enabled: optional boolean` - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_content_tokens: optional number` Maximum number of tokens used by including web page text content in the context. The limit is approximate and does not apply to binary content such as PDFs. minimum: 1 - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `url_sources: optional object` Which sources contribute to the set of URLs the tool may fetch. Omitted means every source. - `client_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which client tools' results contribute fetchable URLs: "all", "none", or an only or except list of client tool names from tools[]. - `server_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which server tools' results contribute fetchable URLs: "all", "none", or an only or except list of server tool names from tools[]; only web_search and web_fetch results ever contribute. - `user_input: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone` Whether URLs in user messages are fetchable: "all" or "none". - `use_cache: optional boolean` Whether to use cached content. Set to false to bypass the cache and fetch fresh content. Only set to false when the user explicitly requests fresh content or when fetching rapidly-changing sources. - `beta_web_search_tool_20260318: object` - `type: "web_search_20260318"` - `name: "web_search"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: optional array of string` If provided, only these domains will be included in results. Cannot be used alongside `blocked_domains`. - `blocked_domains: optional array of string` If provided, these domains will never appear in results. Cannot be used alongside `allowed_domains`. - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `response_inclusion: optional "full" or "excluded"` How this tool's result blocks appear in the API response when the result was consumed by a completed code_execution call in the same turn. 'full' returns the complete content (default). 'excluded' drops the nested server_tool_use and result block pair entirely. Results from direct calls, or from code_execution calls that paused before completing, are always returned in full so they can be sent back on the next turn. - `"full"` - `"excluded"` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `user_location: optional object` Parameters for the user's location. Used to provide more relevant search results. - `type: "approximate"` - `city: optional string` The city of the user. minLength: 1, maxLength: 255 - `country: optional string` The two letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1_alpha-2) of the user. minLength: 2, maxLength: 2 - `region: optional string` The region of the user. minLength: 1, maxLength: 255 - `timezone: optional string` The [IANA timezone](https://nodatime.org/TimeZones) of the user. minLength: 1, maxLength: 255 - `beta_web_fetch_tool_20260318: object` - `type: "web_fetch_20260318"` - `name: "web_fetch"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: optional array of string` List of domains to allow fetching from - `blocked_domains: optional array of string` List of domains to block fetching from - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `citations: optional object` Citations configuration for fetched documents. Citations are disabled by default. - `enabled: optional boolean` - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_content_tokens: optional number` Maximum number of tokens used by including web page text content in the context. The limit is approximate and does not apply to binary content such as PDFs. minimum: 1 - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `response_inclusion: optional "full" or "excluded"` How this tool's result blocks appear in the API response when the result was consumed by a completed code_execution call in the same turn. 'full' returns the complete content (default). 'excluded' drops the nested server_tool_use and result block pair entirely. Results from direct calls, or from code_execution calls that paused before completing, are always returned in full so they can be sent back on the next turn. - `"full"` - `"excluded"` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `url_sources: optional object` Which sources contribute to the set of URLs the tool may fetch. Omitted means every source. - `client_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which client tools' results contribute fetchable URLs: "all", "none", or an only or except list of client tool names from tools[]. - `server_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which server tools' results contribute fetchable URLs: "all", "none", or an only or except list of server tool names from tools[]; only web_search and web_fetch results ever contribute. - `user_input: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone` Whether URLs in user messages are fetchable: "all" or "none". - `use_cache: optional boolean` Whether to use cached content. Set to false to bypass the cache and fetch fresh content. Only set to false when the user explicitly requests fresh content or when fetching rapidly-changing sources. - `beta_advisor_tool_20260301: object` - `type: "advisor_20260301"` - `model: "claude-haiku-5-5" or "claude-sonnet-5-5" or "claude-fable-5-1" or 17 more or string` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-haiku-5-5"` Fastest model for high-volume, real-time tasks - `"claude-sonnet-5-5"` Efficient model for coding and agents - `"claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows - `"claude-opus-5-5"` Powerful intelligence for coding, knowledge work, and long-running agents - `"claude-mythos-5-1"` Our most capable model for cybersecurity and biology research, available through trusted access programs - `"claude-sonnet-5"` Efficient model for coding and agents - `"claude-fable-5"` Next generation of intelligence for the hardest knowledge work and coding problems - `"claude-mythos-5"` Most capable model for cybersecurity and biology research - `"claude-opus-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-8"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-7"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-6"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-6"` Best combination of speed and intelligence - `"claude-haiku-4-5"` - `"claude-haiku-4-5-20251001"` - `"claude-opus-4-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-5-20251101"` Powerful intelligence for long-running agents and coding - `"claude-mythos-preview"` **Deprecated**: Will reach end-of-life on June 30, 2026. Please migrate to claude-mythos-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. New class of intelligence, strongest in coding and cybersecurity - `"claude-sonnet-4-5"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `"claude-sonnet-4-5-20250929"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `name: "advisor"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `caching: optional object` Caching for the advisor's own prompt. When set, each advisor call writes a cache entry at the given TTL so subsequent calls in the same conversation read the stable prefix. When omitted, the advisor prompt is not cached. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_tokens: optional number` Bounds the advisor's total output (thinking + text) per call. When the advisor hits this cap, the returned advisor_result or advisor_redacted_result block carries stop_reason='max_tokens', and a truncation note is appended to the advice text the worker model sees (inside the encrypted blob in redacted mode). When set, the server also emits a remaining-tokens budget block in the advisor's prompt so the advisor self-shapes toward the cap. When omitted, the advisor model's default output cap applies and no budget block is emitted. minimum: 1024 - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_search_tool_bm25_20251119: object` - `type: "tool_search_tool_bm25_20251119" or "tool_search_tool_bm25"` - `"tool_search_tool_bm25_20251119"` - `"tool_search_tool_bm25"` - `name: "tool_search_tool_bm25"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_search_tool_regex_20251119: object` - `type: "tool_search_tool_regex_20251119" or "tool_search_tool_regex"` - `"tool_search_tool_regex_20251119"` - `"tool_search_tool_regex"` - `name: "tool_search_tool_regex"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_mcp_toolset: object` Configuration for a group of tools from an MCP server. Allows configuring enabled status and defer_loading for all tools from an MCP server, with optional per-tool overrides. - `type: "mcp_toolset"` - `mcp_server_name: string` Name of the MCP server to configure tools for minLength: 1, maxLength: 255 - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `configs: optional map[BetaMCPToolConfig]` Configuration overrides for specific tools, keyed by tool name - `defer_loading: optional boolean` - `enabled: optional boolean` - `default_config: optional object` Default configuration applied to all tools from this server - `defer_loading: optional boolean` - `enabled: optional boolean` - `tools: optional array of BetaMCPToolParam` The server's tool listing, pinned: when present, the server is not asked for its tools before sampling and exactly these entries, with `default_config` and `configs` applied, are the toolset's tools. Copy it from the `mcp_tool_listing` block of an earlier response. - `input_schema: map[unknown]` The tool's input schema as the MCP server lists it, verbatim. - `name: string` The tool's name as the MCP server lists it (not prefixed with the server name). minLength: 1 - `description: optional string` The tool's description as the MCP server lists it. - `beta_response_tool_removal_block: object` An entry of a `compaction` block's `tool_changes`: a tool of the request's `tools` (or an MCP tool or toolset) that the compacted range withdrew. Send it back unchanged. - `type: "tool_removal"` - `tool: BetaResponseToolChangeToolReference or BetaResponseToolChangeMCPToolReference or BetaResponseToolChangeMCPToolsetReference` A reference to the withdrawn `tools` entry, MCP tool or MCP toolset. - `beta_response_tool_change_tool_reference: object` Reference to a single tool, by the name the model uses to call it, as a `compaction` block's `tool_changes` entry reports it: a tool declared in `tools` or defined by an earlier `tool_addition` block. Send it back unchanged with the block. - `beta_response_tool_change_mcp_tool_reference: object` Reference to a single MCP tool, by its server and its name on that server, as a `compaction` block's `tool_changes` entry reports it. Send it back unchanged with the block. - `beta_response_tool_change_mcp_toolset_reference: object` Reference to every tool in the named MCP server's toolset, as a `compaction` block's `tool_changes` entry reports it. Send it back unchanged with the block. - `beta_fallback_block: object` Marks the point in `content` where one model's output gives way to the next. One block appears per hop where a preceding model actually ran this turn and declined. A turn where no preceding model ran and declined has no such boundary and carries no block — the signal for whether a fallback model served the response is the presence of a `fallback_message` entry in `usage.iterations`, not this block. The block is treated like a server-tool content block for streaming: it arrives via the standard `content_block_start` / `content_block_stop` pair and carries no deltas. - `type: "fallback"` - `from: object` The model whose output ends at this point — the model that declined at this hop. When the declining hop is the requested model, its `model` echoes the top-level `model` string the caller sent (alias or canonical); when the declining hop is a fallback model, its `model` is that model's canonical id. - `model: "claude-haiku-5-5" or "claude-sonnet-5-5" or "claude-fable-5-1" or 17 more or string` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-haiku-5-5"` Fastest model for high-volume, real-time tasks - `"claude-sonnet-5-5"` Efficient model for coding and agents - `"claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows - `"claude-opus-5-5"` Powerful intelligence for coding, knowledge work, and long-running agents - `"claude-mythos-5-1"` Our most capable model for cybersecurity and biology research, available through trusted access programs - `"claude-sonnet-5"` Efficient model for coding and agents - `"claude-fable-5"` Next generation of intelligence for the hardest knowledge work and coding problems - `"claude-mythos-5"` Most capable model for cybersecurity and biology research - `"claude-opus-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-8"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-7"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-6"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-6"` Best combination of speed and intelligence - `"claude-haiku-4-5"` - `"claude-haiku-4-5-20251001"` - `"claude-opus-4-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-5-20251101"` Powerful intelligence for long-running agents and coding - `"claude-mythos-preview"` **Deprecated**: Will reach end-of-life on June 30, 2026. Please migrate to claude-mythos-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. New class of intelligence, strongest in coding and cybersecurity - `"claude-sonnet-4-5"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `"claude-sonnet-4-5-20250929"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `to: object` The fallback model producing the content that follows this block. Its `model` is always the canonical id. - `model: "claude-haiku-5-5" or "claude-sonnet-5-5" or "claude-fable-5-1" or 17 more or string` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `trigger: object` What caused the `from` model to hand over at this hop. - `type: "refusal"` - `category: "cyber" or "bio" or "frontier_llm" or 2 more` The policy category that triggered the `from` model's refusal at this hop. `null` when the refusal doesn't map to a named category. Same vocabulary as `stop_details.category`. - `"cyber"` The request could enable cyber harm, such as malware or exploit development. Benign cybersecurity work can also trigger this category. - `"bio"` The request could enable biological harm, such as dangerous lab methods. Beneficial life sciences work can also trigger this category. - `"frontier_llm"` The request could assist the development of competing AI models, which is restricted under [Anthropic's commercial terms](https://www.anthropic.com/legal/commercial-terms). Benign machine learning work can also trigger this category. - `"reasoning_extraction"` The request asks the model to reproduce its internal reasoning in the response text. To get reasoning in a structured form instead, use [adaptive thinking](https://platform.claude.com/docs/en/build-with-claude/adaptive-thinking?sdk_languages=cli). - `"general_harms"` The request could be related to an area that was determined as harmful. Benign work might sometimes trigger this category. - `beta_mcp_tool_listing_block: object` The tool listing the server fetched from an MCP server while producing this response. Send the assistant message back unchanged, this block included, so later requests use this listing instead of asking the MCP server again. - `type: "mcp_tool_listing"` - `mcp_server_name: string` - `tools: array of BetaMCPTool` - `input_schema: map[unknown]` - `name: string` - `description: optional string` - `context_management: object` Context management response. Information about context management strategies applied during the request. - `applied_edits: array of BetaClearToolUses20250919EditResponse or BetaClearThinking20251015EditResponse` List of context management edits that were applied. - `beta_clear_tool_uses_20250919_edit_response: object` - `type: "clear_tool_uses_20250919"` The type of context management edit applied. - `cleared_input_tokens: number` Number of input tokens cleared by this edit. minimum: 0 - `cleared_tool_uses: number` Number of tool uses that were cleared. minimum: 0 - `beta_clear_thinking_20251015_edit_response: object` - `type: "clear_thinking_20251015"` The type of context management edit applied. - `cleared_input_tokens: number` Number of input tokens cleared by this edit. minimum: 0 - `cleared_thinking_turns: number` Number of thinking turns that were cleared. minimum: 0 - `diagnostics: object` Request-level diagnostics. `null` when the request did not supply `diagnostics`, or when it did and no prompt-cache divergence was detected. - `cache_miss_reason: BetaCacheMissModelChanged or BetaCacheMissSystemChanged or BetaCacheMissToolsChanged or 3 more` Explains why the prompt cache could not fully reuse the prefix from the request identified by `diagnostics.previous_message_id`. `null` means diagnosis is still pending — the response was serialized before the background comparison completed. - `beta_cache_miss_model_changed: object` - `type: "model_changed"` - `cache_missed_input_tokens: number` Approximate number of input tokens that would have been read from cache had the prefix matched the previous request. - `beta_cache_miss_system_changed: object` - `type: "system_changed"` - `cache_missed_input_tokens: number` Approximate number of input tokens that would have been read from cache had the prefix matched the previous request. - `beta_cache_miss_tools_changed: object` - `type: "tools_changed"` - `cache_missed_input_tokens: number` Approximate number of input tokens that would have been read from cache had the prefix matched the previous request. - `beta_cache_miss_messages_changed: object` - `type: "messages_changed"` - `cache_missed_input_tokens: number` Approximate number of input tokens that would have been read from cache had the prefix matched the previous request. - `beta_cache_miss_previous_message_not_found: object` - `type: "previous_message_not_found"` - `beta_cache_miss_unavailable: object` - `type: "unavailable"` - `model: "claude-haiku-5-5" or "claude-sonnet-5-5" or "claude-fable-5-1" or 17 more or string` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-haiku-5-5"` Fastest model for high-volume, real-time tasks - `"claude-sonnet-5-5"` Efficient model for coding and agents - `"claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows - `"claude-opus-5-5"` Powerful intelligence for coding, knowledge work, and long-running agents - `"claude-mythos-5-1"` Our most capable model for cybersecurity and biology research, available through trusted access programs - `"claude-sonnet-5"` Efficient model for coding and agents - `"claude-fable-5"` Next generation of intelligence for the hardest knowledge work and coding problems - `"claude-mythos-5"` Most capable model for cybersecurity and biology research - `"claude-opus-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-8"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-7"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-6"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-6"` Best combination of speed and intelligence - `"claude-haiku-4-5"` - `"claude-haiku-4-5-20251001"` - `"claude-opus-4-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-5-20251101"` Powerful intelligence for long-running agents and coding - `"claude-mythos-preview"` **Deprecated**: Will reach end-of-life on June 30, 2026. Please migrate to claude-mythos-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. New class of intelligence, strongest in coding and cybersecurity - `"claude-sonnet-4-5"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `"claude-sonnet-4-5-20250929"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `role: "assistant"` Conversational role of the generated message. This will always be `"assistant"`. - `stop_details: object` Structured information about why model output stopped. This is `null` when the `stop_reason` has no additional detail to report. - `type: "refusal"` - `category: "cyber" or "bio" or "frontier_llm" or 2 more` The policy category that triggered the refusal. `null` when the refusal doesn't map to a named category. - `"cyber"` The request could enable cyber harm, such as malware or exploit development. Benign cybersecurity work can also trigger this category. - `"bio"` The request could enable biological harm, such as dangerous lab methods. Beneficial life sciences work can also trigger this category. - `"frontier_llm"` The request could assist the development of competing AI models, which is restricted under [Anthropic's commercial terms](https://www.anthropic.com/legal/commercial-terms). Benign machine learning work can also trigger this category. - `"reasoning_extraction"` The request asks the model to reproduce its internal reasoning in the response text. To get reasoning in a structured form instead, use [adaptive thinking](https://platform.claude.com/docs/en/build-with-claude/adaptive-thinking?sdk_languages=cli). - `"general_harms"` The request could be related to an area that was determined as harmful. Benign work might sometimes trigger this category. - `explanation: string` Human-readable explanation of the refusal. This text is not guaranteed to be stable. `null` when no explanation is available for the category. - `fallback_credit_token: string` Opaque code that refunds the cache-miss cost when retrying this refused request on the fallback model. Pass it as `fallback_credit_token` on the retry request. Expires 5 minutes after the refusal. The retry is sent either with the same request body (`system`, `messages`, `tools`, and other render-shaping fields), or with the same body plus one appended `assistant` message whose content is the partial text (with any trailing whitespace stripped from the final text block) and paired server-tool blocks from this refusal — which also authorizes that appended turn as an assistant-prefill continuation on models that otherwise disallow prefill. A token minted mid-server-tool-loop whose partial content was continuable may only be redeemed the second way — if a same-body retry is rejected with a 400 saying the token must be redeemed by continuing the partial response, retry the second way instead. Either way: same workspace, same platform; a mismatch is a 400. Resending a token for an already-warm prefix is permitted but yields no additional credit. `null` when the refused model isn't eligible for a fallback credit. - `fallback_has_prefill_claim: boolean` Whether the accompanying `fallback_credit_token` may be redeemed with the appended-assistant retry form. Only set when `fallback_credit_token` is present. `true`: retry by resending the same request body plus one appended `assistant` message whose content is this response's `content` with any trailing whitespace stripped from the final text block and unpaired `tool_use` blocks omitted (the same appended-turn shape described on `fallback_credit_token`), with the token attached. `false`: retry by resending the original request body unchanged, with the token attached — the appended-assistant form is not available for this refusal (no continuable partial content, or the request uses `output_format` or a `tool_choice` that forces tool use). One exception: when the request used `output_format` or a forced `tool_choice` and the refusal arrived after server tools (including MCP connector tools) had already executed, the token may not be redeemable by either retry form; if the exact-body retry is then rejected with a 400 saying the token must be redeemed by continuing the partial response, discard the token and retry without it. Advisory: if an appended-assistant retry is rejected with a 400 despite `true`, fall back to resending the original request body with the token. - `recommended_model: string` The server's suggested retry target for this refusal. Populated when a fallback attempt could not be made (the fallback model's rate limit was exhausted, or it was overloaded); names the fallback model the caller can retry directly. Null otherwise. - `stop_reason: "end_turn" or "max_tokens" or "stop_sequence" or 5 more` The reason that we stopped. This may be one the following values: * `"end_turn"`: the model reached a natural stopping point * `"max_tokens"`: we exceeded the requested `max_tokens` or the model's maximum * `"stop_sequence"`: one of your provided custom `stop_sequences` was generated * `"tool_use"`: the model invoked one or more tools * `"pause_turn"`: we paused a long-running turn. You may provide the response back as-is in a subsequent request to let the model continue. * `"refusal"`: when streaming classifiers intervene to handle potential policy violations * `"model_context_window_exceeded"`: we exceeded the model's context window In non-streaming mode this value is always non-null. In streaming mode, it is null in the `message_start` event and non-null otherwise. - `"end_turn"` - `"max_tokens"` - `"stop_sequence"` - `"tool_use"` - `"pause_turn"` - `"compaction"` - `"refusal"` - `"model_context_window_exceeded"` - `stop_sequence: string` Which custom stop sequence was generated, if any. This value will be a non-null string if one of your custom stop sequences was generated. - `usage: object` Billing and rate-limit usage. Anthropic's API bills and rate-limits by token counts, as tokens represent the underlying cost to our systems. Under the hood, the API transforms requests into a format suitable for the model. The model's output then goes through a parsing stage before becoming an API response. As a result, the token counts in `usage` will not match one-to-one with the exact visible content of an API request or response. For example, `output_tokens` will be non-zero, even for an empty string response from Claude. Total input tokens in a request is the summation of `input_tokens`, `cache_creation_input_tokens`, and `cache_read_input_tokens`. - `cache_creation: object` Breakdown of cached tokens by TTL - `ephemeral_1h_input_tokens: number` The number of input tokens used to create the 1 hour cache entry. minimum: 0 - `ephemeral_5m_input_tokens: number` The number of input tokens used to create the 5 minute cache entry. minimum: 0 - `cache_creation_input_tokens: number` The number of input tokens used to create the cache entry. minimum: 0 - `cache_read_input_tokens: number` The number of input tokens read from the cache. minimum: 0 - `fallback_credit: object` Outcome of the `fallback_credit_token` presented on this request. Present on every response to a non-batch request that carried a `fallback_credit_token`, in either redemption mode; absent otherwise (batch items accept and ignore the token and carry no outcome object). - `status: BetaFallbackCreditRedeemed or BetaFallbackCreditNotApplied` Whether the fallback-credit reprice was applied to this response's billing. A union discriminated on `type`. `redeemed`: the retry is billed as if the conversation had been on the retry model all along — including when the resulting shift is zero because there was nothing to move. `not_applied`: no reprice was applied; the arm's `reason` says why. - `beta_fallback_credit_redeemed: object` The reprice was applied: the retry is billed as if the conversation had been on the retry model all along. - `type: "redeemed"` - `beta_fallback_credit_not_applied: object` No reprice was applied; `reason` says why. - `type: "not_applied"` - `reason: "body_mismatch" or "continuation_excluded" or "continuation_only" or 9 more` Why the reprice was not applied. A closed enum; additions to the redemption-check vocabulary arrive as deliberate schema updates. - `"body_mismatch"` - `"continuation_excluded"` - `"continuation_only"` - `"expired"` - `"invalid_target_model"` - `"not_enabled"` - `"reprice_unavailable"` - `"temporarily_unavailable"` - `"variant_fields_present"` - `"wrong_organization"` - `"wrong_platform"` - `"wrong_workspace"` - `remove_to_redeem: optional array of string` Request fields to remove before retrying, so the retry can redeem this token. Present exactly when `reason` is `variant_fields_present` — never null, never an empty array; absent otherwise. Fields are named only from your own request, and only after the sealed variant hash matched. A served best-effort retry has already been billed at normal price; nothing redeems retroactively, but a corrected re-send inside the token's five-minute window can still redeem. - `inference_geo: string` The geographic region where inference was performed for this request. - `input_tokens: number` The number of input tokens which were used. minimum: 0 - `iterations: array of BetaMessageIterationUsage or BetaCompactionIterationUsage or BetaAdvisorMessageIterationUsage or BetaFallbackMessageIterationUsage` Per-iteration token usage breakdown. Each entry represents one sampling iteration, with its own input/output token counts and cache statistics, discriminated by `type`. For `message` entries (model sampling iterations, such as the turns of a server-side tool use loop), this allows you to: - Calculate the context window size from the last `message` entry - Understand token accumulation across server-side tool use loops A `compaction` entry reports the token usage of the compaction operation itself — the server-side request that summarizes the context being closed — NOT the size of the context that was compacted away, and its token counts can be much smaller than that closed context (for example, a compaction that closes a ~200k-token context can report only a few thousand tokens). Do not derive the context window size from a `compaction` entry, even when it is the last entry. A `compaction` entry's tokens are not included in the top-level `usage` fields. When an input-token trigger is in effect (the default — 150,000 tokens unless configured otherwise), each `compaction` entry closes a context that had reached at least that threshold, though the context can exceed it by the final iteration's output and tool results. - `beta_message_iteration_usage: object` Token usage for a sampling iteration. - `type: "message"` Usage for a sampling iteration - `cache_creation: object` Breakdown of cached tokens by TTL - `ephemeral_1h_input_tokens: number` The number of input tokens used to create the 1 hour cache entry. minimum: 0 - `ephemeral_5m_input_tokens: number` The number of input tokens used to create the 5 minute cache entry. minimum: 0 - `cache_creation_input_tokens: number` The number of input tokens used to create the cache entry. minimum: 0 - `cache_read_input_tokens: number` The number of input tokens read from the cache. minimum: 0 - `input_tokens: number` The number of input tokens which were used. minimum: 0 - `model: "claude-haiku-5-5" or "claude-sonnet-5-5" or "claude-fable-5-1" or 17 more or string` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-haiku-5-5"` Fastest model for high-volume, real-time tasks - `"claude-sonnet-5-5"` Efficient model for coding and agents - `"claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows - `"claude-opus-5-5"` Powerful intelligence for coding, knowledge work, and long-running agents - `"claude-mythos-5-1"` Our most capable model for cybersecurity and biology research, available through trusted access programs - `"claude-sonnet-5"` Efficient model for coding and agents - `"claude-fable-5"` Next generation of intelligence for the hardest knowledge work and coding problems - `"claude-mythos-5"` Most capable model for cybersecurity and biology research - `"claude-opus-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-8"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-7"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-6"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-6"` Best combination of speed and intelligence - `"claude-haiku-4-5"` - `"claude-haiku-4-5-20251001"` - `"claude-opus-4-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-5-20251101"` Powerful intelligence for long-running agents and coding - `"claude-mythos-preview"` **Deprecated**: Will reach end-of-life on June 30, 2026. Please migrate to claude-mythos-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. New class of intelligence, strongest in coding and cybersecurity - `"claude-sonnet-4-5"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `"claude-sonnet-4-5-20250929"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `output_tokens: number` The number of output tokens which were used. minimum: 0 - `beta_compaction_iteration_usage: object` Token usage for a compaction iteration. - `type: "compaction"` Usage for a compaction iteration - `cache_creation: object` Breakdown of cached tokens by TTL - `ephemeral_1h_input_tokens: number` The number of input tokens used to create the 1 hour cache entry. minimum: 0 - `ephemeral_5m_input_tokens: number` The number of input tokens used to create the 5 minute cache entry. minimum: 0 - `cache_creation_input_tokens: number` The number of input tokens used to create the cache entry. minimum: 0 - `cache_read_input_tokens: number` The number of input tokens read from the cache. minimum: 0 - `input_tokens: number` The number of input tokens which were used. minimum: 0 - `output_tokens: number` The number of output tokens which were used. minimum: 0 - `beta_advisor_message_iteration_usage: object` Token usage for an advisor sub-inference iteration. - `type: "advisor_message"` Usage for an advisor sub-inference iteration - `cache_creation: object` Breakdown of cached tokens by TTL - `ephemeral_1h_input_tokens: number` The number of input tokens used to create the 1 hour cache entry. minimum: 0 - `ephemeral_5m_input_tokens: number` The number of input tokens used to create the 5 minute cache entry. minimum: 0 - `cache_creation_input_tokens: number` The number of input tokens used to create the cache entry. minimum: 0 - `cache_read_input_tokens: number` The number of input tokens read from the cache. minimum: 0 - `input_tokens: number` The number of input tokens which were used. minimum: 0 - `model: "claude-haiku-5-5" or "claude-sonnet-5-5" or "claude-fable-5-1" or 17 more or string` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-haiku-5-5"` Fastest model for high-volume, real-time tasks - `"claude-sonnet-5-5"` Efficient model for coding and agents - `"claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows - `"claude-opus-5-5"` Powerful intelligence for coding, knowledge work, and long-running agents - `"claude-mythos-5-1"` Our most capable model for cybersecurity and biology research, available through trusted access programs - `"claude-sonnet-5"` Efficient model for coding and agents - `"claude-fable-5"` Next generation of intelligence for the hardest knowledge work and coding problems - `"claude-mythos-5"` Most capable model for cybersecurity and biology research - `"claude-opus-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-8"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-7"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-6"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-6"` Best combination of speed and intelligence - `"claude-haiku-4-5"` - `"claude-haiku-4-5-20251001"` - `"claude-opus-4-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-5-20251101"` Powerful intelligence for long-running agents and coding - `"claude-mythos-preview"` **Deprecated**: Will reach end-of-life on June 30, 2026. Please migrate to claude-mythos-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. New class of intelligence, strongest in coding and cybersecurity - `"claude-sonnet-4-5"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `"claude-sonnet-4-5-20250929"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `output_tokens: number` The number of output tokens which were used. minimum: 0 - `beta_fallback_message_iteration_usage: object` Token usage for the fallback-model attempt of a server-side fallback request. The terminal entry of a fallback-served turn: when a fallback hop's output is the returned message, the entry for the iteration that completed it carries this type in place of `message`. A declined hop and the serving hop's earlier tool-loop iterations produce `message` entries. Whether a fallback model served the response is signalled by the presence of this entry in `usage.iterations`. - `type: "fallback_message"` Usage for the fallback-model attempt that served the response - `cache_creation: object` Breakdown of cached tokens by TTL - `ephemeral_1h_input_tokens: number` The number of input tokens used to create the 1 hour cache entry. minimum: 0 - `ephemeral_5m_input_tokens: number` The number of input tokens used to create the 5 minute cache entry. minimum: 0 - `cache_creation_input_tokens: number` The number of input tokens used to create the cache entry. minimum: 0 - `cache_read_input_tokens: number` The number of input tokens read from the cache. minimum: 0 - `input_tokens: number` The number of input tokens which were used. minimum: 0 - `model: "claude-haiku-5-5" or "claude-sonnet-5-5" or "claude-fable-5-1" or 17 more or string` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-haiku-5-5"` Fastest model for high-volume, real-time tasks - `"claude-sonnet-5-5"` Efficient model for coding and agents - `"claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows - `"claude-opus-5-5"` Powerful intelligence for coding, knowledge work, and long-running agents - `"claude-mythos-5-1"` Our most capable model for cybersecurity and biology research, available through trusted access programs - `"claude-sonnet-5"` Efficient model for coding and agents - `"claude-fable-5"` Next generation of intelligence for the hardest knowledge work and coding problems - `"claude-mythos-5"` Most capable model for cybersecurity and biology research - `"claude-opus-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-8"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-7"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-6"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-6"` Best combination of speed and intelligence - `"claude-haiku-4-5"` - `"claude-haiku-4-5-20251001"` - `"claude-opus-4-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-5-20251101"` Powerful intelligence for long-running agents and coding - `"claude-mythos-preview"` **Deprecated**: Will reach end-of-life on June 30, 2026. Please migrate to claude-mythos-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. New class of intelligence, strongest in coding and cybersecurity - `"claude-sonnet-4-5"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `"claude-sonnet-4-5-20250929"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `output_tokens: number` The number of output tokens which were used. minimum: 0 - `output_tokens: number` The number of output tokens which were used. minimum: 0 - `output_tokens_details: object` Breakdown of output tokens by category. `output_tokens` remains the inclusive, authoritative total used for billing. This object provides a read-only decomposition for observability — for example, how many of the billed output tokens were spent on internal reasoning that may have been summarized before being returned to you. - `thinking_tokens: number` Number of output tokens the model generated as internal reasoning, including the thinking-block delimiter tokens. Reflects the raw reasoning the model produced, not the (possibly shorter) summarized thinking text returned in the response body. Computed by re-tokenizing the raw reasoning text, so it may differ from the model's exact generation count by a small number of tokens. Always ≤ `output_tokens`; `output_tokens - thinking_tokens` approximates the non-reasoning output. minimum: 0 - `server_tool_use: object` The number of server tool requests. - `web_fetch_requests: number` The number of web fetch tool requests. minimum: 0 - `web_search_requests: number` The number of web search tool requests. minimum: 0 - `service_tier: "standard" or "priority" or "batch"` If the request used the priority, standard, or batch tier. - `"standard"` - `"priority"` - `"batch"` - `speed: "standard" or "fast"` The inference speed mode used for this request. - `"standard"` - `"fast"` - `input_transformations: optional array of BetaInputTransformation` Changes the API made to the request's input before showing it to the model, and blocks that failed a binding check but were left unchanged: one entry per block, in request order. Two entry types today. `thinking_dropped` — a `thinking`, `redacted_thinking` or `connector_text` block from the request's `messages` that was removed from the prompt instead of being shown to the model because it failed a binding check. `thinking_mismatch_allowed` — a `thinking` or `redacted_thinking` block that failed the conversation check (the conversation before it differs from the one it was created in, or it carries no record of one on a model that requires it) and was shown to the model all the same, because that check is not enforced for this request. More entry types may be added over time; ignore types you do not recognize. Requires `anthropic-beta: thinking-binding-controls-2026-08-01`. Present on every such response from a model that supports extended thinking, as `[]` when there is no entry to report; without the beta, blocks are removed or left in place all the same but nothing is reported. Removed blocks contribute nothing to `usage.input_tokens`; blocks left in place count as sent. When streaming, the array is final in `message_start`; the final `message_delta` event carries it only when a server-side model fallback happened mid-stream, in which case it holds the serving model's entries and replaces the one in `message_start`. - `beta_thinking_dropped_input_transformation: object` - `type: "thinking_dropped"` Always `thinking_dropped` for this entry type. - `path: string` Where the removed block was in your request, as `messages.{i}.content.{j}`: `i` indexes the `messages` array you sent and `j` that message's `content` array — the same form error messages use. - `reason: "model_binding_mismatch" or "prefix_binding_mismatch" or "organization_binding_mismatch" or "end_user_binding_mismatch"` Which binding check removed the block: `model_binding_mismatch` — it was created by a model whose reasoning the requested model may not read; `prefix_binding_mismatch` — the conversation before it differs from the conversation it was created in (the rest of that turn's consecutive thinking blocks are removed with it, each with this reason); `organization_binding_mismatch` — it was created under a different organization (an Anthropic organization, AWS account or Google Cloud project) and this organization is not one of its additional organizations; `end_user_binding_mismatch` — it was created for a different end user, or was removed by the consumer-organization binding. A block that would fail several checks reports one reason, in this order of precedence: `organization_binding_mismatch`, `end_user_binding_mismatch`, `model_binding_mismatch`, `prefix_binding_mismatch`. - `"model_binding_mismatch"` - `"prefix_binding_mismatch"` - `"organization_binding_mismatch"` - `"end_user_binding_mismatch"` - `beta_thinking_mismatch_allowed_input_transformation: object` - `type: "thinking_mismatch_allowed"` Always `thinking_mismatch_allowed` for this entry type. - `path: string` Where the block is in your request, as `messages.{i}.content.{j}`: `i` indexes the `messages` array you sent and `j` that message's `content` array — the same form error messages use. - `reason: "model_binding_mismatch" or "prefix_binding_mismatch" or "organization_binding_mismatch" or "end_user_binding_mismatch"` Which binding check the block failed; the block was shown to the model all the same. Always `prefix_binding_mismatch` today — the conversation before the block differs from the conversation it was created in, or the block carries no record of one on a model that requires it. Were the check enforced for this request, the block would have been removed or the request rejected (`thinking.block_binding.prefix_mismatch_behavior`). A removal also takes the rest of that turn's consecutive thinking blocks, whereas here each block is checked on its own, so `thinking_mismatch_allowed` entries are a lower bound on what enforcement would remove. - `"model_binding_mismatch"` - `"prefix_binding_mismatch"` - `"organization_binding_mismatch"` - `"end_user_binding_mismatch"` ### Beta Raw Message Stop Event - `beta_raw_message_stop_event: object` - `type: "message_stop"` ### Beta Raw Message Stream Event - `beta_raw_message_stream_event: BetaRawMessageStartEvent or BetaRawMessageDeltaEvent or BetaRawMessageStopEvent or 3 more` - `beta_raw_message_start_event: object` - `type: "message_start"` - `message: object` - `type: "message"` Object type. For Messages, this is always `"message"`. - `id: string` Unique object identifier. The format and length of IDs may change over time. - `container: object` Information about the container used in this request. This will be non-null if a container tool (e.g. code execution) was used. - `id: string` Identifier for the container used in this request - `expires_at: string` The time at which the container will expire. format: date-time - `skills: array of BetaContainerSkill` Skills loaded in the container - `type: "anthropic" or "custom"` Type of skill - either 'anthropic' (built-in) or 'custom' (user-defined) - `"anthropic"` - `"custom"` - `skill_id: string` Skill ID minLength: 1, maxLength: 64 - `version: string` The resolved version: a skill version ID for custom skills. minLength: 1, maxLength: 64 - `content: array of BetaContentBlock` Content generated by the model. This is an array of content blocks, each of which has a `type` that determines its shape. Example: ```json [{"type": "text", "text": "Hi, I'm Claude."}] ``` If the request input `messages` ended with an `assistant` turn, then the response `content` will continue directly from that last turn. You can use this to constrain the model's output. For example, if the input `messages` were: ```json [ {"role": "user", "content": "What's the Greek name for Sun? (A) Sol (B) Helios (C) Sun"}, {"role": "assistant", "content": "The best answer is ("} ] ``` Then the response `content` might be: ```json [{"type": "text", "text": "B)"}] ``` - `beta_text_block: object` - `type: "text"` - `citations: array of BetaTextCitation` Citations supporting the text block. The type of citation returned will depend on the type of document being cited. Citing a PDF results in `page_location`, plain text results in `char_location`, and content document results in `content_block_location`. - `beta_citation_char_location: object` - `type: "char_location"` - `cited_text: string` - `document_index: number` minimum: 0 - `document_title: string` - `end_char_index: number` - `file_id: string` - `start_char_index: number` minimum: 0 - `beta_citation_page_location: object` - `type: "page_location"` - `cited_text: string` - `document_index: number` minimum: 0 - `document_title: string` - `end_page_number: number` - `file_id: string` - `start_page_number: number` minimum: 1 - `beta_citation_content_block_location: object` - `type: "content_block_location"` - `cited_text: string` The full text of the cited block range, concatenated. Always equals the contents of `content[start_block_index:end_block_index]` joined together. The text block is the minimal citable unit; this field is never a substring of a single block. Not counted toward output tokens, and not counted toward input tokens when sent back in subsequent turns. - `document_index: number` minimum: 0 - `document_title: string` - `end_block_index: number` Exclusive 0-based end index of the cited block range in the source's `content` array. Always greater than `start_block_index`; a single-block citation has `end_block_index = start_block_index + 1`. - `file_id: string` - `start_block_index: number` 0-based index of the first cited block in the source's `content` array. minimum: 0 - `beta_citations_web_search_result_location: object` - `type: "web_search_result_location"` - `cited_text: string` - `encrypted_index: string` - `title: string` maxLength: 512 - `url: string` - `beta_citation_search_result_location: object` - `type: "search_result_location"` - `cited_text: string` The full text of the cited block range, concatenated. Always equals the contents of `content[start_block_index:end_block_index]` joined together. The text block is the minimal citable unit; this field is never a substring of a single block. Not counted toward output tokens, and not counted toward input tokens when sent back in subsequent turns. - `end_block_index: number` Exclusive 0-based end index of the cited block range in the source's `content` array. Always greater than `start_block_index`; a single-block citation has `end_block_index = start_block_index + 1`. - `search_result_index: number` 0-based index of the cited search result among all `search_result` content blocks in the request, in the order they appear across messages and tool results. Counted separately from `document_index`; server-side web search results are not included in this count. minimum: 0 - `source: string` - `start_block_index: number` 0-based index of the first cited block in the source's `content` array. minimum: 0 - `title: string` - `text: string` - `beta_thinking_block: object` - `type: "thinking"` - `signature: string` A value used to verify that this thinking block was generated by Claude when it is passed back to the API. This is an opaque field and should not be interpreted or parsed. When passing thinking blocks back to the API (required when using tools with extended thinking), pass them back exactly as received, with this field intact. See [extended thinking](https://platform.claude.com/docs/en/build-with-claude/extended-thinking?sdk_languages=cli) for details. - `thinking: string` The text of Claude's thinking process for this block. - `beta_redacted_thinking_block: object` - `type: "redacted_thinking"` - `data: string` The contents of this redacted thinking block, returned when portions of the model's thinking were safety-redacted. This field is opaque and encrypted, with no readable content. Pass `redacted_thinking` blocks back to the API unchanged when continuing a multi-turn conversation. See [extended thinking](https://platform.claude.com/docs/en/build-with-claude/extended-thinking?sdk_languages=cli#redacted-thinking-blocks) for details. - `beta_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: map[unknown]` - `name: string` minLength: 1 - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` - `beta_direct_caller: object` Tool invocation directly from the model. - `type: "direct"` - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `type: "code_execution_20250825"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `beta_server_tool_caller_20260120: object` - `type: "code_execution_20260120"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `toolset_name: optional string` For a toolset member tool_use, the toolset family. minLength: 1, maxLength: 64, pattern: ^[a-zA-Z0-9_-]+$ - `beta_server_tool_use_block: object` - `type: "server_tool_use"` - `id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `input: map[unknown]` - `name: "advisor" or "web_search" or "web_fetch" or 5 more` - `"advisor"` - `"web_search"` - `"web_fetch"` - `"code_execution"` - `"bash_code_execution"` - `"text_editor_code_execution"` - `"tool_search_tool_regex"` - `"tool_search_tool_bm25"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` - `beta_direct_caller: object` Tool invocation directly from the model. - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `beta_server_tool_caller_20260120: object` - `beta_web_search_tool_result_block: object` - `type: "web_search_tool_result"` - `content: BetaWebSearchToolResultError or array of BetaWebSearchResultBlock` - `beta_web_search_tool_result_error: object` - `type: "web_search_tool_result_error"` - `error_code: "invalid_tool_input" or "unavailable" or "max_uses_exceeded" or 3 more` - `"invalid_tool_input"` - `"unavailable"` - `"max_uses_exceeded"` - `"too_many_requests"` - `"query_too_long"` - `"request_too_large"` - `union_member_1: array of BetaWebSearchResultBlock` - `type: "web_search_result"` - `encrypted_content: string` - `page_age: string` - `title: string` - `url: string` - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` - `beta_direct_caller: object` Tool invocation directly from the model. - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `beta_server_tool_caller_20260120: object` - `beta_web_fetch_tool_result_block: object` - `type: "web_fetch_tool_result"` - `content: BetaWebFetchToolResultErrorBlock or BetaWebFetchBlock` - `beta_web_fetch_tool_result_error_block: object` - `type: "web_fetch_tool_result_error"` - `error_code: "invalid_tool_input" or "url_too_long" or "url_not_allowed" or 7 more` - `"invalid_tool_input"` - `"url_too_long"` - `"url_not_allowed"` - `"url_not_in_prior_context"` - `"url_not_accessible"` - `"unsupported_content_type"` - `"too_many_requests"` - `"max_uses_exceeded"` - `"unavailable"` - `"content_too_large"` - `beta_web_fetch_block: object` - `type: "web_fetch_result"` - `content: object` - `type: "document"` - `citations: object` Citation configuration for the document - `enabled: boolean` - `source: BetaBase64PDFSource or BetaPlainTextSource` - `beta_base64_pdf_source: object` - `type: "base64"` - `data: string` format: byte - `media_type: "application/pdf"` - `beta_plain_text_source: object` - `type: "text"` - `data: string` - `media_type: "text/plain"` - `title: string` The title of the document - `retrieved_at: string` ISO 8601 timestamp when the content was retrieved - `url: string` Fetched content URL - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` - `beta_direct_caller: object` Tool invocation directly from the model. - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `beta_server_tool_caller_20260120: object` - `beta_advisor_tool_result_block: object` - `type: "advisor_tool_result"` - `content: BetaAdvisorToolResultError or BetaAdvisorResultBlock or BetaAdvisorRedactedResultBlock` - `beta_advisor_tool_result_error: object` - `type: "advisor_tool_result_error"` - `error_code: "max_uses_exceeded" or "prompt_too_long" or "too_many_requests" or 4 more` - `"max_uses_exceeded"` - `"prompt_too_long"` - `"too_many_requests"` - `"overloaded"` - `"unavailable"` - `"execution_time_exceeded"` - `"model_not_found"` - `beta_advisor_result_block: object` - `type: "advisor_result"` - `stop_reason: string` The advisor sub-inference's stop reason (same values as the top-level message `stop_reason`). `max_tokens` indicates the advisor's output was truncated at the tool's `max_tokens` value or the advisor model's policy cap. - `text: string` - `beta_advisor_redacted_result_block: object` - `type: "advisor_redacted_result"` - `encrypted_content: string` Opaque blob containing the advisor's output. Round-trip verbatim; do not inspect or modify. - `stop_reason: string` The advisor sub-inference's stop reason (same values as the top-level message `stop_reason`). - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `beta_code_execution_tool_result_block: object` - `type: "code_execution_tool_result"` - `content: BetaCodeExecutionToolResultError or BetaCodeExecutionResultBlock or BetaEncryptedCodeExecutionResultBlock` - `beta_code_execution_tool_result_error: object` - `type: "code_execution_tool_result_error"` - `error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or "execution_time_exceeded"` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `beta_code_execution_result_block: object` - `type: "code_execution_result"` - `content: array of BetaCodeExecutionOutputBlock` - `type: "code_execution_output"` - `file_id: string` - `return_code: number` - `stderr: string` - `stdout: string` - `beta_encrypted_code_execution_result_block: object` Code execution result with encrypted stdout for PFC + web_search results. - `type: "encrypted_code_execution_result"` - `content: array of BetaCodeExecutionOutputBlock` - `type: "code_execution_output"` - `file_id: string` - `encrypted_stdout: string` - `return_code: number` - `stderr: string` - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `beta_bash_code_execution_tool_result_block: object` - `type: "bash_code_execution_tool_result"` - `content: BetaBashCodeExecutionToolResultError or BetaBashCodeExecutionResultBlock` - `beta_bash_code_execution_tool_result_error: object` - `type: "bash_code_execution_tool_result_error"` - `error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or 2 more` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `"output_file_too_large"` - `beta_bash_code_execution_result_block: object` - `type: "bash_code_execution_result"` - `content: array of BetaBashCodeExecutionOutputBlock` - `type: "bash_code_execution_output"` - `file_id: string` - `return_code: number` - `stderr: string` - `stdout: string` - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `beta_text_editor_code_execution_tool_result_block: object` - `type: "text_editor_code_execution_tool_result"` - `content: BetaTextEditorCodeExecutionToolResultError or BetaTextEditorCodeExecutionViewResultBlock or BetaTextEditorCodeExecutionCreateResultBlock or BetaTextEditorCodeExecutionStrReplaceResultBlock` - `beta_text_editor_code_execution_tool_result_error: object` - `type: "text_editor_code_execution_tool_result_error"` - `error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or 2 more` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `"file_not_found"` - `error_message: string` - `beta_text_editor_code_execution_view_result_block: object` - `type: "text_editor_code_execution_view_result"` - `content: string` - `file_type: "text" or "image" or "pdf"` - `"text"` - `"image"` - `"pdf"` - `num_lines: number` - `start_line: number` - `total_lines: number` - `beta_text_editor_code_execution_create_result_block: object` - `type: "text_editor_code_execution_create_result"` - `is_file_update: boolean` - `beta_text_editor_code_execution_str_replace_result_block: object` - `type: "text_editor_code_execution_str_replace_result"` - `lines: array of string` - `new_lines: number` - `new_start: number` - `old_lines: number` - `old_start: number` - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `beta_tool_search_tool_result_block: object` - `type: "tool_search_tool_result"` - `content: BetaToolSearchToolResultError or BetaToolSearchToolSearchResultBlock` - `beta_tool_search_tool_result_error: object` - `type: "tool_search_tool_result_error"` - `error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or "execution_time_exceeded"` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `error_message: string` - `beta_tool_search_tool_search_result_block: object` - `type: "tool_search_tool_search_result"` - `tool_references: array of BetaToolReferenceBlock` - `type: "tool_reference"` - `tool_name: string` minLength: 1, maxLength: 256, pattern: ^[a-zA-Z0-9_-]{1,256}$ - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `beta_mcp_tool_use_block: object` - `type: "mcp_tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: map[unknown]` - `name: string` The name of the MCP tool - `server_name: string` The name of the MCP server - `beta_mcp_tool_result_block: object` - `type: "mcp_tool_result"` - `content: string or array of BetaTextBlock` - `union_member_0: string` - `beta_mcp_tool_result_block_content: array of BetaTextBlock` - `type: "text"` - `citations: array of BetaTextCitation` Citations supporting the text block. The type of citation returned will depend on the type of document being cited. Citing a PDF results in `page_location`, plain text results in `char_location`, and content document results in `content_block_location`. - `text: string` - `is_error: boolean` - `tool_use_id: string` pattern: ^[a-zA-Z0-9_-]+$ - `beta_container_upload_block: object` Response model for a file uploaded to the container. - `type: "container_upload"` - `file_id: string` - `beta_compaction_block: object` A compaction block returned when autocompact is triggered. When content is None, it indicates the compaction failed to produce a valid summary (e.g., malformed output from the model). Clients may round-trip compaction blocks with null content; the server treats them as no-ops. - `type: "compaction"` - `content: string` Summary of compacted content, or null if compaction failed - `encrypted_content: string` Opaque metadata from prior compaction, to be round-tripped verbatim - `signature: optional string` Signature over the summary, to be sent back with the block verbatim - `tool_changes: optional array of BetaResponseToolAdditionBlock or BetaResponseToolRemovalBlock` The tool changes of the compacted range: the `tool_addition` and `tool_removal` blocks that take the request's `tools` to the tool set in effect at the end of the range, or `[]` when the range changed no tool. Absent when the server did not compute them. Send the block back unchanged. - `beta_response_tool_addition_block: object` An entry of a `compaction` block's `tool_changes`: a tool the compacted range made available, as a reference to a `tools` entry or MCP toolset, or as the tool definition in effect at the end of the range, by value. Send it back unchanged. - `type: "tool_addition"` - `tool: BetaResponseToolChangeToolReference or BetaResponseToolChangeMCPToolReference or BetaResponseToolChangeMCPToolsetReference or BetaToolChangeToolDefinition` The tool made available: a reference to a `tools` entry or MCP toolset, or a `tool_definition` carrying the definition by value. - `beta_response_tool_change_tool_reference: object` Reference to a single tool, by the name the model uses to call it, as a `compaction` block's `tool_changes` entry reports it: a tool declared in `tools` or defined by an earlier `tool_addition` block. Send it back unchanged with the block. - `type: "tool_reference"` - `name: string` - `beta_response_tool_change_mcp_tool_reference: object` Reference to a single MCP tool, by its server and its name on that server, as a `compaction` block's `tool_changes` entry reports it. Send it back unchanged with the block. - `type: "mcp_tool_reference"` - `name: string` - `server_name: string` - `beta_response_tool_change_mcp_toolset_reference: object` Reference to every tool in the named MCP server's toolset, as a `compaction` block's `tool_changes` entry reports it. Send it back unchanged with the block. - `type: "mcp_toolset_reference"` - `server_name: string` - `beta_tool_change_tool_definition: object` A tool defined by value, as a `compaction` block's `tool_changes` entry reports it: `definition` is the tool's definition as it was sent, in the form of a `tools` entry, without `cache_control`. Send it back unchanged with the block. - `type: "tool_definition"` - `definition: BetaResponseTool or BetaToolBash20241022 or BetaToolBash20250124 or 25 more` - `beta_response_tool: object` A custom tool definition, as sent. - `type: optional "custom"` - `input_schema: object` [JSON schema](https://json-schema.org/draft/2020-12) for this tool's input. This defines the shape of the `input` that your tool accepts and that the model will produce. - `type: "object"` - `properties: optional map[unknown]` - `required: optional array of string` - `name: string` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. minLength: 1, maxLength: 128, pattern: ^[a-zA-Z0-9_-]{1,128}$ - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `description: optional string` Description of what this tool does. Tool descriptions should be as detailed as possible. The more information that the model has about what the tool is and how to use it, the better it will perform. You can use natural language descriptions to reinforce important aspects of the tool input JSON schema. - `eager_input_streaming: optional boolean` Enable eager input streaming for this tool. When true, tool input parameters will be streamed incrementally as they are generated, and types will be inferred on-the-fly rather than buffering the full JSON output. When false, streaming is disabled for this tool even if the fine-grained-tool-streaming beta is active. When null (default), uses the default behavior based on beta headers. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_bash_20241022: object` - `type: "bash_20241022"` - `name: "bash"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `"5m"` - `"1h"` - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_bash_20250124: object` - `type: "bash_20250124"` - `name: "bash"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_code_execution_tool_20250522: object` - `type: "code_execution_20250522"` - `name: "code_execution"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_code_execution_tool_20250825: object` - `type: "code_execution_20250825"` - `name: "code_execution"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_code_execution_tool_20260120: object` Code execution tool with REPL state persistence (daemon mode + gVisor checkpoint). - `type: "code_execution_20260120"` - `name: "code_execution"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_code_execution_tool_20260521: object` Code execution tool with REPL state persistence. - `type: "code_execution_20260521"` - `name: "code_execution"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_browser_toolset_20260801: object` The browser toolset: a single `tools[]` entry (carrying no `name`) that declares the browser tool family. The model is served the family's tool with any members disabled via `configs` removed from its schema. - `type: "browser_toolset_20260801"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `configs: optional object` Sparse per-member overrides, keyed by member name. Absent, null, and {} are equivalent; a member's defaults apply wherever its key is absent. - `type: optional object` `type`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `close_tab: optional object` `close_tab`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `double_click: optional object` `double_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `file_upload: optional object` `file_upload`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `find: optional object` `find`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `form_input: optional object` `form_input`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `get_page_text: optional object` `get_page_text`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `hold_key: optional object` `hold_key`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `hover: optional object` `hover`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `javascript_exec: optional object` `javascript_exec`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `key: optional object` `key`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_click: optional object` `left_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_click_drag: optional object` `left_click_drag`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_mouse_down: optional object` `left_mouse_down`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_mouse_up: optional object` `left_mouse_up`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `list_tabs: optional object` `list_tabs`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `middle_click: optional object` `middle_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `mouse_move: optional object` `mouse_move`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `navigate: optional object` `navigate`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `new_tab: optional object` `new_tab`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `read_console: optional object` `read_console`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `read_network: optional object` `read_network`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `read_page: optional object` `read_page`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `right_click: optional object` `right_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `screenshot: optional object` `screenshot`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `scroll: optional object` `scroll`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `scroll_to: optional object` `scroll_to`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `switch_tab: optional object` `switch_tab`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `triple_click: optional object` `triple_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `wait: optional object` `wait`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `zoom: optional object` `zoom`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `beta_tool_computer_use_20241022: object` - `type: "computer_20241022"` - `display_height_px: number` The height of the display in pixels. minimum: 1 - `display_width_px: number` The width of the display in pixels. minimum: 1 - `name: "computer"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `display_number: optional number` The X11 display number (e.g. 0, 1) for the display. minimum: 0 - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_memory_tool_20250818: object` - `type: "memory_20250818"` - `name: "memory"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_computer_use_20250124: object` - `type: "computer_20250124"` - `display_height_px: number` The height of the display in pixels. minimum: 1 - `display_width_px: number` The width of the display in pixels. minimum: 1 - `name: "computer"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `display_number: optional number` The X11 display number (e.g. 0, 1) for the display. minimum: 0 - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_text_editor_20241022: object` - `type: "text_editor_20241022"` - `name: "str_replace_editor"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_computer_use_20251124: object` - `type: "computer_20251124"` - `display_height_px: number` The height of the display in pixels. minimum: 1 - `display_width_px: number` The width of the display in pixels. minimum: 1 - `name: "computer"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `display_number: optional number` The X11 display number (e.g. 0, 1) for the display. minimum: 0 - `enable_zoom: optional boolean` Whether to enable an action to take a zoomed-in screenshot of the screen. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_computer_toolset_20260801: object` The computer toolset: a single `tools[]` entry (carrying no `name`) that declares the computer tool family. The model is served the family's tool with any members disabled via `configs` removed from its schema. Every member is enabled by default, zoom included. The single-tool options `display_number` and `enable_zoom` are not fields of a toolset entry — it carries only `type`, `configs`, and `cache_control`; zoom is controlled via `configs.zoom.enabled`. - `type: "computer_toolset_20260801"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `configs: optional object` Sparse per-member overrides, keyed by member name. Absent, null, and {} are equivalent; a member's defaults apply wherever its key is absent. - `type: optional object` `type`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `cursor_position: optional object` `cursor_position`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `double_click: optional object` `double_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `hold_key: optional object` `hold_key`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `key: optional object` `key`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_click: optional object` `left_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_click_drag: optional object` `left_click_drag`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_mouse_down: optional object` `left_mouse_down`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_mouse_up: optional object` `left_mouse_up`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `middle_click: optional object` `middle_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `mouse_move: optional object` `mouse_move`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `right_click: optional object` `right_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `screenshot: optional object` `screenshot`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `scroll: optional object` `scroll`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `triple_click: optional object` `triple_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `wait: optional object` `wait`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `zoom: optional object` `zoom`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `beta_tool_text_editor_20250124: object` - `type: "text_editor_20250124"` - `name: "str_replace_editor"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_text_editor_20250429: object` - `type: "text_editor_20250429"` - `name: "str_replace_based_edit_tool"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_text_editor_20250728: object` - `type: "text_editor_20250728"` - `name: "str_replace_based_edit_tool"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: optional array of map[unknown]` - `max_characters: optional number` Maximum number of characters to display when viewing a file. If not specified, defaults to displaying the full file. minimum: 1 - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_web_search_tool_20250305: object` - `type: "web_search_20250305"` - `name: "web_search"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: optional array of string` If provided, only these domains will be included in results. Cannot be used alongside `blocked_domains`. - `blocked_domains: optional array of string` If provided, these domains will never appear in results. Cannot be used alongside `allowed_domains`. - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `user_location: optional object` Parameters for the user's location. Used to provide more relevant search results. - `type: "approximate"` - `city: optional string` The city of the user. minLength: 1, maxLength: 255 - `country: optional string` The two letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1_alpha-2) of the user. minLength: 2, maxLength: 2 - `region: optional string` The region of the user. minLength: 1, maxLength: 255 - `timezone: optional string` The [IANA timezone](https://nodatime.org/TimeZones) of the user. minLength: 1, maxLength: 255 - `beta_web_fetch_tool_20250910: object` - `type: "web_fetch_20250910"` - `name: "web_fetch"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: optional array of string` List of domains to allow fetching from - `blocked_domains: optional array of string` List of domains to block fetching from - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `citations: optional object` Citations configuration for fetched documents. Citations are disabled by default. - `enabled: optional boolean` - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_content_tokens: optional number` Maximum number of tokens used by including web page text content in the context. The limit is approximate and does not apply to binary content such as PDFs. minimum: 1 - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `url_sources: optional object` Which sources contribute to the set of URLs the tool may fetch. Omitted means every source. - `client_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which client tools' results contribute fetchable URLs: "all", "none", or an only or except list of client tool names from tools[]. - `beta_web_fetch_url_source_all: object` The `url_sources` variant under which a source contributes in full: every result of the tool filter's source, or all user input. - `type: "all"` - `beta_web_fetch_url_source_none: object` The `url_sources` variant under which a source contributes nothing: no result of the tool filter's source, or no user input. - `type: "none"` - `beta_web_fetch_url_source_only: object` The tool filter variant under which only the named tools' results contribute. - `type: "only"` - `tools: array of BetaWebFetchURLSourceToolReference` - `type: "tool_reference"` - `name: string` - `beta_web_fetch_url_source_except: object` The tool filter variant under which every result but the named tools' contributes. - `type: "except"` - `tools: array of BetaWebFetchURLSourceToolReference` - `type: "tool_reference"` - `name: string` - `server_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which server tools' results contribute fetchable URLs: "all", "none", or an only or except list of server tool names from tools[]; only web_search and web_fetch results ever contribute. - `beta_web_fetch_url_source_all: object` The `url_sources` variant under which a source contributes in full: every result of the tool filter's source, or all user input. - `beta_web_fetch_url_source_none: object` The `url_sources` variant under which a source contributes nothing: no result of the tool filter's source, or no user input. - `beta_web_fetch_url_source_only: object` The tool filter variant under which only the named tools' results contribute. - `beta_web_fetch_url_source_except: object` The tool filter variant under which every result but the named tools' contributes. - `user_input: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone` Whether URLs in user messages are fetchable: "all" or "none". - `beta_web_fetch_url_source_all: object` The `url_sources` variant under which a source contributes in full: every result of the tool filter's source, or all user input. - `beta_web_fetch_url_source_none: object` The `url_sources` variant under which a source contributes nothing: no result of the tool filter's source, or no user input. - `beta_web_search_tool_20260209: object` - `type: "web_search_20260209"` - `name: "web_search"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: optional array of string` If provided, only these domains will be included in results. Cannot be used alongside `blocked_domains`. - `blocked_domains: optional array of string` If provided, these domains will never appear in results. Cannot be used alongside `allowed_domains`. - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `user_location: optional object` Parameters for the user's location. Used to provide more relevant search results. - `type: "approximate"` - `city: optional string` The city of the user. minLength: 1, maxLength: 255 - `country: optional string` The two letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1_alpha-2) of the user. minLength: 2, maxLength: 2 - `region: optional string` The region of the user. minLength: 1, maxLength: 255 - `timezone: optional string` The [IANA timezone](https://nodatime.org/TimeZones) of the user. minLength: 1, maxLength: 255 - `beta_web_fetch_tool_20260209: object` - `type: "web_fetch_20260209"` - `name: "web_fetch"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: optional array of string` List of domains to allow fetching from - `blocked_domains: optional array of string` List of domains to block fetching from - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `citations: optional object` Citations configuration for fetched documents. Citations are disabled by default. - `enabled: optional boolean` - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_content_tokens: optional number` Maximum number of tokens used by including web page text content in the context. The limit is approximate and does not apply to binary content such as PDFs. minimum: 1 - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `url_sources: optional object` Which sources contribute to the set of URLs the tool may fetch. Omitted means every source. - `client_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which client tools' results contribute fetchable URLs: "all", "none", or an only or except list of client tool names from tools[]. - `server_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which server tools' results contribute fetchable URLs: "all", "none", or an only or except list of server tool names from tools[]; only web_search and web_fetch results ever contribute. - `user_input: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone` Whether URLs in user messages are fetchable: "all" or "none". - `beta_web_fetch_tool_20260309: object` Web fetch tool with use_cache parameter for bypassing cached content. - `type: "web_fetch_20260309"` - `name: "web_fetch"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: optional array of string` List of domains to allow fetching from - `blocked_domains: optional array of string` List of domains to block fetching from - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `citations: optional object` Citations configuration for fetched documents. Citations are disabled by default. - `enabled: optional boolean` - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_content_tokens: optional number` Maximum number of tokens used by including web page text content in the context. The limit is approximate and does not apply to binary content such as PDFs. minimum: 1 - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `url_sources: optional object` Which sources contribute to the set of URLs the tool may fetch. Omitted means every source. - `client_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which client tools' results contribute fetchable URLs: "all", "none", or an only or except list of client tool names from tools[]. - `server_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which server tools' results contribute fetchable URLs: "all", "none", or an only or except list of server tool names from tools[]; only web_search and web_fetch results ever contribute. - `user_input: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone` Whether URLs in user messages are fetchable: "all" or "none". - `use_cache: optional boolean` Whether to use cached content. Set to false to bypass the cache and fetch fresh content. Only set to false when the user explicitly requests fresh content or when fetching rapidly-changing sources. - `beta_web_search_tool_20260318: object` - `type: "web_search_20260318"` - `name: "web_search"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: optional array of string` If provided, only these domains will be included in results. Cannot be used alongside `blocked_domains`. - `blocked_domains: optional array of string` If provided, these domains will never appear in results. Cannot be used alongside `allowed_domains`. - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `response_inclusion: optional "full" or "excluded"` How this tool's result blocks appear in the API response when the result was consumed by a completed code_execution call in the same turn. 'full' returns the complete content (default). 'excluded' drops the nested server_tool_use and result block pair entirely. Results from direct calls, or from code_execution calls that paused before completing, are always returned in full so they can be sent back on the next turn. - `"full"` - `"excluded"` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `user_location: optional object` Parameters for the user's location. Used to provide more relevant search results. - `type: "approximate"` - `city: optional string` The city of the user. minLength: 1, maxLength: 255 - `country: optional string` The two letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1_alpha-2) of the user. minLength: 2, maxLength: 2 - `region: optional string` The region of the user. minLength: 1, maxLength: 255 - `timezone: optional string` The [IANA timezone](https://nodatime.org/TimeZones) of the user. minLength: 1, maxLength: 255 - `beta_web_fetch_tool_20260318: object` - `type: "web_fetch_20260318"` - `name: "web_fetch"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: optional array of string` List of domains to allow fetching from - `blocked_domains: optional array of string` List of domains to block fetching from - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `citations: optional object` Citations configuration for fetched documents. Citations are disabled by default. - `enabled: optional boolean` - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_content_tokens: optional number` Maximum number of tokens used by including web page text content in the context. The limit is approximate and does not apply to binary content such as PDFs. minimum: 1 - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `response_inclusion: optional "full" or "excluded"` How this tool's result blocks appear in the API response when the result was consumed by a completed code_execution call in the same turn. 'full' returns the complete content (default). 'excluded' drops the nested server_tool_use and result block pair entirely. Results from direct calls, or from code_execution calls that paused before completing, are always returned in full so they can be sent back on the next turn. - `"full"` - `"excluded"` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `url_sources: optional object` Which sources contribute to the set of URLs the tool may fetch. Omitted means every source. - `client_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which client tools' results contribute fetchable URLs: "all", "none", or an only or except list of client tool names from tools[]. - `server_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which server tools' results contribute fetchable URLs: "all", "none", or an only or except list of server tool names from tools[]; only web_search and web_fetch results ever contribute. - `user_input: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone` Whether URLs in user messages are fetchable: "all" or "none". - `use_cache: optional boolean` Whether to use cached content. Set to false to bypass the cache and fetch fresh content. Only set to false when the user explicitly requests fresh content or when fetching rapidly-changing sources. - `beta_advisor_tool_20260301: object` - `type: "advisor_20260301"` - `model: "claude-haiku-5-5" or "claude-sonnet-5-5" or "claude-fable-5-1" or 17 more or string` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-haiku-5-5"` Fastest model for high-volume, real-time tasks - `"claude-sonnet-5-5"` Efficient model for coding and agents - `"claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows - `"claude-opus-5-5"` Powerful intelligence for coding, knowledge work, and long-running agents - `"claude-mythos-5-1"` Our most capable model for cybersecurity and biology research, available through trusted access programs - `"claude-sonnet-5"` Efficient model for coding and agents - `"claude-fable-5"` Next generation of intelligence for the hardest knowledge work and coding problems - `"claude-mythos-5"` Most capable model for cybersecurity and biology research - `"claude-opus-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-8"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-7"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-6"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-6"` Best combination of speed and intelligence - `"claude-haiku-4-5"` - `"claude-haiku-4-5-20251001"` - `"claude-opus-4-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-5-20251101"` Powerful intelligence for long-running agents and coding - `"claude-mythos-preview"` **Deprecated**: Will reach end-of-life on June 30, 2026. Please migrate to claude-mythos-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. New class of intelligence, strongest in coding and cybersecurity - `"claude-sonnet-4-5"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `"claude-sonnet-4-5-20250929"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `name: "advisor"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `caching: optional object` Caching for the advisor's own prompt. When set, each advisor call writes a cache entry at the given TTL so subsequent calls in the same conversation read the stable prefix. When omitted, the advisor prompt is not cached. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_tokens: optional number` Bounds the advisor's total output (thinking + text) per call. When the advisor hits this cap, the returned advisor_result or advisor_redacted_result block carries stop_reason='max_tokens', and a truncation note is appended to the advice text the worker model sees (inside the encrypted blob in redacted mode). When set, the server also emits a remaining-tokens budget block in the advisor's prompt so the advisor self-shapes toward the cap. When omitted, the advisor model's default output cap applies and no budget block is emitted. minimum: 1024 - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_search_tool_bm25_20251119: object` - `type: "tool_search_tool_bm25_20251119" or "tool_search_tool_bm25"` - `"tool_search_tool_bm25_20251119"` - `"tool_search_tool_bm25"` - `name: "tool_search_tool_bm25"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_search_tool_regex_20251119: object` - `type: "tool_search_tool_regex_20251119" or "tool_search_tool_regex"` - `"tool_search_tool_regex_20251119"` - `"tool_search_tool_regex"` - `name: "tool_search_tool_regex"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_mcp_toolset: object` Configuration for a group of tools from an MCP server. Allows configuring enabled status and defer_loading for all tools from an MCP server, with optional per-tool overrides. - `type: "mcp_toolset"` - `mcp_server_name: string` Name of the MCP server to configure tools for minLength: 1, maxLength: 255 - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `configs: optional map[BetaMCPToolConfig]` Configuration overrides for specific tools, keyed by tool name - `defer_loading: optional boolean` - `enabled: optional boolean` - `default_config: optional object` Default configuration applied to all tools from this server - `defer_loading: optional boolean` - `enabled: optional boolean` - `tools: optional array of BetaMCPToolParam` The server's tool listing, pinned: when present, the server is not asked for its tools before sampling and exactly these entries, with `default_config` and `configs` applied, are the toolset's tools. Copy it from the `mcp_tool_listing` block of an earlier response. - `input_schema: map[unknown]` The tool's input schema as the MCP server lists it, verbatim. - `name: string` The tool's name as the MCP server lists it (not prefixed with the server name). minLength: 1 - `description: optional string` The tool's description as the MCP server lists it. - `beta_response_tool_removal_block: object` An entry of a `compaction` block's `tool_changes`: a tool of the request's `tools` (or an MCP tool or toolset) that the compacted range withdrew. Send it back unchanged. - `type: "tool_removal"` - `tool: BetaResponseToolChangeToolReference or BetaResponseToolChangeMCPToolReference or BetaResponseToolChangeMCPToolsetReference` A reference to the withdrawn `tools` entry, MCP tool or MCP toolset. - `beta_response_tool_change_tool_reference: object` Reference to a single tool, by the name the model uses to call it, as a `compaction` block's `tool_changes` entry reports it: a tool declared in `tools` or defined by an earlier `tool_addition` block. Send it back unchanged with the block. - `beta_response_tool_change_mcp_tool_reference: object` Reference to a single MCP tool, by its server and its name on that server, as a `compaction` block's `tool_changes` entry reports it. Send it back unchanged with the block. - `beta_response_tool_change_mcp_toolset_reference: object` Reference to every tool in the named MCP server's toolset, as a `compaction` block's `tool_changes` entry reports it. Send it back unchanged with the block. - `beta_fallback_block: object` Marks the point in `content` where one model's output gives way to the next. One block appears per hop where a preceding model actually ran this turn and declined. A turn where no preceding model ran and declined has no such boundary and carries no block — the signal for whether a fallback model served the response is the presence of a `fallback_message` entry in `usage.iterations`, not this block. The block is treated like a server-tool content block for streaming: it arrives via the standard `content_block_start` / `content_block_stop` pair and carries no deltas. - `type: "fallback"` - `from: object` The model whose output ends at this point — the model that declined at this hop. When the declining hop is the requested model, its `model` echoes the top-level `model` string the caller sent (alias or canonical); when the declining hop is a fallback model, its `model` is that model's canonical id. - `model: "claude-haiku-5-5" or "claude-sonnet-5-5" or "claude-fable-5-1" or 17 more or string` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-haiku-5-5"` Fastest model for high-volume, real-time tasks - `"claude-sonnet-5-5"` Efficient model for coding and agents - `"claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows - `"claude-opus-5-5"` Powerful intelligence for coding, knowledge work, and long-running agents - `"claude-mythos-5-1"` Our most capable model for cybersecurity and biology research, available through trusted access programs - `"claude-sonnet-5"` Efficient model for coding and agents - `"claude-fable-5"` Next generation of intelligence for the hardest knowledge work and coding problems - `"claude-mythos-5"` Most capable model for cybersecurity and biology research - `"claude-opus-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-8"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-7"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-6"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-6"` Best combination of speed and intelligence - `"claude-haiku-4-5"` - `"claude-haiku-4-5-20251001"` - `"claude-opus-4-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-5-20251101"` Powerful intelligence for long-running agents and coding - `"claude-mythos-preview"` **Deprecated**: Will reach end-of-life on June 30, 2026. Please migrate to claude-mythos-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. New class of intelligence, strongest in coding and cybersecurity - `"claude-sonnet-4-5"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `"claude-sonnet-4-5-20250929"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `to: object` The fallback model producing the content that follows this block. Its `model` is always the canonical id. - `model: "claude-haiku-5-5" or "claude-sonnet-5-5" or "claude-fable-5-1" or 17 more or string` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `trigger: object` What caused the `from` model to hand over at this hop. - `type: "refusal"` - `category: "cyber" or "bio" or "frontier_llm" or 2 more` The policy category that triggered the `from` model's refusal at this hop. `null` when the refusal doesn't map to a named category. Same vocabulary as `stop_details.category`. - `"cyber"` The request could enable cyber harm, such as malware or exploit development. Benign cybersecurity work can also trigger this category. - `"bio"` The request could enable biological harm, such as dangerous lab methods. Beneficial life sciences work can also trigger this category. - `"frontier_llm"` The request could assist the development of competing AI models, which is restricted under [Anthropic's commercial terms](https://www.anthropic.com/legal/commercial-terms). Benign machine learning work can also trigger this category. - `"reasoning_extraction"` The request asks the model to reproduce its internal reasoning in the response text. To get reasoning in a structured form instead, use [adaptive thinking](https://platform.claude.com/docs/en/build-with-claude/adaptive-thinking?sdk_languages=cli). - `"general_harms"` The request could be related to an area that was determined as harmful. Benign work might sometimes trigger this category. - `beta_mcp_tool_listing_block: object` The tool listing the server fetched from an MCP server while producing this response. Send the assistant message back unchanged, this block included, so later requests use this listing instead of asking the MCP server again. - `type: "mcp_tool_listing"` - `mcp_server_name: string` - `tools: array of BetaMCPTool` - `input_schema: map[unknown]` - `name: string` - `description: optional string` - `context_management: object` Context management response. Information about context management strategies applied during the request. - `applied_edits: array of BetaClearToolUses20250919EditResponse or BetaClearThinking20251015EditResponse` List of context management edits that were applied. - `beta_clear_tool_uses_20250919_edit_response: object` - `type: "clear_tool_uses_20250919"` The type of context management edit applied. - `cleared_input_tokens: number` Number of input tokens cleared by this edit. minimum: 0 - `cleared_tool_uses: number` Number of tool uses that were cleared. minimum: 0 - `beta_clear_thinking_20251015_edit_response: object` - `type: "clear_thinking_20251015"` The type of context management edit applied. - `cleared_input_tokens: number` Number of input tokens cleared by this edit. minimum: 0 - `cleared_thinking_turns: number` Number of thinking turns that were cleared. minimum: 0 - `diagnostics: object` Request-level diagnostics. `null` when the request did not supply `diagnostics`, or when it did and no prompt-cache divergence was detected. - `cache_miss_reason: BetaCacheMissModelChanged or BetaCacheMissSystemChanged or BetaCacheMissToolsChanged or 3 more` Explains why the prompt cache could not fully reuse the prefix from the request identified by `diagnostics.previous_message_id`. `null` means diagnosis is still pending — the response was serialized before the background comparison completed. - `beta_cache_miss_model_changed: object` - `type: "model_changed"` - `cache_missed_input_tokens: number` Approximate number of input tokens that would have been read from cache had the prefix matched the previous request. - `beta_cache_miss_system_changed: object` - `type: "system_changed"` - `cache_missed_input_tokens: number` Approximate number of input tokens that would have been read from cache had the prefix matched the previous request. - `beta_cache_miss_tools_changed: object` - `type: "tools_changed"` - `cache_missed_input_tokens: number` Approximate number of input tokens that would have been read from cache had the prefix matched the previous request. - `beta_cache_miss_messages_changed: object` - `type: "messages_changed"` - `cache_missed_input_tokens: number` Approximate number of input tokens that would have been read from cache had the prefix matched the previous request. - `beta_cache_miss_previous_message_not_found: object` - `type: "previous_message_not_found"` - `beta_cache_miss_unavailable: object` - `type: "unavailable"` - `model: "claude-haiku-5-5" or "claude-sonnet-5-5" or "claude-fable-5-1" or 17 more or string` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-haiku-5-5"` Fastest model for high-volume, real-time tasks - `"claude-sonnet-5-5"` Efficient model for coding and agents - `"claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows - `"claude-opus-5-5"` Powerful intelligence for coding, knowledge work, and long-running agents - `"claude-mythos-5-1"` Our most capable model for cybersecurity and biology research, available through trusted access programs - `"claude-sonnet-5"` Efficient model for coding and agents - `"claude-fable-5"` Next generation of intelligence for the hardest knowledge work and coding problems - `"claude-mythos-5"` Most capable model for cybersecurity and biology research - `"claude-opus-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-8"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-7"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-6"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-6"` Best combination of speed and intelligence - `"claude-haiku-4-5"` - `"claude-haiku-4-5-20251001"` - `"claude-opus-4-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-5-20251101"` Powerful intelligence for long-running agents and coding - `"claude-mythos-preview"` **Deprecated**: Will reach end-of-life on June 30, 2026. Please migrate to claude-mythos-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. New class of intelligence, strongest in coding and cybersecurity - `"claude-sonnet-4-5"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `"claude-sonnet-4-5-20250929"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `role: "assistant"` Conversational role of the generated message. This will always be `"assistant"`. - `stop_details: object` Structured information about why model output stopped. This is `null` when the `stop_reason` has no additional detail to report. - `type: "refusal"` - `category: "cyber" or "bio" or "frontier_llm" or 2 more` The policy category that triggered the refusal. `null` when the refusal doesn't map to a named category. - `"cyber"` The request could enable cyber harm, such as malware or exploit development. Benign cybersecurity work can also trigger this category. - `"bio"` The request could enable biological harm, such as dangerous lab methods. Beneficial life sciences work can also trigger this category. - `"frontier_llm"` The request could assist the development of competing AI models, which is restricted under [Anthropic's commercial terms](https://www.anthropic.com/legal/commercial-terms). Benign machine learning work can also trigger this category. - `"reasoning_extraction"` The request asks the model to reproduce its internal reasoning in the response text. To get reasoning in a structured form instead, use [adaptive thinking](https://platform.claude.com/docs/en/build-with-claude/adaptive-thinking?sdk_languages=cli). - `"general_harms"` The request could be related to an area that was determined as harmful. Benign work might sometimes trigger this category. - `explanation: string` Human-readable explanation of the refusal. This text is not guaranteed to be stable. `null` when no explanation is available for the category. - `fallback_credit_token: string` Opaque code that refunds the cache-miss cost when retrying this refused request on the fallback model. Pass it as `fallback_credit_token` on the retry request. Expires 5 minutes after the refusal. The retry is sent either with the same request body (`system`, `messages`, `tools`, and other render-shaping fields), or with the same body plus one appended `assistant` message whose content is the partial text (with any trailing whitespace stripped from the final text block) and paired server-tool blocks from this refusal — which also authorizes that appended turn as an assistant-prefill continuation on models that otherwise disallow prefill. A token minted mid-server-tool-loop whose partial content was continuable may only be redeemed the second way — if a same-body retry is rejected with a 400 saying the token must be redeemed by continuing the partial response, retry the second way instead. Either way: same workspace, same platform; a mismatch is a 400. Resending a token for an already-warm prefix is permitted but yields no additional credit. `null` when the refused model isn't eligible for a fallback credit. - `fallback_has_prefill_claim: boolean` Whether the accompanying `fallback_credit_token` may be redeemed with the appended-assistant retry form. Only set when `fallback_credit_token` is present. `true`: retry by resending the same request body plus one appended `assistant` message whose content is this response's `content` with any trailing whitespace stripped from the final text block and unpaired `tool_use` blocks omitted (the same appended-turn shape described on `fallback_credit_token`), with the token attached. `false`: retry by resending the original request body unchanged, with the token attached — the appended-assistant form is not available for this refusal (no continuable partial content, or the request uses `output_format` or a `tool_choice` that forces tool use). One exception: when the request used `output_format` or a forced `tool_choice` and the refusal arrived after server tools (including MCP connector tools) had already executed, the token may not be redeemable by either retry form; if the exact-body retry is then rejected with a 400 saying the token must be redeemed by continuing the partial response, discard the token and retry without it. Advisory: if an appended-assistant retry is rejected with a 400 despite `true`, fall back to resending the original request body with the token. - `recommended_model: string` The server's suggested retry target for this refusal. Populated when a fallback attempt could not be made (the fallback model's rate limit was exhausted, or it was overloaded); names the fallback model the caller can retry directly. Null otherwise. - `stop_reason: "end_turn" or "max_tokens" or "stop_sequence" or 5 more` The reason that we stopped. This may be one the following values: * `"end_turn"`: the model reached a natural stopping point * `"max_tokens"`: we exceeded the requested `max_tokens` or the model's maximum * `"stop_sequence"`: one of your provided custom `stop_sequences` was generated * `"tool_use"`: the model invoked one or more tools * `"pause_turn"`: we paused a long-running turn. You may provide the response back as-is in a subsequent request to let the model continue. * `"refusal"`: when streaming classifiers intervene to handle potential policy violations * `"model_context_window_exceeded"`: we exceeded the model's context window In non-streaming mode this value is always non-null. In streaming mode, it is null in the `message_start` event and non-null otherwise. - `"end_turn"` - `"max_tokens"` - `"stop_sequence"` - `"tool_use"` - `"pause_turn"` - `"compaction"` - `"refusal"` - `"model_context_window_exceeded"` - `stop_sequence: string` Which custom stop sequence was generated, if any. This value will be a non-null string if one of your custom stop sequences was generated. - `usage: object` Billing and rate-limit usage. Anthropic's API bills and rate-limits by token counts, as tokens represent the underlying cost to our systems. Under the hood, the API transforms requests into a format suitable for the model. The model's output then goes through a parsing stage before becoming an API response. As a result, the token counts in `usage` will not match one-to-one with the exact visible content of an API request or response. For example, `output_tokens` will be non-zero, even for an empty string response from Claude. Total input tokens in a request is the summation of `input_tokens`, `cache_creation_input_tokens`, and `cache_read_input_tokens`. - `cache_creation: object` Breakdown of cached tokens by TTL - `ephemeral_1h_input_tokens: number` The number of input tokens used to create the 1 hour cache entry. minimum: 0 - `ephemeral_5m_input_tokens: number` The number of input tokens used to create the 5 minute cache entry. minimum: 0 - `cache_creation_input_tokens: number` The number of input tokens used to create the cache entry. minimum: 0 - `cache_read_input_tokens: number` The number of input tokens read from the cache. minimum: 0 - `fallback_credit: object` Outcome of the `fallback_credit_token` presented on this request. Present on every response to a non-batch request that carried a `fallback_credit_token`, in either redemption mode; absent otherwise (batch items accept and ignore the token and carry no outcome object). - `status: BetaFallbackCreditRedeemed or BetaFallbackCreditNotApplied` Whether the fallback-credit reprice was applied to this response's billing. A union discriminated on `type`. `redeemed`: the retry is billed as if the conversation had been on the retry model all along — including when the resulting shift is zero because there was nothing to move. `not_applied`: no reprice was applied; the arm's `reason` says why. - `beta_fallback_credit_redeemed: object` The reprice was applied: the retry is billed as if the conversation had been on the retry model all along. - `type: "redeemed"` - `beta_fallback_credit_not_applied: object` No reprice was applied; `reason` says why. - `type: "not_applied"` - `reason: "body_mismatch" or "continuation_excluded" or "continuation_only" or 9 more` Why the reprice was not applied. A closed enum; additions to the redemption-check vocabulary arrive as deliberate schema updates. - `"body_mismatch"` - `"continuation_excluded"` - `"continuation_only"` - `"expired"` - `"invalid_target_model"` - `"not_enabled"` - `"reprice_unavailable"` - `"temporarily_unavailable"` - `"variant_fields_present"` - `"wrong_organization"` - `"wrong_platform"` - `"wrong_workspace"` - `remove_to_redeem: optional array of string` Request fields to remove before retrying, so the retry can redeem this token. Present exactly when `reason` is `variant_fields_present` — never null, never an empty array; absent otherwise. Fields are named only from your own request, and only after the sealed variant hash matched. A served best-effort retry has already been billed at normal price; nothing redeems retroactively, but a corrected re-send inside the token's five-minute window can still redeem. - `inference_geo: string` The geographic region where inference was performed for this request. - `input_tokens: number` The number of input tokens which were used. minimum: 0 - `iterations: array of BetaMessageIterationUsage or BetaCompactionIterationUsage or BetaAdvisorMessageIterationUsage or BetaFallbackMessageIterationUsage` Per-iteration token usage breakdown. Each entry represents one sampling iteration, with its own input/output token counts and cache statistics, discriminated by `type`. For `message` entries (model sampling iterations, such as the turns of a server-side tool use loop), this allows you to: - Calculate the context window size from the last `message` entry - Understand token accumulation across server-side tool use loops A `compaction` entry reports the token usage of the compaction operation itself — the server-side request that summarizes the context being closed — NOT the size of the context that was compacted away, and its token counts can be much smaller than that closed context (for example, a compaction that closes a ~200k-token context can report only a few thousand tokens). Do not derive the context window size from a `compaction` entry, even when it is the last entry. A `compaction` entry's tokens are not included in the top-level `usage` fields. When an input-token trigger is in effect (the default — 150,000 tokens unless configured otherwise), each `compaction` entry closes a context that had reached at least that threshold, though the context can exceed it by the final iteration's output and tool results. - `beta_message_iteration_usage: object` Token usage for a sampling iteration. - `type: "message"` Usage for a sampling iteration - `cache_creation: object` Breakdown of cached tokens by TTL - `ephemeral_1h_input_tokens: number` The number of input tokens used to create the 1 hour cache entry. minimum: 0 - `ephemeral_5m_input_tokens: number` The number of input tokens used to create the 5 minute cache entry. minimum: 0 - `cache_creation_input_tokens: number` The number of input tokens used to create the cache entry. minimum: 0 - `cache_read_input_tokens: number` The number of input tokens read from the cache. minimum: 0 - `input_tokens: number` The number of input tokens which were used. minimum: 0 - `model: "claude-haiku-5-5" or "claude-sonnet-5-5" or "claude-fable-5-1" or 17 more or string` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-haiku-5-5"` Fastest model for high-volume, real-time tasks - `"claude-sonnet-5-5"` Efficient model for coding and agents - `"claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows - `"claude-opus-5-5"` Powerful intelligence for coding, knowledge work, and long-running agents - `"claude-mythos-5-1"` Our most capable model for cybersecurity and biology research, available through trusted access programs - `"claude-sonnet-5"` Efficient model for coding and agents - `"claude-fable-5"` Next generation of intelligence for the hardest knowledge work and coding problems - `"claude-mythos-5"` Most capable model for cybersecurity and biology research - `"claude-opus-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-8"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-7"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-6"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-6"` Best combination of speed and intelligence - `"claude-haiku-4-5"` - `"claude-haiku-4-5-20251001"` - `"claude-opus-4-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-5-20251101"` Powerful intelligence for long-running agents and coding - `"claude-mythos-preview"` **Deprecated**: Will reach end-of-life on June 30, 2026. Please migrate to claude-mythos-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. New class of intelligence, strongest in coding and cybersecurity - `"claude-sonnet-4-5"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `"claude-sonnet-4-5-20250929"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `output_tokens: number` The number of output tokens which were used. minimum: 0 - `beta_compaction_iteration_usage: object` Token usage for a compaction iteration. - `type: "compaction"` Usage for a compaction iteration - `cache_creation: object` Breakdown of cached tokens by TTL - `ephemeral_1h_input_tokens: number` The number of input tokens used to create the 1 hour cache entry. minimum: 0 - `ephemeral_5m_input_tokens: number` The number of input tokens used to create the 5 minute cache entry. minimum: 0 - `cache_creation_input_tokens: number` The number of input tokens used to create the cache entry. minimum: 0 - `cache_read_input_tokens: number` The number of input tokens read from the cache. minimum: 0 - `input_tokens: number` The number of input tokens which were used. minimum: 0 - `output_tokens: number` The number of output tokens which were used. minimum: 0 - `beta_advisor_message_iteration_usage: object` Token usage for an advisor sub-inference iteration. - `type: "advisor_message"` Usage for an advisor sub-inference iteration - `cache_creation: object` Breakdown of cached tokens by TTL - `ephemeral_1h_input_tokens: number` The number of input tokens used to create the 1 hour cache entry. minimum: 0 - `ephemeral_5m_input_tokens: number` The number of input tokens used to create the 5 minute cache entry. minimum: 0 - `cache_creation_input_tokens: number` The number of input tokens used to create the cache entry. minimum: 0 - `cache_read_input_tokens: number` The number of input tokens read from the cache. minimum: 0 - `input_tokens: number` The number of input tokens which were used. minimum: 0 - `model: "claude-haiku-5-5" or "claude-sonnet-5-5" or "claude-fable-5-1" or 17 more or string` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-haiku-5-5"` Fastest model for high-volume, real-time tasks - `"claude-sonnet-5-5"` Efficient model for coding and agents - `"claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows - `"claude-opus-5-5"` Powerful intelligence for coding, knowledge work, and long-running agents - `"claude-mythos-5-1"` Our most capable model for cybersecurity and biology research, available through trusted access programs - `"claude-sonnet-5"` Efficient model for coding and agents - `"claude-fable-5"` Next generation of intelligence for the hardest knowledge work and coding problems - `"claude-mythos-5"` Most capable model for cybersecurity and biology research - `"claude-opus-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-8"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-7"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-6"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-6"` Best combination of speed and intelligence - `"claude-haiku-4-5"` - `"claude-haiku-4-5-20251001"` - `"claude-opus-4-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-5-20251101"` Powerful intelligence for long-running agents and coding - `"claude-mythos-preview"` **Deprecated**: Will reach end-of-life on June 30, 2026. Please migrate to claude-mythos-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. New class of intelligence, strongest in coding and cybersecurity - `"claude-sonnet-4-5"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `"claude-sonnet-4-5-20250929"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `output_tokens: number` The number of output tokens which were used. minimum: 0 - `beta_fallback_message_iteration_usage: object` Token usage for the fallback-model attempt of a server-side fallback request. The terminal entry of a fallback-served turn: when a fallback hop's output is the returned message, the entry for the iteration that completed it carries this type in place of `message`. A declined hop and the serving hop's earlier tool-loop iterations produce `message` entries. Whether a fallback model served the response is signalled by the presence of this entry in `usage.iterations`. - `type: "fallback_message"` Usage for the fallback-model attempt that served the response - `cache_creation: object` Breakdown of cached tokens by TTL - `ephemeral_1h_input_tokens: number` The number of input tokens used to create the 1 hour cache entry. minimum: 0 - `ephemeral_5m_input_tokens: number` The number of input tokens used to create the 5 minute cache entry. minimum: 0 - `cache_creation_input_tokens: number` The number of input tokens used to create the cache entry. minimum: 0 - `cache_read_input_tokens: number` The number of input tokens read from the cache. minimum: 0 - `input_tokens: number` The number of input tokens which were used. minimum: 0 - `model: "claude-haiku-5-5" or "claude-sonnet-5-5" or "claude-fable-5-1" or 17 more or string` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-haiku-5-5"` Fastest model for high-volume, real-time tasks - `"claude-sonnet-5-5"` Efficient model for coding and agents - `"claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows - `"claude-opus-5-5"` Powerful intelligence for coding, knowledge work, and long-running agents - `"claude-mythos-5-1"` Our most capable model for cybersecurity and biology research, available through trusted access programs - `"claude-sonnet-5"` Efficient model for coding and agents - `"claude-fable-5"` Next generation of intelligence for the hardest knowledge work and coding problems - `"claude-mythos-5"` Most capable model for cybersecurity and biology research - `"claude-opus-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-8"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-7"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-6"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-6"` Best combination of speed and intelligence - `"claude-haiku-4-5"` - `"claude-haiku-4-5-20251001"` - `"claude-opus-4-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-5-20251101"` Powerful intelligence for long-running agents and coding - `"claude-mythos-preview"` **Deprecated**: Will reach end-of-life on June 30, 2026. Please migrate to claude-mythos-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. New class of intelligence, strongest in coding and cybersecurity - `"claude-sonnet-4-5"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `"claude-sonnet-4-5-20250929"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `output_tokens: number` The number of output tokens which were used. minimum: 0 - `output_tokens: number` The number of output tokens which were used. minimum: 0 - `output_tokens_details: object` Breakdown of output tokens by category. `output_tokens` remains the inclusive, authoritative total used for billing. This object provides a read-only decomposition for observability — for example, how many of the billed output tokens were spent on internal reasoning that may have been summarized before being returned to you. - `thinking_tokens: number` Number of output tokens the model generated as internal reasoning, including the thinking-block delimiter tokens. Reflects the raw reasoning the model produced, not the (possibly shorter) summarized thinking text returned in the response body. Computed by re-tokenizing the raw reasoning text, so it may differ from the model's exact generation count by a small number of tokens. Always ≤ `output_tokens`; `output_tokens - thinking_tokens` approximates the non-reasoning output. minimum: 0 - `server_tool_use: object` The number of server tool requests. - `web_fetch_requests: number` The number of web fetch tool requests. minimum: 0 - `web_search_requests: number` The number of web search tool requests. minimum: 0 - `service_tier: "standard" or "priority" or "batch"` If the request used the priority, standard, or batch tier. - `"standard"` - `"priority"` - `"batch"` - `speed: "standard" or "fast"` The inference speed mode used for this request. - `"standard"` - `"fast"` - `input_transformations: optional array of BetaInputTransformation` Changes the API made to the request's input before showing it to the model, and blocks that failed a binding check but were left unchanged: one entry per block, in request order. Two entry types today. `thinking_dropped` — a `thinking`, `redacted_thinking` or `connector_text` block from the request's `messages` that was removed from the prompt instead of being shown to the model because it failed a binding check. `thinking_mismatch_allowed` — a `thinking` or `redacted_thinking` block that failed the conversation check (the conversation before it differs from the one it was created in, or it carries no record of one on a model that requires it) and was shown to the model all the same, because that check is not enforced for this request. More entry types may be added over time; ignore types you do not recognize. Requires `anthropic-beta: thinking-binding-controls-2026-08-01`. Present on every such response from a model that supports extended thinking, as `[]` when there is no entry to report; without the beta, blocks are removed or left in place all the same but nothing is reported. Removed blocks contribute nothing to `usage.input_tokens`; blocks left in place count as sent. When streaming, the array is final in `message_start`; the final `message_delta` event carries it only when a server-side model fallback happened mid-stream, in which case it holds the serving model's entries and replaces the one in `message_start`. - `beta_thinking_dropped_input_transformation: object` - `type: "thinking_dropped"` Always `thinking_dropped` for this entry type. - `path: string` Where the removed block was in your request, as `messages.{i}.content.{j}`: `i` indexes the `messages` array you sent and `j` that message's `content` array — the same form error messages use. - `reason: "model_binding_mismatch" or "prefix_binding_mismatch" or "organization_binding_mismatch" or "end_user_binding_mismatch"` Which binding check removed the block: `model_binding_mismatch` — it was created by a model whose reasoning the requested model may not read; `prefix_binding_mismatch` — the conversation before it differs from the conversation it was created in (the rest of that turn's consecutive thinking blocks are removed with it, each with this reason); `organization_binding_mismatch` — it was created under a different organization (an Anthropic organization, AWS account or Google Cloud project) and this organization is not one of its additional organizations; `end_user_binding_mismatch` — it was created for a different end user, or was removed by the consumer-organization binding. A block that would fail several checks reports one reason, in this order of precedence: `organization_binding_mismatch`, `end_user_binding_mismatch`, `model_binding_mismatch`, `prefix_binding_mismatch`. - `"model_binding_mismatch"` - `"prefix_binding_mismatch"` - `"organization_binding_mismatch"` - `"end_user_binding_mismatch"` - `beta_thinking_mismatch_allowed_input_transformation: object` - `type: "thinking_mismatch_allowed"` Always `thinking_mismatch_allowed` for this entry type. - `path: string` Where the block is in your request, as `messages.{i}.content.{j}`: `i` indexes the `messages` array you sent and `j` that message's `content` array — the same form error messages use. - `reason: "model_binding_mismatch" or "prefix_binding_mismatch" or "organization_binding_mismatch" or "end_user_binding_mismatch"` Which binding check the block failed; the block was shown to the model all the same. Always `prefix_binding_mismatch` today — the conversation before the block differs from the conversation it was created in, or the block carries no record of one on a model that requires it. Were the check enforced for this request, the block would have been removed or the request rejected (`thinking.block_binding.prefix_mismatch_behavior`). A removal also takes the rest of that turn's consecutive thinking blocks, whereas here each block is checked on its own, so `thinking_mismatch_allowed` entries are a lower bound on what enforcement would remove. - `"model_binding_mismatch"` - `"prefix_binding_mismatch"` - `"organization_binding_mismatch"` - `"end_user_binding_mismatch"` - `beta_raw_message_delta_event: object` - `type: "message_delta"` - `context_management: object` Information about context management strategies applied during the request - `applied_edits: array of BetaClearToolUses20250919EditResponse or BetaClearThinking20251015EditResponse` List of context management edits that were applied. - `delta: object` - `container: object` Information about the container used in this request. This will be non-null if a container tool (e.g. code execution) was used. - `id: string` Identifier for the container used in this request - `expires_at: string` The time at which the container will expire. format: date-time - `skills: array of BetaContainerSkill` Skills loaded in the container - `stop_details: object` Structured information about why model output stopped. This is `null` when the `stop_reason` has no additional detail to report. - `type: "refusal"` - `category: "cyber" or "bio" or "frontier_llm" or 2 more` The policy category that triggered the refusal. `null` when the refusal doesn't map to a named category. - `explanation: string` Human-readable explanation of the refusal. This text is not guaranteed to be stable. `null` when no explanation is available for the category. - `fallback_credit_token: string` Opaque code that refunds the cache-miss cost when retrying this refused request on the fallback model. Pass it as `fallback_credit_token` on the retry request. Expires 5 minutes after the refusal. The retry is sent either with the same request body (`system`, `messages`, `tools`, and other render-shaping fields), or with the same body plus one appended `assistant` message whose content is the partial text (with any trailing whitespace stripped from the final text block) and paired server-tool blocks from this refusal — which also authorizes that appended turn as an assistant-prefill continuation on models that otherwise disallow prefill. A token minted mid-server-tool-loop whose partial content was continuable may only be redeemed the second way — if a same-body retry is rejected with a 400 saying the token must be redeemed by continuing the partial response, retry the second way instead. Either way: same workspace, same platform; a mismatch is a 400. Resending a token for an already-warm prefix is permitted but yields no additional credit. `null` when the refused model isn't eligible for a fallback credit. - `fallback_has_prefill_claim: boolean` Whether the accompanying `fallback_credit_token` may be redeemed with the appended-assistant retry form. Only set when `fallback_credit_token` is present. `true`: retry by resending the same request body plus one appended `assistant` message whose content is this response's `content` with any trailing whitespace stripped from the final text block and unpaired `tool_use` blocks omitted (the same appended-turn shape described on `fallback_credit_token`), with the token attached. `false`: retry by resending the original request body unchanged, with the token attached — the appended-assistant form is not available for this refusal (no continuable partial content, or the request uses `output_format` or a `tool_choice` that forces tool use). One exception: when the request used `output_format` or a forced `tool_choice` and the refusal arrived after server tools (including MCP connector tools) had already executed, the token may not be redeemable by either retry form; if the exact-body retry is then rejected with a 400 saying the token must be redeemed by continuing the partial response, discard the token and retry without it. Advisory: if an appended-assistant retry is rejected with a 400 despite `true`, fall back to resending the original request body with the token. - `recommended_model: string` The server's suggested retry target for this refusal. Populated when a fallback attempt could not be made (the fallback model's rate limit was exhausted, or it was overloaded); names the fallback model the caller can retry directly. Null otherwise. - `stop_reason: "end_turn" or "max_tokens" or "stop_sequence" or 5 more` - `"end_turn"` - `"max_tokens"` - `"stop_sequence"` - `"tool_use"` - `"pause_turn"` - `"compaction"` - `"refusal"` - `"model_context_window_exceeded"` - `stop_sequence: string` - `usage: object` Billing and rate-limit usage. Anthropic's API bills and rate-limits by token counts, as tokens represent the underlying cost to our systems. Under the hood, the API transforms requests into a format suitable for the model. The model's output then goes through a parsing stage before becoming an API response. As a result, the token counts in `usage` will not match one-to-one with the exact visible content of an API request or response. For example, `output_tokens` will be non-zero, even for an empty string response from Claude. Total input tokens in a request is the summation of `input_tokens`, `cache_creation_input_tokens`, and `cache_read_input_tokens`. - `cache_creation_input_tokens: number` The cumulative number of input tokens used to create the cache entry. minimum: 0 - `cache_read_input_tokens: number` The cumulative number of input tokens read from the cache. minimum: 0 - `fallback_credit: object` Outcome of the `fallback_credit_token` presented on this request. Present on every response to a non-batch request that carried a `fallback_credit_token`, in either redemption mode; absent otherwise (batch items accept and ignore the token and carry no outcome object). - `status: BetaFallbackCreditRedeemed or BetaFallbackCreditNotApplied` Whether the fallback-credit reprice was applied to this response's billing. A union discriminated on `type`. `redeemed`: the retry is billed as if the conversation had been on the retry model all along — including when the resulting shift is zero because there was nothing to move. `not_applied`: no reprice was applied; the arm's `reason` says why. - `input_tokens: number` The cumulative number of input tokens which were used. minimum: 0 - `iterations: array of BetaMessageIterationUsage or BetaCompactionIterationUsage or BetaAdvisorMessageIterationUsage or BetaFallbackMessageIterationUsage` Per-iteration token usage breakdown. Each entry represents one sampling iteration, with its own input/output token counts and cache statistics, discriminated by `type`. For `message` entries (model sampling iterations, such as the turns of a server-side tool use loop), this allows you to: - Calculate the context window size from the last `message` entry - Understand token accumulation across server-side tool use loops A `compaction` entry reports the token usage of the compaction operation itself — the server-side request that summarizes the context being closed — NOT the size of the context that was compacted away, and its token counts can be much smaller than that closed context (for example, a compaction that closes a ~200k-token context can report only a few thousand tokens). Do not derive the context window size from a `compaction` entry, even when it is the last entry. A `compaction` entry's tokens are not included in the top-level `usage` fields. When an input-token trigger is in effect (the default — 150,000 tokens unless configured otherwise), each `compaction` entry closes a context that had reached at least that threshold, though the context can exceed it by the final iteration's output and tool results. - `beta_message_iteration_usage: object` Token usage for a sampling iteration. - `beta_compaction_iteration_usage: object` Token usage for a compaction iteration. - `beta_advisor_message_iteration_usage: object` Token usage for an advisor sub-inference iteration. - `beta_fallback_message_iteration_usage: object` Token usage for the fallback-model attempt of a server-side fallback request. The terminal entry of a fallback-served turn: when a fallback hop's output is the returned message, the entry for the iteration that completed it carries this type in place of `message`. A declined hop and the serving hop's earlier tool-loop iterations produce `message` entries. Whether a fallback model served the response is signalled by the presence of this entry in `usage.iterations`. - `output_tokens: number` The cumulative number of output tokens which were used. - `output_tokens_details: object` Breakdown of output tokens by category. `output_tokens` remains the inclusive, authoritative total used for billing. This object provides a read-only decomposition for observability — for example, how many of the billed output tokens were spent on internal reasoning that may have been summarized before being returned to you. - `thinking_tokens: number` Number of output tokens the model generated as internal reasoning, including the thinking-block delimiter tokens. Reflects the raw reasoning the model produced, not the (possibly shorter) summarized thinking text returned in the response body. Computed by re-tokenizing the raw reasoning text, so it may differ from the model's exact generation count by a small number of tokens. Always ≤ `output_tokens`; `output_tokens - thinking_tokens` approximates the non-reasoning output. minimum: 0 - `server_tool_use: object` The number of server tool requests. - `web_fetch_requests: number` The number of web fetch tool requests. minimum: 0 - `web_search_requests: number` The number of web search tool requests. minimum: 0 - `input_transformations: optional array of BetaInputTransformation` Changes the API made to the request's input before showing it to the model, and blocks that failed a binding check but were left unchanged: one entry per block, in request order. Two entry types today. `thinking_dropped` — a `thinking`, `redacted_thinking` or `connector_text` block from the request's `messages` that was removed from the prompt instead of being shown to the model because it failed a binding check. `thinking_mismatch_allowed` — a `thinking` or `redacted_thinking` block that failed the conversation check (the conversation before it differs from the one it was created in, or it carries no record of one on a model that requires it) and was shown to the model all the same, because that check is not enforced for this request. More entry types may be added over time; ignore types you do not recognize. Requires `anthropic-beta: thinking-binding-controls-2026-08-01`. Present on every such response from a model that supports extended thinking, as `[]` when there is no entry to report; without the beta, blocks are removed or left in place all the same but nothing is reported. Removed blocks contribute nothing to `usage.input_tokens`; blocks left in place count as sent. When streaming, the array is final in `message_start`; the final `message_delta` event carries it only when a server-side model fallback happened mid-stream, in which case it holds the serving model's entries and replaces the one in `message_start`. - `beta_thinking_dropped_input_transformation: object` - `beta_thinking_mismatch_allowed_input_transformation: object` - `beta_raw_message_stop_event: object` - `type: "message_stop"` - `beta_raw_content_block_start_event: object` - `type: "content_block_start"` - `content_block: BetaTextBlock or BetaThinkingBlock or BetaRedactedThinkingBlock or 15 more` - `beta_text_block: object` - `type: "text"` - `citations: array of BetaTextCitation` Citations supporting the text block. The type of citation returned will depend on the type of document being cited. Citing a PDF results in `page_location`, plain text results in `char_location`, and content document results in `content_block_location`. - `text: string` - `beta_thinking_block: object` - `type: "thinking"` - `signature: string` A value used to verify that this thinking block was generated by Claude when it is passed back to the API. This is an opaque field and should not be interpreted or parsed. When passing thinking blocks back to the API (required when using tools with extended thinking), pass them back exactly as received, with this field intact. See [extended thinking](https://platform.claude.com/docs/en/build-with-claude/extended-thinking?sdk_languages=cli) for details. - `thinking: string` The text of Claude's thinking process for this block. - `beta_redacted_thinking_block: object` - `type: "redacted_thinking"` - `data: string` The contents of this redacted thinking block, returned when portions of the model's thinking were safety-redacted. This field is opaque and encrypted, with no readable content. Pass `redacted_thinking` blocks back to the API unchanged when continuing a multi-turn conversation. See [extended thinking](https://platform.claude.com/docs/en/build-with-claude/extended-thinking?sdk_languages=cli#redacted-thinking-blocks) for details. - `beta_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: map[unknown]` - `name: string` minLength: 1 - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` - `toolset_name: optional string` For a toolset member tool_use, the toolset family. minLength: 1, maxLength: 64, pattern: ^[a-zA-Z0-9_-]+$ - `beta_server_tool_use_block: object` - `type: "server_tool_use"` - `id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `input: map[unknown]` - `name: "advisor" or "web_search" or "web_fetch" or 5 more` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` - `beta_web_search_tool_result_block: object` - `type: "web_search_tool_result"` - `content: BetaWebSearchToolResultError or array of BetaWebSearchResultBlock` - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` - `beta_web_fetch_tool_result_block: object` - `type: "web_fetch_tool_result"` - `content: BetaWebFetchToolResultErrorBlock or BetaWebFetchBlock` - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` - `beta_advisor_tool_result_block: object` - `type: "advisor_tool_result"` - `content: BetaAdvisorToolResultError or BetaAdvisorResultBlock or BetaAdvisorRedactedResultBlock` - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `beta_code_execution_tool_result_block: object` - `type: "code_execution_tool_result"` - `content: BetaCodeExecutionToolResultError or BetaCodeExecutionResultBlock or BetaEncryptedCodeExecutionResultBlock` - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `beta_bash_code_execution_tool_result_block: object` - `type: "bash_code_execution_tool_result"` - `content: BetaBashCodeExecutionToolResultError or BetaBashCodeExecutionResultBlock` - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `beta_text_editor_code_execution_tool_result_block: object` - `type: "text_editor_code_execution_tool_result"` - `content: BetaTextEditorCodeExecutionToolResultError or BetaTextEditorCodeExecutionViewResultBlock or BetaTextEditorCodeExecutionCreateResultBlock or BetaTextEditorCodeExecutionStrReplaceResultBlock` - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `beta_tool_search_tool_result_block: object` - `type: "tool_search_tool_result"` - `content: BetaToolSearchToolResultError or BetaToolSearchToolSearchResultBlock` - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `beta_mcp_tool_use_block: object` - `type: "mcp_tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: map[unknown]` - `name: string` The name of the MCP tool - `server_name: string` The name of the MCP server - `beta_mcp_tool_result_block: object` - `type: "mcp_tool_result"` - `content: string or array of BetaTextBlock` - `is_error: boolean` - `tool_use_id: string` pattern: ^[a-zA-Z0-9_-]+$ - `beta_container_upload_block: object` Response model for a file uploaded to the container. - `type: "container_upload"` - `file_id: string` - `beta_compaction_block: object` A compaction block returned when autocompact is triggered. When content is None, it indicates the compaction failed to produce a valid summary (e.g., malformed output from the model). Clients may round-trip compaction blocks with null content; the server treats them as no-ops. - `type: "compaction"` - `content: string` Summary of compacted content, or null if compaction failed - `encrypted_content: string` Opaque metadata from prior compaction, to be round-tripped verbatim - `signature: optional string` Signature over the summary, to be sent back with the block verbatim - `tool_changes: optional array of BetaResponseToolAdditionBlock or BetaResponseToolRemovalBlock` The tool changes of the compacted range: the `tool_addition` and `tool_removal` blocks that take the request's `tools` to the tool set in effect at the end of the range, or `[]` when the range changed no tool. Absent when the server did not compute them. Send the block back unchanged. - `beta_fallback_block: object` Marks the point in `content` where one model's output gives way to the next. One block appears per hop where a preceding model actually ran this turn and declined. A turn where no preceding model ran and declined has no such boundary and carries no block — the signal for whether a fallback model served the response is the presence of a `fallback_message` entry in `usage.iterations`, not this block. The block is treated like a server-tool content block for streaming: it arrives via the standard `content_block_start` / `content_block_stop` pair and carries no deltas. - `type: "fallback"` - `from: object` The model whose output ends at this point — the model that declined at this hop. When the declining hop is the requested model, its `model` echoes the top-level `model` string the caller sent (alias or canonical); when the declining hop is a fallback model, its `model` is that model's canonical id. - `to: object` The fallback model producing the content that follows this block. Its `model` is always the canonical id. - `trigger: object` What caused the `from` model to hand over at this hop. - `beta_mcp_tool_listing_block: object` The tool listing the server fetched from an MCP server while producing this response. Send the assistant message back unchanged, this block included, so later requests use this listing instead of asking the MCP server again. - `type: "mcp_tool_listing"` - `mcp_server_name: string` - `tools: array of BetaMCPTool` - `index: number` - `beta_raw_content_block_delta_event: object` - `type: "content_block_delta"` - `delta: BetaTextDelta or BetaInputJSONDelta or BetaCitationsDelta or 3 more` - `beta_text_delta: object` - `type: "text_delta"` - `text: string` - `beta_input_json_delta: object` - `type: "input_json_delta"` - `partial_json: string` - `beta_citations_delta: object` - `type: "citations_delta"` - `citation: BetaCitationCharLocation or BetaCitationPageLocation or BetaCitationContentBlockLocation or 2 more` - `beta_citation_char_location: object` - `type: "char_location"` - `cited_text: string` - `document_index: number` minimum: 0 - `document_title: string` - `end_char_index: number` - `file_id: string` - `start_char_index: number` minimum: 0 - `beta_citation_page_location: object` - `type: "page_location"` - `cited_text: string` - `document_index: number` minimum: 0 - `document_title: string` - `end_page_number: number` - `file_id: string` - `start_page_number: number` minimum: 1 - `beta_citation_content_block_location: object` - `type: "content_block_location"` - `cited_text: string` The full text of the cited block range, concatenated. Always equals the contents of `content[start_block_index:end_block_index]` joined together. The text block is the minimal citable unit; this field is never a substring of a single block. Not counted toward output tokens, and not counted toward input tokens when sent back in subsequent turns. - `document_index: number` minimum: 0 - `document_title: string` - `end_block_index: number` Exclusive 0-based end index of the cited block range in the source's `content` array. Always greater than `start_block_index`; a single-block citation has `end_block_index = start_block_index + 1`. - `file_id: string` - `start_block_index: number` 0-based index of the first cited block in the source's `content` array. minimum: 0 - `beta_citations_web_search_result_location: object` - `type: "web_search_result_location"` - `cited_text: string` - `encrypted_index: string` - `title: string` maxLength: 512 - `url: string` - `beta_citation_search_result_location: object` - `type: "search_result_location"` - `cited_text: string` The full text of the cited block range, concatenated. Always equals the contents of `content[start_block_index:end_block_index]` joined together. The text block is the minimal citable unit; this field is never a substring of a single block. Not counted toward output tokens, and not counted toward input tokens when sent back in subsequent turns. - `end_block_index: number` Exclusive 0-based end index of the cited block range in the source's `content` array. Always greater than `start_block_index`; a single-block citation has `end_block_index = start_block_index + 1`. - `search_result_index: number` 0-based index of the cited search result among all `search_result` content blocks in the request, in the order they appear across messages and tool results. Counted separately from `document_index`; server-side web search results are not included in this count. minimum: 0 - `source: string` - `start_block_index: number` 0-based index of the first cited block in the source's `content` array. minimum: 0 - `title: string` - `beta_thinking_delta: object` - `type: "thinking_delta"` - `estimated_tokens: number` Per-frame increment of a coarse, running estimate of the tokens this thinking block has produced so far. Present whenever the `thinking-token-count-2026-05-13` beta is set; `null` unless `thinking.display` resolves to `"omitted"` and a count is due this frame. Sum the increments across `thinking_delta` frames on this block for a progress indicator. Each increment is a non-negative multiple of a fixed quantum and the cadence is rate-limited, so this is a deliberately lossy display hint, not a billable count; `usage.output_tokens` remains authoritative. - `thinking: string` The incremental `thinking` text for this content block. Concatenate the `thinking` values of successive `thinking_delta` events to assemble the block's full `thinking` value. - `beta_signature_delta: object` - `type: "signature_delta"` - `signature: string` The `signature` for this thinking block: an opaque value used to verify that the block was generated by Claude when it is passed back to the API. Delivered in a `signature_delta` event just before the block's `content_block_stop` event. - `beta_compaction_content_block_delta: object` - `type: "compaction_delta"` - `content: string` - `encrypted_content: string` Opaque metadata from prior compaction, to be round-tripped verbatim - `index: number` - `beta_raw_content_block_stop_event: object` - `type: "content_block_stop"` - `index: number` ### Beta Redacted Thinking Block - `beta_redacted_thinking_block: object` - `type: "redacted_thinking"` - `data: string` The contents of this redacted thinking block, returned when portions of the model's thinking were safety-redacted. This field is opaque and encrypted, with no readable content. Pass `redacted_thinking` blocks back to the API unchanged when continuing a multi-turn conversation. See [extended thinking](https://platform.claude.com/docs/en/build-with-claude/extended-thinking?sdk_languages=cli#redacted-thinking-blocks) for details. ### Beta Redacted Thinking Block Param - `beta_redacted_thinking_block_param: object` - `type: "redacted_thinking"` - `data: string` The `data` value of this redacted thinking block, exactly as returned by the API in a previous response. Opaque and encrypted; pass it back unchanged. ### Beta Refusal Stop Details - `beta_refusal_stop_details: object` Structured information about a refusal. - `type: "refusal"` - `category: "cyber" or "bio" or "frontier_llm" or 2 more` The policy category that triggered the refusal. `null` when the refusal doesn't map to a named category. - `"cyber"` The request could enable cyber harm, such as malware or exploit development. Benign cybersecurity work can also trigger this category. - `"bio"` The request could enable biological harm, such as dangerous lab methods. Beneficial life sciences work can also trigger this category. - `"frontier_llm"` The request could assist the development of competing AI models, which is restricted under [Anthropic's commercial terms](https://www.anthropic.com/legal/commercial-terms). Benign machine learning work can also trigger this category. - `"reasoning_extraction"` The request asks the model to reproduce its internal reasoning in the response text. To get reasoning in a structured form instead, use [adaptive thinking](https://platform.claude.com/docs/en/build-with-claude/adaptive-thinking?sdk_languages=cli). - `"general_harms"` The request could be related to an area that was determined as harmful. Benign work might sometimes trigger this category. - `explanation: string` Human-readable explanation of the refusal. This text is not guaranteed to be stable. `null` when no explanation is available for the category. - `fallback_credit_token: string` Opaque code that refunds the cache-miss cost when retrying this refused request on the fallback model. Pass it as `fallback_credit_token` on the retry request. Expires 5 minutes after the refusal. The retry is sent either with the same request body (`system`, `messages`, `tools`, and other render-shaping fields), or with the same body plus one appended `assistant` message whose content is the partial text (with any trailing whitespace stripped from the final text block) and paired server-tool blocks from this refusal — which also authorizes that appended turn as an assistant-prefill continuation on models that otherwise disallow prefill. A token minted mid-server-tool-loop whose partial content was continuable may only be redeemed the second way — if a same-body retry is rejected with a 400 saying the token must be redeemed by continuing the partial response, retry the second way instead. Either way: same workspace, same platform; a mismatch is a 400. Resending a token for an already-warm prefix is permitted but yields no additional credit. `null` when the refused model isn't eligible for a fallback credit. - `fallback_has_prefill_claim: boolean` Whether the accompanying `fallback_credit_token` may be redeemed with the appended-assistant retry form. Only set when `fallback_credit_token` is present. `true`: retry by resending the same request body plus one appended `assistant` message whose content is this response's `content` with any trailing whitespace stripped from the final text block and unpaired `tool_use` blocks omitted (the same appended-turn shape described on `fallback_credit_token`), with the token attached. `false`: retry by resending the original request body unchanged, with the token attached — the appended-assistant form is not available for this refusal (no continuable partial content, or the request uses `output_format` or a `tool_choice` that forces tool use). One exception: when the request used `output_format` or a forced `tool_choice` and the refusal arrived after server tools (including MCP connector tools) had already executed, the token may not be redeemable by either retry form; if the exact-body retry is then rejected with a 400 saying the token must be redeemed by continuing the partial response, discard the token and retry without it. Advisory: if an appended-assistant retry is rejected with a 400 despite `true`, fall back to resending the original request body with the token. - `recommended_model: string` The server's suggested retry target for this refusal. Populated when a fallback attempt could not be made (the fallback model's rate limit was exhausted, or it was overloaded); names the fallback model the caller can retry directly. Null otherwise. ### Beta Request Document Block - `beta_request_document_block: object` - `type: "document"` - `source: BetaBase64PDFSource or BetaPlainTextSource or BetaContentBlockSource or 2 more` - `beta_base64_pdf_source: object` - `type: "base64"` - `data: string` format: byte - `media_type: "application/pdf"` - `beta_plain_text_source: object` - `type: "text"` - `data: string` - `media_type: "text/plain"` - `beta_content_block_source: object` - `type: "content"` - `content: string or array of BetaContentBlockSourceContent` - `union_member_0: string` - `beta_content_block_source_content: array of BetaContentBlockSourceContent` - `beta_text_block_param: object` - `type: "text"` - `text: string` minLength: 1 - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `"5m"` - `"1h"` - `citations: optional array of BetaTextCitationParam` - `beta_citation_char_location_param: object` - `type: "char_location"` - `cited_text: string` - `document_index: number` minimum: 0 - `document_title: string` minLength: 1, maxLength: 500 - `end_char_index: number` - `start_char_index: number` minimum: 0 - `beta_citation_page_location_param: object` - `type: "page_location"` - `cited_text: string` - `document_index: number` minimum: 0 - `document_title: string` minLength: 1, maxLength: 500 - `end_page_number: number` - `start_page_number: number` minimum: 1 - `beta_citation_content_block_location_param: object` - `type: "content_block_location"` - `cited_text: string` The full text of the cited block range, concatenated. Always equals the contents of `content[start_block_index:end_block_index]` joined together. The text block is the minimal citable unit; this field is never a substring of a single block. Not counted toward output tokens, and not counted toward input tokens when sent back in subsequent turns. - `document_index: number` minimum: 0 - `document_title: string` minLength: 1, maxLength: 500 - `end_block_index: number` Exclusive 0-based end index of the cited block range in the source's `content` array. Always greater than `start_block_index`; a single-block citation has `end_block_index = start_block_index + 1`. - `start_block_index: number` 0-based index of the first cited block in the source's `content` array. minimum: 0 - `beta_citation_web_search_result_location_param: object` - `type: "web_search_result_location"` - `cited_text: string` - `encrypted_index: string` - `title: string` minLength: 1, maxLength: 512 - `url: string` minLength: 1 - `beta_citation_search_result_location_param: object` - `type: "search_result_location"` - `cited_text: string` The full text of the cited block range, concatenated. Always equals the contents of `content[start_block_index:end_block_index]` joined together. The text block is the minimal citable unit; this field is never a substring of a single block. Not counted toward output tokens, and not counted toward input tokens when sent back in subsequent turns. - `end_block_index: number` Exclusive 0-based end index of the cited block range in the source's `content` array. Always greater than `start_block_index`; a single-block citation has `end_block_index = start_block_index + 1`. - `search_result_index: number` 0-based index of the cited search result among all `search_result` content blocks in the request, in the order they appear across messages and tool results. Counted separately from `document_index`; server-side web search results are not included in this count. minimum: 0 - `source: string` - `start_block_index: number` 0-based index of the first cited block in the source's `content` array. minimum: 0 - `title: string` - `beta_image_block_param: object` - `type: "image"` - `source: BetaBase64ImageSource or BetaURLImageSource or BetaFileImageSource` - `beta_base64_image_source: object` - `type: "base64"` - `data: string` format: byte - `media_type: "image/jpeg" or "image/png" or "image/gif" or "image/webp"` - `"image/jpeg"` - `"image/png"` - `"image/gif"` - `"image/webp"` - `beta_url_image_source: object` - `type: "url"` - `url: string` - `beta_file_image_source: object` - `type: "file"` - `file_id: string` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `transformations: optional object` Configures the transformations the server applies to this image before the model observes it. Each key names a condition the server transforms images for; its value selects the transformation applied. Omitted keys keep their default behavior, and an empty object is equivalent to omitting the field. - `oversized_image: optional "downsize" or "error"` What the server does when this image exceeds the model's maximum image size. `"downsize"` (the default) scales the image down to fit, which changes the dimensions the model observes without telling you. `"error"` instead rejects the request with a 400 error naming the image's dimensions and the largest dimensions that fit, so you can scale the image deliberately — your image is never silently scaled down. - `"downsize"` - `"error"` - `beta_url_pdf_source: object` - `type: "url"` - `url: string` - `beta_file_document_source: object` - `type: "file"` - `file_id: string` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `citations: optional object` - `enabled: optional boolean` - `context: optional string` minLength: 1 - `title: optional string` minLength: 1, maxLength: 500 ### Beta Request MCP Server Tool Configuration - `beta_request_mcp_server_tool_configuration: object` - `allowed_tools: optional array of string` - `enabled: optional boolean` ### Beta Request MCP Server URL Definition - `beta_request_mcp_server_url_definition: object` - `type: "url"` - `name: string` - `url: string` - `authorization_token: optional string` - `tool_configuration: optional object` - `allowed_tools: optional array of string` - `enabled: optional boolean` ### Beta Request MCP Tool Result Block Param - `beta_request_mcp_tool_result_block_param: object` - `type: "mcp_tool_result"` - `tool_use_id: string` pattern: ^[a-zA-Z0-9_-]+$ - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `"5m"` - `"1h"` - `content: optional string or array of BetaTextBlockParam` - `union_member_0: string` - `beta_mcp_tool_result_block_param_content: array of BetaTextBlockParam` - `type: "text"` - `text: string` minLength: 1 - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `citations: optional array of BetaTextCitationParam` - `beta_citation_char_location_param: object` - `type: "char_location"` - `cited_text: string` - `document_index: number` minimum: 0 - `document_title: string` minLength: 1, maxLength: 500 - `end_char_index: number` - `start_char_index: number` minimum: 0 - `beta_citation_page_location_param: object` - `type: "page_location"` - `cited_text: string` - `document_index: number` minimum: 0 - `document_title: string` minLength: 1, maxLength: 500 - `end_page_number: number` - `start_page_number: number` minimum: 1 - `beta_citation_content_block_location_param: object` - `type: "content_block_location"` - `cited_text: string` The full text of the cited block range, concatenated. Always equals the contents of `content[start_block_index:end_block_index]` joined together. The text block is the minimal citable unit; this field is never a substring of a single block. Not counted toward output tokens, and not counted toward input tokens when sent back in subsequent turns. - `document_index: number` minimum: 0 - `document_title: string` minLength: 1, maxLength: 500 - `end_block_index: number` Exclusive 0-based end index of the cited block range in the source's `content` array. Always greater than `start_block_index`; a single-block citation has `end_block_index = start_block_index + 1`. - `start_block_index: number` 0-based index of the first cited block in the source's `content` array. minimum: 0 - `beta_citation_web_search_result_location_param: object` - `type: "web_search_result_location"` - `cited_text: string` - `encrypted_index: string` - `title: string` minLength: 1, maxLength: 512 - `url: string` minLength: 1 - `beta_citation_search_result_location_param: object` - `type: "search_result_location"` - `cited_text: string` The full text of the cited block range, concatenated. Always equals the contents of `content[start_block_index:end_block_index]` joined together. The text block is the minimal citable unit; this field is never a substring of a single block. Not counted toward output tokens, and not counted toward input tokens when sent back in subsequent turns. - `end_block_index: number` Exclusive 0-based end index of the cited block range in the source's `content` array. Always greater than `start_block_index`; a single-block citation has `end_block_index = start_block_index + 1`. - `search_result_index: number` 0-based index of the cited search result among all `search_result` content blocks in the request, in the order they appear across messages and tool results. Counted separately from `document_index`; server-side web search results are not included in this count. minimum: 0 - `source: string` - `start_block_index: number` 0-based index of the first cited block in the source's `content` array. minimum: 0 - `title: string` - `is_error: optional boolean` ### Beta Request Tool Addition Block - `beta_request_tool_addition_block: object` Mid-conversation directive to make a tool available. `tool` is a reference to a tool (or MCP toolset) declared in the request's `tools`. Under the `inline-tools-2026-09-15` beta it may instead be a reference to a tool defined earlier in `messages`, or a `tool_definition` object that carries an inline tool definition in `definition` (the same object a `tools` entry holds). An `mcp_toolset` definition also requires the `mcp-client-2026-09-15` beta. The tool is offered to the model from this point in the conversation onward. - `type: "tool_addition"` - `tool: BetaToolChangeToolReference or BetaToolChangeMCPToolReference or BetaToolChangeMCPToolsetReference or BetaToolChangeToolDefinitionParam` - `beta_tool_change_tool_reference: object` Reference to a single tool, by the name the model uses to call it: a tool declared in `tools` or defined by an earlier `tool_addition` block. Does not accept the composed `{server}_{name}` form the server assigns to MCP-resolved tools; use `mcp_tool_reference` or `mcp_toolset_reference` for those. - `type: "tool_reference"` - `name: string` pattern: ^[a-zA-Z0-9_-]{1,128}$ - `beta_tool_change_mcp_tool_reference: object` Reference to a single MCP tool by its server and remote name; the same `server_name`/`name` pair `mcp_tool_use` carries. - `type: "mcp_tool_reference"` - `name: string` - `server_name: string` - `beta_tool_change_mcp_toolset_reference: object` Reference to every tool in the named MCP server's toolset. - `type: "mcp_toolset_reference"` - `server_name: string` - `beta_tool_change_tool_definition_param: object` A tool defined by value: `definition` is a `tools` entry (any kind `tools` accepts, an MCP toolset included). An `mcp_toolset` given here also requires the `mcp-client-2026-09-15` beta. - `type: "tool_definition"` - `definition: BetaTool or BetaToolBash20241022 or BetaToolBash20250124 or 25 more` - `beta_tool: object` - `type: optional "custom"` - `input_schema: object` [JSON schema](https://json-schema.org/draft/2020-12) for this tool's input. This defines the shape of the `input` that your tool accepts and that the model will produce. - `type: "object"` - `properties: optional map[unknown]` - `required: optional array of string` - `name: string` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. minLength: 1, maxLength: 128, pattern: ^[a-zA-Z0-9_-]{1,128}$ - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `"5m"` - `"1h"` - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `description: optional string` Description of what this tool does. Tool descriptions should be as detailed as possible. The more information that the model has about what the tool is and how to use it, the better it will perform. You can use natural language descriptions to reinforce important aspects of the tool input JSON schema. - `eager_input_streaming: optional boolean` Enable eager input streaming for this tool. When true, tool input parameters will be streamed incrementally as they are generated, and types will be inferred on-the-fly rather than buffering the full JSON output. When false, streaming is disabled for this tool even if the fine-grained-tool-streaming beta is active. When null (default), uses the default behavior based on beta headers. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_bash_20241022: object` - `type: "bash_20241022"` - `name: "bash"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_bash_20250124: object` - `type: "bash_20250124"` - `name: "bash"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_code_execution_tool_20250522: object` - `type: "code_execution_20250522"` - `name: "code_execution"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_code_execution_tool_20250825: object` - `type: "code_execution_20250825"` - `name: "code_execution"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_code_execution_tool_20260120: object` Code execution tool with REPL state persistence (daemon mode + gVisor checkpoint). - `type: "code_execution_20260120"` - `name: "code_execution"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_code_execution_tool_20260521: object` Code execution tool with REPL state persistence. - `type: "code_execution_20260521"` - `name: "code_execution"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_browser_toolset_20260801: object` The browser toolset: a single `tools[]` entry (carrying no `name`) that declares the browser tool family. The model is served the family's tool with any members disabled via `configs` removed from its schema. - `type: "browser_toolset_20260801"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `configs: optional object` Sparse per-member overrides, keyed by member name. Absent, null, and {} are equivalent; a member's defaults apply wherever its key is absent. - `type: optional object` `type`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `close_tab: optional object` `close_tab`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `double_click: optional object` `double_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `file_upload: optional object` `file_upload`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `find: optional object` `find`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `form_input: optional object` `form_input`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `get_page_text: optional object` `get_page_text`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `hold_key: optional object` `hold_key`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `hover: optional object` `hover`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `javascript_exec: optional object` `javascript_exec`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `key: optional object` `key`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_click: optional object` `left_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_click_drag: optional object` `left_click_drag`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_mouse_down: optional object` `left_mouse_down`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_mouse_up: optional object` `left_mouse_up`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `list_tabs: optional object` `list_tabs`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `middle_click: optional object` `middle_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `mouse_move: optional object` `mouse_move`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `navigate: optional object` `navigate`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `new_tab: optional object` `new_tab`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `read_console: optional object` `read_console`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `read_network: optional object` `read_network`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `read_page: optional object` `read_page`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `right_click: optional object` `right_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `screenshot: optional object` `screenshot`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `scroll: optional object` `scroll`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `scroll_to: optional object` `scroll_to`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `switch_tab: optional object` `switch_tab`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `triple_click: optional object` `triple_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `wait: optional object` `wait`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `zoom: optional object` `zoom`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `beta_tool_computer_use_20241022: object` - `type: "computer_20241022"` - `display_height_px: number` The height of the display in pixels. minimum: 1 - `display_width_px: number` The width of the display in pixels. minimum: 1 - `name: "computer"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `display_number: optional number` The X11 display number (e.g. 0, 1) for the display. minimum: 0 - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_memory_tool_20250818: object` - `type: "memory_20250818"` - `name: "memory"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_computer_use_20250124: object` - `type: "computer_20250124"` - `display_height_px: number` The height of the display in pixels. minimum: 1 - `display_width_px: number` The width of the display in pixels. minimum: 1 - `name: "computer"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `display_number: optional number` The X11 display number (e.g. 0, 1) for the display. minimum: 0 - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_text_editor_20241022: object` - `type: "text_editor_20241022"` - `name: "str_replace_editor"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_computer_use_20251124: object` - `type: "computer_20251124"` - `display_height_px: number` The height of the display in pixels. minimum: 1 - `display_width_px: number` The width of the display in pixels. minimum: 1 - `name: "computer"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `display_number: optional number` The X11 display number (e.g. 0, 1) for the display. minimum: 0 - `enable_zoom: optional boolean` Whether to enable an action to take a zoomed-in screenshot of the screen. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_computer_toolset_20260801: object` The computer toolset: a single `tools[]` entry (carrying no `name`) that declares the computer tool family. The model is served the family's tool with any members disabled via `configs` removed from its schema. Every member is enabled by default, zoom included. The single-tool options `display_number` and `enable_zoom` are not fields of a toolset entry — it carries only `type`, `configs`, and `cache_control`; zoom is controlled via `configs.zoom.enabled`. - `type: "computer_toolset_20260801"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `configs: optional object` Sparse per-member overrides, keyed by member name. Absent, null, and {} are equivalent; a member's defaults apply wherever its key is absent. - `type: optional object` `type`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `cursor_position: optional object` `cursor_position`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `double_click: optional object` `double_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `hold_key: optional object` `hold_key`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `key: optional object` `key`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_click: optional object` `left_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_click_drag: optional object` `left_click_drag`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_mouse_down: optional object` `left_mouse_down`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_mouse_up: optional object` `left_mouse_up`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `middle_click: optional object` `middle_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `mouse_move: optional object` `mouse_move`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `right_click: optional object` `right_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `screenshot: optional object` `screenshot`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `scroll: optional object` `scroll`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `triple_click: optional object` `triple_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `wait: optional object` `wait`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `zoom: optional object` `zoom`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `beta_tool_text_editor_20250124: object` - `type: "text_editor_20250124"` - `name: "str_replace_editor"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_text_editor_20250429: object` - `type: "text_editor_20250429"` - `name: "str_replace_based_edit_tool"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_text_editor_20250728: object` - `type: "text_editor_20250728"` - `name: "str_replace_based_edit_tool"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: optional array of map[unknown]` - `max_characters: optional number` Maximum number of characters to display when viewing a file. If not specified, defaults to displaying the full file. minimum: 1 - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_web_search_tool_20250305: object` - `type: "web_search_20250305"` - `name: "web_search"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: optional array of string` If provided, only these domains will be included in results. Cannot be used alongside `blocked_domains`. - `blocked_domains: optional array of string` If provided, these domains will never appear in results. Cannot be used alongside `allowed_domains`. - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `user_location: optional object` Parameters for the user's location. Used to provide more relevant search results. - `type: "approximate"` - `city: optional string` The city of the user. minLength: 1, maxLength: 255 - `country: optional string` The two letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1_alpha-2) of the user. minLength: 2, maxLength: 2 - `region: optional string` The region of the user. minLength: 1, maxLength: 255 - `timezone: optional string` The [IANA timezone](https://nodatime.org/TimeZones) of the user. minLength: 1, maxLength: 255 - `beta_web_fetch_tool_20250910: object` - `type: "web_fetch_20250910"` - `name: "web_fetch"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: optional array of string` List of domains to allow fetching from - `blocked_domains: optional array of string` List of domains to block fetching from - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `citations: optional object` Citations configuration for fetched documents. Citations are disabled by default. - `enabled: optional boolean` - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_content_tokens: optional number` Maximum number of tokens used by including web page text content in the context. The limit is approximate and does not apply to binary content such as PDFs. minimum: 1 - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `url_sources: optional object` Which sources contribute to the set of URLs the tool may fetch. Omitted means every source. - `client_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which client tools' results contribute fetchable URLs: "all", "none", or an only or except list of client tool names from tools[]. - `beta_web_fetch_url_source_all: object` The `url_sources` variant under which a source contributes in full: every result of the tool filter's source, or all user input. - `type: "all"` - `beta_web_fetch_url_source_none: object` The `url_sources` variant under which a source contributes nothing: no result of the tool filter's source, or no user input. - `type: "none"` - `beta_web_fetch_url_source_only: object` The tool filter variant under which only the named tools' results contribute. - `type: "only"` - `tools: array of BetaWebFetchURLSourceToolReference` - `type: "tool_reference"` - `name: string` - `beta_web_fetch_url_source_except: object` The tool filter variant under which every result but the named tools' contributes. - `type: "except"` - `tools: array of BetaWebFetchURLSourceToolReference` - `type: "tool_reference"` - `name: string` - `server_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which server tools' results contribute fetchable URLs: "all", "none", or an only or except list of server tool names from tools[]; only web_search and web_fetch results ever contribute. - `beta_web_fetch_url_source_all: object` The `url_sources` variant under which a source contributes in full: every result of the tool filter's source, or all user input. - `beta_web_fetch_url_source_none: object` The `url_sources` variant under which a source contributes nothing: no result of the tool filter's source, or no user input. - `beta_web_fetch_url_source_only: object` The tool filter variant under which only the named tools' results contribute. - `beta_web_fetch_url_source_except: object` The tool filter variant under which every result but the named tools' contributes. - `user_input: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone` Whether URLs in user messages are fetchable: "all" or "none". - `beta_web_fetch_url_source_all: object` The `url_sources` variant under which a source contributes in full: every result of the tool filter's source, or all user input. - `beta_web_fetch_url_source_none: object` The `url_sources` variant under which a source contributes nothing: no result of the tool filter's source, or no user input. - `beta_web_search_tool_20260209: object` - `type: "web_search_20260209"` - `name: "web_search"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: optional array of string` If provided, only these domains will be included in results. Cannot be used alongside `blocked_domains`. - `blocked_domains: optional array of string` If provided, these domains will never appear in results. Cannot be used alongside `allowed_domains`. - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `user_location: optional object` Parameters for the user's location. Used to provide more relevant search results. - `type: "approximate"` - `city: optional string` The city of the user. minLength: 1, maxLength: 255 - `country: optional string` The two letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1_alpha-2) of the user. minLength: 2, maxLength: 2 - `region: optional string` The region of the user. minLength: 1, maxLength: 255 - `timezone: optional string` The [IANA timezone](https://nodatime.org/TimeZones) of the user. minLength: 1, maxLength: 255 - `beta_web_fetch_tool_20260209: object` - `type: "web_fetch_20260209"` - `name: "web_fetch"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: optional array of string` List of domains to allow fetching from - `blocked_domains: optional array of string` List of domains to block fetching from - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `citations: optional object` Citations configuration for fetched documents. Citations are disabled by default. - `enabled: optional boolean` - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_content_tokens: optional number` Maximum number of tokens used by including web page text content in the context. The limit is approximate and does not apply to binary content such as PDFs. minimum: 1 - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `url_sources: optional object` Which sources contribute to the set of URLs the tool may fetch. Omitted means every source. - `client_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which client tools' results contribute fetchable URLs: "all", "none", or an only or except list of client tool names from tools[]. - `server_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which server tools' results contribute fetchable URLs: "all", "none", or an only or except list of server tool names from tools[]; only web_search and web_fetch results ever contribute. - `user_input: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone` Whether URLs in user messages are fetchable: "all" or "none". - `beta_web_fetch_tool_20260309: object` Web fetch tool with use_cache parameter for bypassing cached content. - `type: "web_fetch_20260309"` - `name: "web_fetch"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: optional array of string` List of domains to allow fetching from - `blocked_domains: optional array of string` List of domains to block fetching from - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `citations: optional object` Citations configuration for fetched documents. Citations are disabled by default. - `enabled: optional boolean` - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_content_tokens: optional number` Maximum number of tokens used by including web page text content in the context. The limit is approximate and does not apply to binary content such as PDFs. minimum: 1 - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `url_sources: optional object` Which sources contribute to the set of URLs the tool may fetch. Omitted means every source. - `client_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which client tools' results contribute fetchable URLs: "all", "none", or an only or except list of client tool names from tools[]. - `server_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which server tools' results contribute fetchable URLs: "all", "none", or an only or except list of server tool names from tools[]; only web_search and web_fetch results ever contribute. - `user_input: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone` Whether URLs in user messages are fetchable: "all" or "none". - `use_cache: optional boolean` Whether to use cached content. Set to false to bypass the cache and fetch fresh content. Only set to false when the user explicitly requests fresh content or when fetching rapidly-changing sources. - `beta_web_search_tool_20260318: object` - `type: "web_search_20260318"` - `name: "web_search"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: optional array of string` If provided, only these domains will be included in results. Cannot be used alongside `blocked_domains`. - `blocked_domains: optional array of string` If provided, these domains will never appear in results. Cannot be used alongside `allowed_domains`. - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `response_inclusion: optional "full" or "excluded"` How this tool's result blocks appear in the API response when the result was consumed by a completed code_execution call in the same turn. 'full' returns the complete content (default). 'excluded' drops the nested server_tool_use and result block pair entirely. Results from direct calls, or from code_execution calls that paused before completing, are always returned in full so they can be sent back on the next turn. - `"full"` - `"excluded"` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `user_location: optional object` Parameters for the user's location. Used to provide more relevant search results. - `type: "approximate"` - `city: optional string` The city of the user. minLength: 1, maxLength: 255 - `country: optional string` The two letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1_alpha-2) of the user. minLength: 2, maxLength: 2 - `region: optional string` The region of the user. minLength: 1, maxLength: 255 - `timezone: optional string` The [IANA timezone](https://nodatime.org/TimeZones) of the user. minLength: 1, maxLength: 255 - `beta_web_fetch_tool_20260318: object` - `type: "web_fetch_20260318"` - `name: "web_fetch"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: optional array of string` List of domains to allow fetching from - `blocked_domains: optional array of string` List of domains to block fetching from - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `citations: optional object` Citations configuration for fetched documents. Citations are disabled by default. - `enabled: optional boolean` - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_content_tokens: optional number` Maximum number of tokens used by including web page text content in the context. The limit is approximate and does not apply to binary content such as PDFs. minimum: 1 - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `response_inclusion: optional "full" or "excluded"` How this tool's result blocks appear in the API response when the result was consumed by a completed code_execution call in the same turn. 'full' returns the complete content (default). 'excluded' drops the nested server_tool_use and result block pair entirely. Results from direct calls, or from code_execution calls that paused before completing, are always returned in full so they can be sent back on the next turn. - `"full"` - `"excluded"` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `url_sources: optional object` Which sources contribute to the set of URLs the tool may fetch. Omitted means every source. - `client_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which client tools' results contribute fetchable URLs: "all", "none", or an only or except list of client tool names from tools[]. - `server_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which server tools' results contribute fetchable URLs: "all", "none", or an only or except list of server tool names from tools[]; only web_search and web_fetch results ever contribute. - `user_input: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone` Whether URLs in user messages are fetchable: "all" or "none". - `use_cache: optional boolean` Whether to use cached content. Set to false to bypass the cache and fetch fresh content. Only set to false when the user explicitly requests fresh content or when fetching rapidly-changing sources. - `beta_advisor_tool_20260301: object` - `type: "advisor_20260301"` - `model: "claude-haiku-5-5" or "claude-sonnet-5-5" or "claude-fable-5-1" or 17 more or string` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-haiku-5-5"` Fastest model for high-volume, real-time tasks - `"claude-sonnet-5-5"` Efficient model for coding and agents - `"claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows - `"claude-opus-5-5"` Powerful intelligence for coding, knowledge work, and long-running agents - `"claude-mythos-5-1"` Our most capable model for cybersecurity and biology research, available through trusted access programs - `"claude-sonnet-5"` Efficient model for coding and agents - `"claude-fable-5"` Next generation of intelligence for the hardest knowledge work and coding problems - `"claude-mythos-5"` Most capable model for cybersecurity and biology research - `"claude-opus-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-8"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-7"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-6"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-6"` Best combination of speed and intelligence - `"claude-haiku-4-5"` - `"claude-haiku-4-5-20251001"` - `"claude-opus-4-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-5-20251101"` Powerful intelligence for long-running agents and coding - `"claude-mythos-preview"` **Deprecated**: Will reach end-of-life on June 30, 2026. Please migrate to claude-mythos-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. New class of intelligence, strongest in coding and cybersecurity - `"claude-sonnet-4-5"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `"claude-sonnet-4-5-20250929"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `name: "advisor"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `caching: optional object` Caching for the advisor's own prompt. When set, each advisor call writes a cache entry at the given TTL so subsequent calls in the same conversation read the stable prefix. When omitted, the advisor prompt is not cached. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_tokens: optional number` Bounds the advisor's total output (thinking + text) per call. When the advisor hits this cap, the returned advisor_result or advisor_redacted_result block carries stop_reason='max_tokens', and a truncation note is appended to the advice text the worker model sees (inside the encrypted blob in redacted mode). When set, the server also emits a remaining-tokens budget block in the advisor's prompt so the advisor self-shapes toward the cap. When omitted, the advisor model's default output cap applies and no budget block is emitted. minimum: 1024 - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_search_tool_bm25_20251119: object` - `type: "tool_search_tool_bm25_20251119" or "tool_search_tool_bm25"` - `"tool_search_tool_bm25_20251119"` - `"tool_search_tool_bm25"` - `name: "tool_search_tool_bm25"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_search_tool_regex_20251119: object` - `type: "tool_search_tool_regex_20251119" or "tool_search_tool_regex"` - `"tool_search_tool_regex_20251119"` - `"tool_search_tool_regex"` - `name: "tool_search_tool_regex"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_mcp_toolset: object` Configuration for a group of tools from an MCP server. Allows configuring enabled status and defer_loading for all tools from an MCP server, with optional per-tool overrides. - `type: "mcp_toolset"` - `mcp_server_name: string` Name of the MCP server to configure tools for minLength: 1, maxLength: 255 - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `configs: optional map[BetaMCPToolConfig]` Configuration overrides for specific tools, keyed by tool name - `defer_loading: optional boolean` - `enabled: optional boolean` - `default_config: optional object` Default configuration applied to all tools from this server - `defer_loading: optional boolean` - `enabled: optional boolean` - `tools: optional array of BetaMCPToolParam` The server's tool listing, pinned: when present, the server is not asked for its tools before sampling and exactly these entries, with `default_config` and `configs` applied, are the toolset's tools. Copy it from the `mcp_tool_listing` block of an earlier response. - `input_schema: map[unknown]` The tool's input schema as the MCP server lists it, verbatim. - `name: string` The tool's name as the MCP server lists it (not prefixed with the server name). minLength: 1 - `description: optional string` The tool's description as the MCP server lists it. - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. ### Beta Request Tool Removal Block - `beta_request_tool_removal_block: object` Mid-conversation directive to withdraw a tool. `tool` references a tool (or MCP toolset) by name: one declared in the request's `tools` or defined earlier in `messages`. It is no longer offered to the model from this point in the conversation onward. - `type: "tool_removal"` - `tool: BetaToolChangeToolReference or BetaToolChangeMCPToolReference or BetaToolChangeMCPToolsetReference` - `beta_tool_change_tool_reference: object` Reference to a single tool, by the name the model uses to call it: a tool declared in `tools` or defined by an earlier `tool_addition` block. Does not accept the composed `{server}_{name}` form the server assigns to MCP-resolved tools; use `mcp_tool_reference` or `mcp_toolset_reference` for those. - `type: "tool_reference"` - `name: string` pattern: ^[a-zA-Z0-9_-]{1,128}$ - `beta_tool_change_mcp_tool_reference: object` Reference to a single MCP tool by its server and remote name; the same `server_name`/`name` pair `mcp_tool_use` carries. - `type: "mcp_tool_reference"` - `name: string` - `server_name: string` - `beta_tool_change_mcp_toolset_reference: object` Reference to every tool in the named MCP server's toolset. - `type: "mcp_toolset_reference"` - `server_name: string` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `"5m"` - `"1h"` ### Beta Response Tool - `beta_response_tool: object` A custom tool definition, as sent. - `type: optional "custom"` - `input_schema: object` [JSON schema](https://json-schema.org/draft/2020-12) for this tool's input. This defines the shape of the `input` that your tool accepts and that the model will produce. - `type: "object"` - `properties: optional map[unknown]` - `required: optional array of string` - `name: string` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. minLength: 1, maxLength: 128, pattern: ^[a-zA-Z0-9_-]{1,128}$ - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `description: optional string` Description of what this tool does. Tool descriptions should be as detailed as possible. The more information that the model has about what the tool is and how to use it, the better it will perform. You can use natural language descriptions to reinforce important aspects of the tool input JSON schema. - `eager_input_streaming: optional boolean` Enable eager input streaming for this tool. When true, tool input parameters will be streamed incrementally as they are generated, and types will be inferred on-the-fly rather than buffering the full JSON output. When false, streaming is disabled for this tool even if the fine-grained-tool-streaming beta is active. When null (default), uses the default behavior based on beta headers. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs ### Beta Response Tool Addition Block - `beta_response_tool_addition_block: object` An entry of a `compaction` block's `tool_changes`: a tool the compacted range made available, as a reference to a `tools` entry or MCP toolset, or as the tool definition in effect at the end of the range, by value. Send it back unchanged. - `type: "tool_addition"` - `tool: BetaResponseToolChangeToolReference or BetaResponseToolChangeMCPToolReference or BetaResponseToolChangeMCPToolsetReference or BetaToolChangeToolDefinition` The tool made available: a reference to a `tools` entry or MCP toolset, or a `tool_definition` carrying the definition by value. - `beta_response_tool_change_tool_reference: object` Reference to a single tool, by the name the model uses to call it, as a `compaction` block's `tool_changes` entry reports it: a tool declared in `tools` or defined by an earlier `tool_addition` block. Send it back unchanged with the block. - `type: "tool_reference"` - `name: string` - `beta_response_tool_change_mcp_tool_reference: object` Reference to a single MCP tool, by its server and its name on that server, as a `compaction` block's `tool_changes` entry reports it. Send it back unchanged with the block. - `type: "mcp_tool_reference"` - `name: string` - `server_name: string` - `beta_response_tool_change_mcp_toolset_reference: object` Reference to every tool in the named MCP server's toolset, as a `compaction` block's `tool_changes` entry reports it. Send it back unchanged with the block. - `type: "mcp_toolset_reference"` - `server_name: string` - `beta_tool_change_tool_definition: object` A tool defined by value, as a `compaction` block's `tool_changes` entry reports it: `definition` is the tool's definition as it was sent, in the form of a `tools` entry, without `cache_control`. Send it back unchanged with the block. - `type: "tool_definition"` - `definition: BetaResponseTool or BetaToolBash20241022 or BetaToolBash20250124 or 25 more` - `beta_response_tool: object` A custom tool definition, as sent. - `type: optional "custom"` - `input_schema: object` [JSON schema](https://json-schema.org/draft/2020-12) for this tool's input. This defines the shape of the `input` that your tool accepts and that the model will produce. - `type: "object"` - `properties: optional map[unknown]` - `required: optional array of string` - `name: string` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. minLength: 1, maxLength: 128, pattern: ^[a-zA-Z0-9_-]{1,128}$ - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `description: optional string` Description of what this tool does. Tool descriptions should be as detailed as possible. The more information that the model has about what the tool is and how to use it, the better it will perform. You can use natural language descriptions to reinforce important aspects of the tool input JSON schema. - `eager_input_streaming: optional boolean` Enable eager input streaming for this tool. When true, tool input parameters will be streamed incrementally as they are generated, and types will be inferred on-the-fly rather than buffering the full JSON output. When false, streaming is disabled for this tool even if the fine-grained-tool-streaming beta is active. When null (default), uses the default behavior based on beta headers. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_bash_20241022: object` - `type: "bash_20241022"` - `name: "bash"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `"5m"` - `"1h"` - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_bash_20250124: object` - `type: "bash_20250124"` - `name: "bash"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_code_execution_tool_20250522: object` - `type: "code_execution_20250522"` - `name: "code_execution"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_code_execution_tool_20250825: object` - `type: "code_execution_20250825"` - `name: "code_execution"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_code_execution_tool_20260120: object` Code execution tool with REPL state persistence (daemon mode + gVisor checkpoint). - `type: "code_execution_20260120"` - `name: "code_execution"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_code_execution_tool_20260521: object` Code execution tool with REPL state persistence. - `type: "code_execution_20260521"` - `name: "code_execution"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_browser_toolset_20260801: object` The browser toolset: a single `tools[]` entry (carrying no `name`) that declares the browser tool family. The model is served the family's tool with any members disabled via `configs` removed from its schema. - `type: "browser_toolset_20260801"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `configs: optional object` Sparse per-member overrides, keyed by member name. Absent, null, and {} are equivalent; a member's defaults apply wherever its key is absent. - `type: optional object` `type`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `close_tab: optional object` `close_tab`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `double_click: optional object` `double_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `file_upload: optional object` `file_upload`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `find: optional object` `find`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `form_input: optional object` `form_input`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `get_page_text: optional object` `get_page_text`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `hold_key: optional object` `hold_key`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `hover: optional object` `hover`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `javascript_exec: optional object` `javascript_exec`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `key: optional object` `key`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_click: optional object` `left_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_click_drag: optional object` `left_click_drag`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_mouse_down: optional object` `left_mouse_down`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_mouse_up: optional object` `left_mouse_up`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `list_tabs: optional object` `list_tabs`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `middle_click: optional object` `middle_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `mouse_move: optional object` `mouse_move`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `navigate: optional object` `navigate`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `new_tab: optional object` `new_tab`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `read_console: optional object` `read_console`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `read_network: optional object` `read_network`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `read_page: optional object` `read_page`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `right_click: optional object` `right_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `screenshot: optional object` `screenshot`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `scroll: optional object` `scroll`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `scroll_to: optional object` `scroll_to`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `switch_tab: optional object` `switch_tab`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `triple_click: optional object` `triple_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `wait: optional object` `wait`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `zoom: optional object` `zoom`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `beta_tool_computer_use_20241022: object` - `type: "computer_20241022"` - `display_height_px: number` The height of the display in pixels. minimum: 1 - `display_width_px: number` The width of the display in pixels. minimum: 1 - `name: "computer"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `display_number: optional number` The X11 display number (e.g. 0, 1) for the display. minimum: 0 - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_memory_tool_20250818: object` - `type: "memory_20250818"` - `name: "memory"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_computer_use_20250124: object` - `type: "computer_20250124"` - `display_height_px: number` The height of the display in pixels. minimum: 1 - `display_width_px: number` The width of the display in pixels. minimum: 1 - `name: "computer"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `display_number: optional number` The X11 display number (e.g. 0, 1) for the display. minimum: 0 - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_text_editor_20241022: object` - `type: "text_editor_20241022"` - `name: "str_replace_editor"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_computer_use_20251124: object` - `type: "computer_20251124"` - `display_height_px: number` The height of the display in pixels. minimum: 1 - `display_width_px: number` The width of the display in pixels. minimum: 1 - `name: "computer"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `display_number: optional number` The X11 display number (e.g. 0, 1) for the display. minimum: 0 - `enable_zoom: optional boolean` Whether to enable an action to take a zoomed-in screenshot of the screen. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_computer_toolset_20260801: object` The computer toolset: a single `tools[]` entry (carrying no `name`) that declares the computer tool family. The model is served the family's tool with any members disabled via `configs` removed from its schema. Every member is enabled by default, zoom included. The single-tool options `display_number` and `enable_zoom` are not fields of a toolset entry — it carries only `type`, `configs`, and `cache_control`; zoom is controlled via `configs.zoom.enabled`. - `type: "computer_toolset_20260801"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `configs: optional object` Sparse per-member overrides, keyed by member name. Absent, null, and {} are equivalent; a member's defaults apply wherever its key is absent. - `type: optional object` `type`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `cursor_position: optional object` `cursor_position`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `double_click: optional object` `double_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `hold_key: optional object` `hold_key`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `key: optional object` `key`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_click: optional object` `left_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_click_drag: optional object` `left_click_drag`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_mouse_down: optional object` `left_mouse_down`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_mouse_up: optional object` `left_mouse_up`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `middle_click: optional object` `middle_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `mouse_move: optional object` `mouse_move`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `right_click: optional object` `right_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `screenshot: optional object` `screenshot`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `scroll: optional object` `scroll`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `triple_click: optional object` `triple_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `wait: optional object` `wait`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `zoom: optional object` `zoom`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `beta_tool_text_editor_20250124: object` - `type: "text_editor_20250124"` - `name: "str_replace_editor"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_text_editor_20250429: object` - `type: "text_editor_20250429"` - `name: "str_replace_based_edit_tool"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_text_editor_20250728: object` - `type: "text_editor_20250728"` - `name: "str_replace_based_edit_tool"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: optional array of map[unknown]` - `max_characters: optional number` Maximum number of characters to display when viewing a file. If not specified, defaults to displaying the full file. minimum: 1 - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_web_search_tool_20250305: object` - `type: "web_search_20250305"` - `name: "web_search"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: optional array of string` If provided, only these domains will be included in results. Cannot be used alongside `blocked_domains`. - `blocked_domains: optional array of string` If provided, these domains will never appear in results. Cannot be used alongside `allowed_domains`. - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `user_location: optional object` Parameters for the user's location. Used to provide more relevant search results. - `type: "approximate"` - `city: optional string` The city of the user. minLength: 1, maxLength: 255 - `country: optional string` The two letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1_alpha-2) of the user. minLength: 2, maxLength: 2 - `region: optional string` The region of the user. minLength: 1, maxLength: 255 - `timezone: optional string` The [IANA timezone](https://nodatime.org/TimeZones) of the user. minLength: 1, maxLength: 255 - `beta_web_fetch_tool_20250910: object` - `type: "web_fetch_20250910"` - `name: "web_fetch"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: optional array of string` List of domains to allow fetching from - `blocked_domains: optional array of string` List of domains to block fetching from - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `citations: optional object` Citations configuration for fetched documents. Citations are disabled by default. - `enabled: optional boolean` - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_content_tokens: optional number` Maximum number of tokens used by including web page text content in the context. The limit is approximate and does not apply to binary content such as PDFs. minimum: 1 - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `url_sources: optional object` Which sources contribute to the set of URLs the tool may fetch. Omitted means every source. - `client_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which client tools' results contribute fetchable URLs: "all", "none", or an only or except list of client tool names from tools[]. - `beta_web_fetch_url_source_all: object` The `url_sources` variant under which a source contributes in full: every result of the tool filter's source, or all user input. - `type: "all"` - `beta_web_fetch_url_source_none: object` The `url_sources` variant under which a source contributes nothing: no result of the tool filter's source, or no user input. - `type: "none"` - `beta_web_fetch_url_source_only: object` The tool filter variant under which only the named tools' results contribute. - `type: "only"` - `tools: array of BetaWebFetchURLSourceToolReference` - `type: "tool_reference"` - `name: string` - `beta_web_fetch_url_source_except: object` The tool filter variant under which every result but the named tools' contributes. - `type: "except"` - `tools: array of BetaWebFetchURLSourceToolReference` - `type: "tool_reference"` - `name: string` - `server_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which server tools' results contribute fetchable URLs: "all", "none", or an only or except list of server tool names from tools[]; only web_search and web_fetch results ever contribute. - `beta_web_fetch_url_source_all: object` The `url_sources` variant under which a source contributes in full: every result of the tool filter's source, or all user input. - `beta_web_fetch_url_source_none: object` The `url_sources` variant under which a source contributes nothing: no result of the tool filter's source, or no user input. - `beta_web_fetch_url_source_only: object` The tool filter variant under which only the named tools' results contribute. - `beta_web_fetch_url_source_except: object` The tool filter variant under which every result but the named tools' contributes. - `user_input: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone` Whether URLs in user messages are fetchable: "all" or "none". - `beta_web_fetch_url_source_all: object` The `url_sources` variant under which a source contributes in full: every result of the tool filter's source, or all user input. - `beta_web_fetch_url_source_none: object` The `url_sources` variant under which a source contributes nothing: no result of the tool filter's source, or no user input. - `beta_web_search_tool_20260209: object` - `type: "web_search_20260209"` - `name: "web_search"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: optional array of string` If provided, only these domains will be included in results. Cannot be used alongside `blocked_domains`. - `blocked_domains: optional array of string` If provided, these domains will never appear in results. Cannot be used alongside `allowed_domains`. - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `user_location: optional object` Parameters for the user's location. Used to provide more relevant search results. - `type: "approximate"` - `city: optional string` The city of the user. minLength: 1, maxLength: 255 - `country: optional string` The two letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1_alpha-2) of the user. minLength: 2, maxLength: 2 - `region: optional string` The region of the user. minLength: 1, maxLength: 255 - `timezone: optional string` The [IANA timezone](https://nodatime.org/TimeZones) of the user. minLength: 1, maxLength: 255 - `beta_web_fetch_tool_20260209: object` - `type: "web_fetch_20260209"` - `name: "web_fetch"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: optional array of string` List of domains to allow fetching from - `blocked_domains: optional array of string` List of domains to block fetching from - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `citations: optional object` Citations configuration for fetched documents. Citations are disabled by default. - `enabled: optional boolean` - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_content_tokens: optional number` Maximum number of tokens used by including web page text content in the context. The limit is approximate and does not apply to binary content such as PDFs. minimum: 1 - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `url_sources: optional object` Which sources contribute to the set of URLs the tool may fetch. Omitted means every source. - `client_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which client tools' results contribute fetchable URLs: "all", "none", or an only or except list of client tool names from tools[]. - `server_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which server tools' results contribute fetchable URLs: "all", "none", or an only or except list of server tool names from tools[]; only web_search and web_fetch results ever contribute. - `user_input: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone` Whether URLs in user messages are fetchable: "all" or "none". - `beta_web_fetch_tool_20260309: object` Web fetch tool with use_cache parameter for bypassing cached content. - `type: "web_fetch_20260309"` - `name: "web_fetch"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: optional array of string` List of domains to allow fetching from - `blocked_domains: optional array of string` List of domains to block fetching from - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `citations: optional object` Citations configuration for fetched documents. Citations are disabled by default. - `enabled: optional boolean` - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_content_tokens: optional number` Maximum number of tokens used by including web page text content in the context. The limit is approximate and does not apply to binary content such as PDFs. minimum: 1 - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `url_sources: optional object` Which sources contribute to the set of URLs the tool may fetch. Omitted means every source. - `client_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which client tools' results contribute fetchable URLs: "all", "none", or an only or except list of client tool names from tools[]. - `server_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which server tools' results contribute fetchable URLs: "all", "none", or an only or except list of server tool names from tools[]; only web_search and web_fetch results ever contribute. - `user_input: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone` Whether URLs in user messages are fetchable: "all" or "none". - `use_cache: optional boolean` Whether to use cached content. Set to false to bypass the cache and fetch fresh content. Only set to false when the user explicitly requests fresh content or when fetching rapidly-changing sources. - `beta_web_search_tool_20260318: object` - `type: "web_search_20260318"` - `name: "web_search"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: optional array of string` If provided, only these domains will be included in results. Cannot be used alongside `blocked_domains`. - `blocked_domains: optional array of string` If provided, these domains will never appear in results. Cannot be used alongside `allowed_domains`. - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `response_inclusion: optional "full" or "excluded"` How this tool's result blocks appear in the API response when the result was consumed by a completed code_execution call in the same turn. 'full' returns the complete content (default). 'excluded' drops the nested server_tool_use and result block pair entirely. Results from direct calls, or from code_execution calls that paused before completing, are always returned in full so they can be sent back on the next turn. - `"full"` - `"excluded"` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `user_location: optional object` Parameters for the user's location. Used to provide more relevant search results. - `type: "approximate"` - `city: optional string` The city of the user. minLength: 1, maxLength: 255 - `country: optional string` The two letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1_alpha-2) of the user. minLength: 2, maxLength: 2 - `region: optional string` The region of the user. minLength: 1, maxLength: 255 - `timezone: optional string` The [IANA timezone](https://nodatime.org/TimeZones) of the user. minLength: 1, maxLength: 255 - `beta_web_fetch_tool_20260318: object` - `type: "web_fetch_20260318"` - `name: "web_fetch"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: optional array of string` List of domains to allow fetching from - `blocked_domains: optional array of string` List of domains to block fetching from - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `citations: optional object` Citations configuration for fetched documents. Citations are disabled by default. - `enabled: optional boolean` - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_content_tokens: optional number` Maximum number of tokens used by including web page text content in the context. The limit is approximate and does not apply to binary content such as PDFs. minimum: 1 - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `response_inclusion: optional "full" or "excluded"` How this tool's result blocks appear in the API response when the result was consumed by a completed code_execution call in the same turn. 'full' returns the complete content (default). 'excluded' drops the nested server_tool_use and result block pair entirely. Results from direct calls, or from code_execution calls that paused before completing, are always returned in full so they can be sent back on the next turn. - `"full"` - `"excluded"` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `url_sources: optional object` Which sources contribute to the set of URLs the tool may fetch. Omitted means every source. - `client_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which client tools' results contribute fetchable URLs: "all", "none", or an only or except list of client tool names from tools[]. - `server_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which server tools' results contribute fetchable URLs: "all", "none", or an only or except list of server tool names from tools[]; only web_search and web_fetch results ever contribute. - `user_input: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone` Whether URLs in user messages are fetchable: "all" or "none". - `use_cache: optional boolean` Whether to use cached content. Set to false to bypass the cache and fetch fresh content. Only set to false when the user explicitly requests fresh content or when fetching rapidly-changing sources. - `beta_advisor_tool_20260301: object` - `type: "advisor_20260301"` - `model: "claude-haiku-5-5" or "claude-sonnet-5-5" or "claude-fable-5-1" or 17 more or string` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-haiku-5-5"` Fastest model for high-volume, real-time tasks - `"claude-sonnet-5-5"` Efficient model for coding and agents - `"claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows - `"claude-opus-5-5"` Powerful intelligence for coding, knowledge work, and long-running agents - `"claude-mythos-5-1"` Our most capable model for cybersecurity and biology research, available through trusted access programs - `"claude-sonnet-5"` Efficient model for coding and agents - `"claude-fable-5"` Next generation of intelligence for the hardest knowledge work and coding problems - `"claude-mythos-5"` Most capable model for cybersecurity and biology research - `"claude-opus-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-8"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-7"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-6"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-6"` Best combination of speed and intelligence - `"claude-haiku-4-5"` - `"claude-haiku-4-5-20251001"` - `"claude-opus-4-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-5-20251101"` Powerful intelligence for long-running agents and coding - `"claude-mythos-preview"` **Deprecated**: Will reach end-of-life on June 30, 2026. Please migrate to claude-mythos-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. New class of intelligence, strongest in coding and cybersecurity - `"claude-sonnet-4-5"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `"claude-sonnet-4-5-20250929"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `name: "advisor"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `caching: optional object` Caching for the advisor's own prompt. When set, each advisor call writes a cache entry at the given TTL so subsequent calls in the same conversation read the stable prefix. When omitted, the advisor prompt is not cached. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_tokens: optional number` Bounds the advisor's total output (thinking + text) per call. When the advisor hits this cap, the returned advisor_result or advisor_redacted_result block carries stop_reason='max_tokens', and a truncation note is appended to the advice text the worker model sees (inside the encrypted blob in redacted mode). When set, the server also emits a remaining-tokens budget block in the advisor's prompt so the advisor self-shapes toward the cap. When omitted, the advisor model's default output cap applies and no budget block is emitted. minimum: 1024 - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_search_tool_bm25_20251119: object` - `type: "tool_search_tool_bm25_20251119" or "tool_search_tool_bm25"` - `"tool_search_tool_bm25_20251119"` - `"tool_search_tool_bm25"` - `name: "tool_search_tool_bm25"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_search_tool_regex_20251119: object` - `type: "tool_search_tool_regex_20251119" or "tool_search_tool_regex"` - `"tool_search_tool_regex_20251119"` - `"tool_search_tool_regex"` - `name: "tool_search_tool_regex"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_mcp_toolset: object` Configuration for a group of tools from an MCP server. Allows configuring enabled status and defer_loading for all tools from an MCP server, with optional per-tool overrides. - `type: "mcp_toolset"` - `mcp_server_name: string` Name of the MCP server to configure tools for minLength: 1, maxLength: 255 - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `configs: optional map[BetaMCPToolConfig]` Configuration overrides for specific tools, keyed by tool name - `defer_loading: optional boolean` - `enabled: optional boolean` - `default_config: optional object` Default configuration applied to all tools from this server - `defer_loading: optional boolean` - `enabled: optional boolean` - `tools: optional array of BetaMCPToolParam` The server's tool listing, pinned: when present, the server is not asked for its tools before sampling and exactly these entries, with `default_config` and `configs` applied, are the toolset's tools. Copy it from the `mcp_tool_listing` block of an earlier response. - `input_schema: map[unknown]` The tool's input schema as the MCP server lists it, verbatim. - `name: string` The tool's name as the MCP server lists it (not prefixed with the server name). minLength: 1 - `description: optional string` The tool's description as the MCP server lists it. ### Beta Response Tool Change MCP Tool Reference - `beta_response_tool_change_mcp_tool_reference: object` Reference to a single MCP tool, by its server and its name on that server, as a `compaction` block's `tool_changes` entry reports it. Send it back unchanged with the block. - `type: "mcp_tool_reference"` - `name: string` - `server_name: string` ### Beta Response Tool Change MCP Toolset Reference - `beta_response_tool_change_mcp_toolset_reference: object` Reference to every tool in the named MCP server's toolset, as a `compaction` block's `tool_changes` entry reports it. Send it back unchanged with the block. - `type: "mcp_toolset_reference"` - `server_name: string` ### Beta Response Tool Change Tool Reference - `beta_response_tool_change_tool_reference: object` Reference to a single tool, by the name the model uses to call it, as a `compaction` block's `tool_changes` entry reports it: a tool declared in `tools` or defined by an earlier `tool_addition` block. Send it back unchanged with the block. - `type: "tool_reference"` - `name: string` ### Beta Response Tool Input Schema - `beta_response_tool_input_schema: object` [JSON schema](https://json-schema.org/draft/2020-12) for this tool's input. This defines the shape of the `input` that your tool accepts and that the model will produce. - `type: "object"` - `properties: optional map[unknown]` - `required: optional array of string` ### Beta Response Tool Removal Block - `beta_response_tool_removal_block: object` An entry of a `compaction` block's `tool_changes`: a tool of the request's `tools` (or an MCP tool or toolset) that the compacted range withdrew. Send it back unchanged. - `type: "tool_removal"` - `tool: BetaResponseToolChangeToolReference or BetaResponseToolChangeMCPToolReference or BetaResponseToolChangeMCPToolsetReference` A reference to the withdrawn `tools` entry, MCP tool or MCP toolset. - `beta_response_tool_change_tool_reference: object` Reference to a single tool, by the name the model uses to call it, as a `compaction` block's `tool_changes` entry reports it: a tool declared in `tools` or defined by an earlier `tool_addition` block. Send it back unchanged with the block. - `type: "tool_reference"` - `name: string` - `beta_response_tool_change_mcp_tool_reference: object` Reference to a single MCP tool, by its server and its name on that server, as a `compaction` block's `tool_changes` entry reports it. Send it back unchanged with the block. - `type: "mcp_tool_reference"` - `name: string` - `server_name: string` - `beta_response_tool_change_mcp_toolset_reference: object` Reference to every tool in the named MCP server's toolset, as a `compaction` block's `tool_changes` entry reports it. Send it back unchanged with the block. - `type: "mcp_toolset_reference"` - `server_name: string` ### Beta Response Tool Union - `beta_response_tool_union: BetaResponseTool or BetaToolBash20241022 or BetaToolBash20250124 or 25 more` - `beta_response_tool: object` A custom tool definition, as sent. - `type: optional "custom"` - `input_schema: object` [JSON schema](https://json-schema.org/draft/2020-12) for this tool's input. This defines the shape of the `input` that your tool accepts and that the model will produce. - `type: "object"` - `properties: optional map[unknown]` - `required: optional array of string` - `name: string` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. minLength: 1, maxLength: 128, pattern: ^[a-zA-Z0-9_-]{1,128}$ - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `description: optional string` Description of what this tool does. Tool descriptions should be as detailed as possible. The more information that the model has about what the tool is and how to use it, the better it will perform. You can use natural language descriptions to reinforce important aspects of the tool input JSON schema. - `eager_input_streaming: optional boolean` Enable eager input streaming for this tool. When true, tool input parameters will be streamed incrementally as they are generated, and types will be inferred on-the-fly rather than buffering the full JSON output. When false, streaming is disabled for this tool even if the fine-grained-tool-streaming beta is active. When null (default), uses the default behavior based on beta headers. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_bash_20241022: object` - `type: "bash_20241022"` - `name: "bash"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `"5m"` - `"1h"` - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_bash_20250124: object` - `type: "bash_20250124"` - `name: "bash"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_code_execution_tool_20250522: object` - `type: "code_execution_20250522"` - `name: "code_execution"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_code_execution_tool_20250825: object` - `type: "code_execution_20250825"` - `name: "code_execution"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_code_execution_tool_20260120: object` Code execution tool with REPL state persistence (daemon mode + gVisor checkpoint). - `type: "code_execution_20260120"` - `name: "code_execution"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_code_execution_tool_20260521: object` Code execution tool with REPL state persistence. - `type: "code_execution_20260521"` - `name: "code_execution"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_browser_toolset_20260801: object` The browser toolset: a single `tools[]` entry (carrying no `name`) that declares the browser tool family. The model is served the family's tool with any members disabled via `configs` removed from its schema. - `type: "browser_toolset_20260801"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `configs: optional object` Sparse per-member overrides, keyed by member name. Absent, null, and {} are equivalent; a member's defaults apply wherever its key is absent. - `type: optional object` `type`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `close_tab: optional object` `close_tab`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `double_click: optional object` `double_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `file_upload: optional object` `file_upload`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `find: optional object` `find`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `form_input: optional object` `form_input`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `get_page_text: optional object` `get_page_text`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `hold_key: optional object` `hold_key`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `hover: optional object` `hover`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `javascript_exec: optional object` `javascript_exec`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `key: optional object` `key`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_click: optional object` `left_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_click_drag: optional object` `left_click_drag`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_mouse_down: optional object` `left_mouse_down`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_mouse_up: optional object` `left_mouse_up`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `list_tabs: optional object` `list_tabs`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `middle_click: optional object` `middle_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `mouse_move: optional object` `mouse_move`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `navigate: optional object` `navigate`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `new_tab: optional object` `new_tab`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `read_console: optional object` `read_console`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `read_network: optional object` `read_network`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `read_page: optional object` `read_page`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `right_click: optional object` `right_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `screenshot: optional object` `screenshot`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `scroll: optional object` `scroll`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `scroll_to: optional object` `scroll_to`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `switch_tab: optional object` `switch_tab`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `triple_click: optional object` `triple_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `wait: optional object` `wait`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `zoom: optional object` `zoom`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `beta_tool_computer_use_20241022: object` - `type: "computer_20241022"` - `display_height_px: number` The height of the display in pixels. minimum: 1 - `display_width_px: number` The width of the display in pixels. minimum: 1 - `name: "computer"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `display_number: optional number` The X11 display number (e.g. 0, 1) for the display. minimum: 0 - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_memory_tool_20250818: object` - `type: "memory_20250818"` - `name: "memory"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_computer_use_20250124: object` - `type: "computer_20250124"` - `display_height_px: number` The height of the display in pixels. minimum: 1 - `display_width_px: number` The width of the display in pixels. minimum: 1 - `name: "computer"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `display_number: optional number` The X11 display number (e.g. 0, 1) for the display. minimum: 0 - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_text_editor_20241022: object` - `type: "text_editor_20241022"` - `name: "str_replace_editor"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_computer_use_20251124: object` - `type: "computer_20251124"` - `display_height_px: number` The height of the display in pixels. minimum: 1 - `display_width_px: number` The width of the display in pixels. minimum: 1 - `name: "computer"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `display_number: optional number` The X11 display number (e.g. 0, 1) for the display. minimum: 0 - `enable_zoom: optional boolean` Whether to enable an action to take a zoomed-in screenshot of the screen. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_computer_toolset_20260801: object` The computer toolset: a single `tools[]` entry (carrying no `name`) that declares the computer tool family. The model is served the family's tool with any members disabled via `configs` removed from its schema. Every member is enabled by default, zoom included. The single-tool options `display_number` and `enable_zoom` are not fields of a toolset entry — it carries only `type`, `configs`, and `cache_control`; zoom is controlled via `configs.zoom.enabled`. - `type: "computer_toolset_20260801"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `configs: optional object` Sparse per-member overrides, keyed by member name. Absent, null, and {} are equivalent; a member's defaults apply wherever its key is absent. - `type: optional object` `type`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `cursor_position: optional object` `cursor_position`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `double_click: optional object` `double_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `hold_key: optional object` `hold_key`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `key: optional object` `key`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_click: optional object` `left_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_click_drag: optional object` `left_click_drag`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_mouse_down: optional object` `left_mouse_down`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_mouse_up: optional object` `left_mouse_up`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `middle_click: optional object` `middle_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `mouse_move: optional object` `mouse_move`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `right_click: optional object` `right_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `screenshot: optional object` `screenshot`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `scroll: optional object` `scroll`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `triple_click: optional object` `triple_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `wait: optional object` `wait`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `zoom: optional object` `zoom`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `beta_tool_text_editor_20250124: object` - `type: "text_editor_20250124"` - `name: "str_replace_editor"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_text_editor_20250429: object` - `type: "text_editor_20250429"` - `name: "str_replace_based_edit_tool"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_text_editor_20250728: object` - `type: "text_editor_20250728"` - `name: "str_replace_based_edit_tool"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: optional array of map[unknown]` - `max_characters: optional number` Maximum number of characters to display when viewing a file. If not specified, defaults to displaying the full file. minimum: 1 - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_web_search_tool_20250305: object` - `type: "web_search_20250305"` - `name: "web_search"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: optional array of string` If provided, only these domains will be included in results. Cannot be used alongside `blocked_domains`. - `blocked_domains: optional array of string` If provided, these domains will never appear in results. Cannot be used alongside `allowed_domains`. - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `user_location: optional object` Parameters for the user's location. Used to provide more relevant search results. - `type: "approximate"` - `city: optional string` The city of the user. minLength: 1, maxLength: 255 - `country: optional string` The two letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1_alpha-2) of the user. minLength: 2, maxLength: 2 - `region: optional string` The region of the user. minLength: 1, maxLength: 255 - `timezone: optional string` The [IANA timezone](https://nodatime.org/TimeZones) of the user. minLength: 1, maxLength: 255 - `beta_web_fetch_tool_20250910: object` - `type: "web_fetch_20250910"` - `name: "web_fetch"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: optional array of string` List of domains to allow fetching from - `blocked_domains: optional array of string` List of domains to block fetching from - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `citations: optional object` Citations configuration for fetched documents. Citations are disabled by default. - `enabled: optional boolean` - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_content_tokens: optional number` Maximum number of tokens used by including web page text content in the context. The limit is approximate and does not apply to binary content such as PDFs. minimum: 1 - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `url_sources: optional object` Which sources contribute to the set of URLs the tool may fetch. Omitted means every source. - `client_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which client tools' results contribute fetchable URLs: "all", "none", or an only or except list of client tool names from tools[]. - `beta_web_fetch_url_source_all: object` The `url_sources` variant under which a source contributes in full: every result of the tool filter's source, or all user input. - `type: "all"` - `beta_web_fetch_url_source_none: object` The `url_sources` variant under which a source contributes nothing: no result of the tool filter's source, or no user input. - `type: "none"` - `beta_web_fetch_url_source_only: object` The tool filter variant under which only the named tools' results contribute. - `type: "only"` - `tools: array of BetaWebFetchURLSourceToolReference` - `type: "tool_reference"` - `name: string` - `beta_web_fetch_url_source_except: object` The tool filter variant under which every result but the named tools' contributes. - `type: "except"` - `tools: array of BetaWebFetchURLSourceToolReference` - `type: "tool_reference"` - `name: string` - `server_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which server tools' results contribute fetchable URLs: "all", "none", or an only or except list of server tool names from tools[]; only web_search and web_fetch results ever contribute. - `beta_web_fetch_url_source_all: object` The `url_sources` variant under which a source contributes in full: every result of the tool filter's source, or all user input. - `beta_web_fetch_url_source_none: object` The `url_sources` variant under which a source contributes nothing: no result of the tool filter's source, or no user input. - `beta_web_fetch_url_source_only: object` The tool filter variant under which only the named tools' results contribute. - `beta_web_fetch_url_source_except: object` The tool filter variant under which every result but the named tools' contributes. - `user_input: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone` Whether URLs in user messages are fetchable: "all" or "none". - `beta_web_fetch_url_source_all: object` The `url_sources` variant under which a source contributes in full: every result of the tool filter's source, or all user input. - `beta_web_fetch_url_source_none: object` The `url_sources` variant under which a source contributes nothing: no result of the tool filter's source, or no user input. - `beta_web_search_tool_20260209: object` - `type: "web_search_20260209"` - `name: "web_search"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: optional array of string` If provided, only these domains will be included in results. Cannot be used alongside `blocked_domains`. - `blocked_domains: optional array of string` If provided, these domains will never appear in results. Cannot be used alongside `allowed_domains`. - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `user_location: optional object` Parameters for the user's location. Used to provide more relevant search results. - `type: "approximate"` - `city: optional string` The city of the user. minLength: 1, maxLength: 255 - `country: optional string` The two letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1_alpha-2) of the user. minLength: 2, maxLength: 2 - `region: optional string` The region of the user. minLength: 1, maxLength: 255 - `timezone: optional string` The [IANA timezone](https://nodatime.org/TimeZones) of the user. minLength: 1, maxLength: 255 - `beta_web_fetch_tool_20260209: object` - `type: "web_fetch_20260209"` - `name: "web_fetch"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: optional array of string` List of domains to allow fetching from - `blocked_domains: optional array of string` List of domains to block fetching from - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `citations: optional object` Citations configuration for fetched documents. Citations are disabled by default. - `enabled: optional boolean` - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_content_tokens: optional number` Maximum number of tokens used by including web page text content in the context. The limit is approximate and does not apply to binary content such as PDFs. minimum: 1 - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `url_sources: optional object` Which sources contribute to the set of URLs the tool may fetch. Omitted means every source. - `client_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which client tools' results contribute fetchable URLs: "all", "none", or an only or except list of client tool names from tools[]. - `server_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which server tools' results contribute fetchable URLs: "all", "none", or an only or except list of server tool names from tools[]; only web_search and web_fetch results ever contribute. - `user_input: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone` Whether URLs in user messages are fetchable: "all" or "none". - `beta_web_fetch_tool_20260309: object` Web fetch tool with use_cache parameter for bypassing cached content. - `type: "web_fetch_20260309"` - `name: "web_fetch"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: optional array of string` List of domains to allow fetching from - `blocked_domains: optional array of string` List of domains to block fetching from - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `citations: optional object` Citations configuration for fetched documents. Citations are disabled by default. - `enabled: optional boolean` - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_content_tokens: optional number` Maximum number of tokens used by including web page text content in the context. The limit is approximate and does not apply to binary content such as PDFs. minimum: 1 - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `url_sources: optional object` Which sources contribute to the set of URLs the tool may fetch. Omitted means every source. - `client_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which client tools' results contribute fetchable URLs: "all", "none", or an only or except list of client tool names from tools[]. - `server_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which server tools' results contribute fetchable URLs: "all", "none", or an only or except list of server tool names from tools[]; only web_search and web_fetch results ever contribute. - `user_input: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone` Whether URLs in user messages are fetchable: "all" or "none". - `use_cache: optional boolean` Whether to use cached content. Set to false to bypass the cache and fetch fresh content. Only set to false when the user explicitly requests fresh content or when fetching rapidly-changing sources. - `beta_web_search_tool_20260318: object` - `type: "web_search_20260318"` - `name: "web_search"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: optional array of string` If provided, only these domains will be included in results. Cannot be used alongside `blocked_domains`. - `blocked_domains: optional array of string` If provided, these domains will never appear in results. Cannot be used alongside `allowed_domains`. - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `response_inclusion: optional "full" or "excluded"` How this tool's result blocks appear in the API response when the result was consumed by a completed code_execution call in the same turn. 'full' returns the complete content (default). 'excluded' drops the nested server_tool_use and result block pair entirely. Results from direct calls, or from code_execution calls that paused before completing, are always returned in full so they can be sent back on the next turn. - `"full"` - `"excluded"` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `user_location: optional object` Parameters for the user's location. Used to provide more relevant search results. - `type: "approximate"` - `city: optional string` The city of the user. minLength: 1, maxLength: 255 - `country: optional string` The two letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1_alpha-2) of the user. minLength: 2, maxLength: 2 - `region: optional string` The region of the user. minLength: 1, maxLength: 255 - `timezone: optional string` The [IANA timezone](https://nodatime.org/TimeZones) of the user. minLength: 1, maxLength: 255 - `beta_web_fetch_tool_20260318: object` - `type: "web_fetch_20260318"` - `name: "web_fetch"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: optional array of string` List of domains to allow fetching from - `blocked_domains: optional array of string` List of domains to block fetching from - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `citations: optional object` Citations configuration for fetched documents. Citations are disabled by default. - `enabled: optional boolean` - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_content_tokens: optional number` Maximum number of tokens used by including web page text content in the context. The limit is approximate and does not apply to binary content such as PDFs. minimum: 1 - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `response_inclusion: optional "full" or "excluded"` How this tool's result blocks appear in the API response when the result was consumed by a completed code_execution call in the same turn. 'full' returns the complete content (default). 'excluded' drops the nested server_tool_use and result block pair entirely. Results from direct calls, or from code_execution calls that paused before completing, are always returned in full so they can be sent back on the next turn. - `"full"` - `"excluded"` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `url_sources: optional object` Which sources contribute to the set of URLs the tool may fetch. Omitted means every source. - `client_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which client tools' results contribute fetchable URLs: "all", "none", or an only or except list of client tool names from tools[]. - `server_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which server tools' results contribute fetchable URLs: "all", "none", or an only or except list of server tool names from tools[]; only web_search and web_fetch results ever contribute. - `user_input: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone` Whether URLs in user messages are fetchable: "all" or "none". - `use_cache: optional boolean` Whether to use cached content. Set to false to bypass the cache and fetch fresh content. Only set to false when the user explicitly requests fresh content or when fetching rapidly-changing sources. - `beta_advisor_tool_20260301: object` - `type: "advisor_20260301"` - `model: "claude-haiku-5-5" or "claude-sonnet-5-5" or "claude-fable-5-1" or 17 more or string` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-haiku-5-5"` Fastest model for high-volume, real-time tasks - `"claude-sonnet-5-5"` Efficient model for coding and agents - `"claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows - `"claude-opus-5-5"` Powerful intelligence for coding, knowledge work, and long-running agents - `"claude-mythos-5-1"` Our most capable model for cybersecurity and biology research, available through trusted access programs - `"claude-sonnet-5"` Efficient model for coding and agents - `"claude-fable-5"` Next generation of intelligence for the hardest knowledge work and coding problems - `"claude-mythos-5"` Most capable model for cybersecurity and biology research - `"claude-opus-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-8"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-7"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-6"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-6"` Best combination of speed and intelligence - `"claude-haiku-4-5"` - `"claude-haiku-4-5-20251001"` - `"claude-opus-4-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-5-20251101"` Powerful intelligence for long-running agents and coding - `"claude-mythos-preview"` **Deprecated**: Will reach end-of-life on June 30, 2026. Please migrate to claude-mythos-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. New class of intelligence, strongest in coding and cybersecurity - `"claude-sonnet-4-5"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `"claude-sonnet-4-5-20250929"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `name: "advisor"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `caching: optional object` Caching for the advisor's own prompt. When set, each advisor call writes a cache entry at the given TTL so subsequent calls in the same conversation read the stable prefix. When omitted, the advisor prompt is not cached. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_tokens: optional number` Bounds the advisor's total output (thinking + text) per call. When the advisor hits this cap, the returned advisor_result or advisor_redacted_result block carries stop_reason='max_tokens', and a truncation note is appended to the advice text the worker model sees (inside the encrypted blob in redacted mode). When set, the server also emits a remaining-tokens budget block in the advisor's prompt so the advisor self-shapes toward the cap. When omitted, the advisor model's default output cap applies and no budget block is emitted. minimum: 1024 - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_search_tool_bm25_20251119: object` - `type: "tool_search_tool_bm25_20251119" or "tool_search_tool_bm25"` - `"tool_search_tool_bm25_20251119"` - `"tool_search_tool_bm25"` - `name: "tool_search_tool_bm25"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_search_tool_regex_20251119: object` - `type: "tool_search_tool_regex_20251119" or "tool_search_tool_regex"` - `"tool_search_tool_regex_20251119"` - `"tool_search_tool_regex"` - `name: "tool_search_tool_regex"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_mcp_toolset: object` Configuration for a group of tools from an MCP server. Allows configuring enabled status and defer_loading for all tools from an MCP server, with optional per-tool overrides. - `type: "mcp_toolset"` - `mcp_server_name: string` Name of the MCP server to configure tools for minLength: 1, maxLength: 255 - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `configs: optional map[BetaMCPToolConfig]` Configuration overrides for specific tools, keyed by tool name - `defer_loading: optional boolean` - `enabled: optional boolean` - `default_config: optional object` Default configuration applied to all tools from this server - `defer_loading: optional boolean` - `enabled: optional boolean` - `tools: optional array of BetaMCPToolParam` The server's tool listing, pinned: when present, the server is not asked for its tools before sampling and exactly these entries, with `default_config` and `configs` applied, are the toolset's tools. Copy it from the `mcp_tool_listing` block of an earlier response. - `input_schema: map[unknown]` The tool's input schema as the MCP server lists it, verbatim. - `name: string` The tool's name as the MCP server lists it (not prefixed with the server name). minLength: 1 - `description: optional string` The tool's description as the MCP server lists it. ### Beta Search Result Block Param - `beta_search_result_block_param: object` - `type: "search_result"` - `content: array of BetaTextBlockParam` - `type: "text"` - `text: string` minLength: 1 - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `"5m"` - `"1h"` - `citations: optional array of BetaTextCitationParam` - `beta_citation_char_location_param: object` - `type: "char_location"` - `cited_text: string` - `document_index: number` minimum: 0 - `document_title: string` minLength: 1, maxLength: 500 - `end_char_index: number` - `start_char_index: number` minimum: 0 - `beta_citation_page_location_param: object` - `type: "page_location"` - `cited_text: string` - `document_index: number` minimum: 0 - `document_title: string` minLength: 1, maxLength: 500 - `end_page_number: number` - `start_page_number: number` minimum: 1 - `beta_citation_content_block_location_param: object` - `type: "content_block_location"` - `cited_text: string` The full text of the cited block range, concatenated. Always equals the contents of `content[start_block_index:end_block_index]` joined together. The text block is the minimal citable unit; this field is never a substring of a single block. Not counted toward output tokens, and not counted toward input tokens when sent back in subsequent turns. - `document_index: number` minimum: 0 - `document_title: string` minLength: 1, maxLength: 500 - `end_block_index: number` Exclusive 0-based end index of the cited block range in the source's `content` array. Always greater than `start_block_index`; a single-block citation has `end_block_index = start_block_index + 1`. - `start_block_index: number` 0-based index of the first cited block in the source's `content` array. minimum: 0 - `beta_citation_web_search_result_location_param: object` - `type: "web_search_result_location"` - `cited_text: string` - `encrypted_index: string` - `title: string` minLength: 1, maxLength: 512 - `url: string` minLength: 1 - `beta_citation_search_result_location_param: object` - `type: "search_result_location"` - `cited_text: string` The full text of the cited block range, concatenated. Always equals the contents of `content[start_block_index:end_block_index]` joined together. The text block is the minimal citable unit; this field is never a substring of a single block. Not counted toward output tokens, and not counted toward input tokens when sent back in subsequent turns. - `end_block_index: number` Exclusive 0-based end index of the cited block range in the source's `content` array. Always greater than `start_block_index`; a single-block citation has `end_block_index = start_block_index + 1`. - `search_result_index: number` 0-based index of the cited search result among all `search_result` content blocks in the request, in the order they appear across messages and tool results. Counted separately from `document_index`; server-side web search results are not included in this count. minimum: 0 - `source: string` - `start_block_index: number` 0-based index of the first cited block in the source's `content` array. minimum: 0 - `title: string` - `source: string` - `title: string` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `citations: optional object` - `enabled: optional boolean` ### Beta Server Tool Caller - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `type: "code_execution_20250825"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ ### Beta Server Tool Caller 20260120 - `beta_server_tool_caller_20260120: object` - `type: "code_execution_20260120"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ ### Beta Server Tool Usage - `beta_server_tool_usage: object` - `web_fetch_requests: number` The number of web fetch tool requests. minimum: 0 - `web_search_requests: number` The number of web search tool requests. minimum: 0 ### Beta Server Tool Use Block - `beta_server_tool_use_block: object` - `type: "server_tool_use"` - `id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `input: map[unknown]` - `name: "advisor" or "web_search" or "web_fetch" or 5 more` - `"advisor"` - `"web_search"` - `"web_fetch"` - `"code_execution"` - `"bash_code_execution"` - `"text_editor_code_execution"` - `"tool_search_tool_regex"` - `"tool_search_tool_bm25"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` - `beta_direct_caller: object` Tool invocation directly from the model. - `type: "direct"` - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `type: "code_execution_20250825"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `beta_server_tool_caller_20260120: object` - `type: "code_execution_20260120"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ ### Beta Server Tool Use Block Param - `beta_server_tool_use_block_param: object` - `type: "server_tool_use"` - `id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `input: map[unknown]` - `name: "advisor" or "web_search" or "web_fetch" or 5 more` - `"advisor"` - `"web_search"` - `"web_fetch"` - `"code_execution"` - `"bash_code_execution"` - `"text_editor_code_execution"` - `"tool_search_tool_regex"` - `"tool_search_tool_bm25"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `"5m"` - `"1h"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` - `beta_direct_caller: object` Tool invocation directly from the model. - `type: "direct"` - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `type: "code_execution_20250825"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `beta_server_tool_caller_20260120: object` - `type: "code_execution_20260120"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ ### Beta Signature Delta - `beta_signature_delta: object` - `type: "signature_delta"` - `signature: string` The `signature` for this thinking block: an opaque value used to verify that the block was generated by Claude when it is passed back to the API. Delivered in a `signature_delta` event just before the block's `content_block_stop` event. ### Beta Skill Params - `beta_skill_params: object` Specification for a skill to be loaded in a container (request model). - `type: "anthropic" or "custom"` Type of skill - either 'anthropic' (built-in) or 'custom' (user-defined) - `"anthropic"` - `"custom"` - `skill_id: string` Skill ID minLength: 1, maxLength: 64 - `version: optional string` Skill version or 'latest' for most recent version minLength: 1, maxLength: 64 ### Beta Stop Reason - `beta_stop_reason: "end_turn" or "max_tokens" or "stop_sequence" or 5 more` - `"end_turn"` - `"max_tokens"` - `"stop_sequence"` - `"tool_use"` - `"pause_turn"` - `"compaction"` - `"refusal"` - `"model_context_window_exceeded"` ### Beta Summarize Compaction - `beta_summarize_compaction: object` Compact the whole conversation and return a signed `compaction` block, alone, that a later request sends back first in `messages`, in place of the messages it summarizes. There is no trigger and no pause flag: sending the parameter compacts, and nothing is sampled after the block. The summarization prompt is the server's own unless `instructions` are given, which then replace it for this request; a value that is empty or only whitespace counts as absent. - `type: "summarize"` - `instructions: optional string` Replaces the server's default summarization prompt for this request. An empty or whitespace-only value counts as absent. maxLength: 16384 ### Beta System Message Output Config - `beta_system_message_output_config: object` Per-message output configuration on a role:"system" input message. Fields here apply per-turn; `format` remains top-level only. An empty `{}` is accepted on a message that carries content; a message with neither content nor output_config fields is rejected. - `effort: optional "low" or "medium" or "high" or 2 more` How much effort the model should put into its response. Higher effort levels may result in more thorough analysis but take longer. Valid values are `low`, `medium`, `high`, `xhigh`, or `max`. - `"low"` - `"medium"` - `"high"` - `"xhigh"` - `"max"` ### Beta Text Block - `beta_text_block: object` - `type: "text"` - `citations: array of BetaTextCitation` Citations supporting the text block. The type of citation returned will depend on the type of document being cited. Citing a PDF results in `page_location`, plain text results in `char_location`, and content document results in `content_block_location`. - `beta_citation_char_location: object` - `type: "char_location"` - `cited_text: string` - `document_index: number` minimum: 0 - `document_title: string` - `end_char_index: number` - `file_id: string` - `start_char_index: number` minimum: 0 - `beta_citation_page_location: object` - `type: "page_location"` - `cited_text: string` - `document_index: number` minimum: 0 - `document_title: string` - `end_page_number: number` - `file_id: string` - `start_page_number: number` minimum: 1 - `beta_citation_content_block_location: object` - `type: "content_block_location"` - `cited_text: string` The full text of the cited block range, concatenated. Always equals the contents of `content[start_block_index:end_block_index]` joined together. The text block is the minimal citable unit; this field is never a substring of a single block. Not counted toward output tokens, and not counted toward input tokens when sent back in subsequent turns. - `document_index: number` minimum: 0 - `document_title: string` - `end_block_index: number` Exclusive 0-based end index of the cited block range in the source's `content` array. Always greater than `start_block_index`; a single-block citation has `end_block_index = start_block_index + 1`. - `file_id: string` - `start_block_index: number` 0-based index of the first cited block in the source's `content` array. minimum: 0 - `beta_citations_web_search_result_location: object` - `type: "web_search_result_location"` - `cited_text: string` - `encrypted_index: string` - `title: string` maxLength: 512 - `url: string` - `beta_citation_search_result_location: object` - `type: "search_result_location"` - `cited_text: string` The full text of the cited block range, concatenated. Always equals the contents of `content[start_block_index:end_block_index]` joined together. The text block is the minimal citable unit; this field is never a substring of a single block. Not counted toward output tokens, and not counted toward input tokens when sent back in subsequent turns. - `end_block_index: number` Exclusive 0-based end index of the cited block range in the source's `content` array. Always greater than `start_block_index`; a single-block citation has `end_block_index = start_block_index + 1`. - `search_result_index: number` 0-based index of the cited search result among all `search_result` content blocks in the request, in the order they appear across messages and tool results. Counted separately from `document_index`; server-side web search results are not included in this count. minimum: 0 - `source: string` - `start_block_index: number` 0-based index of the first cited block in the source's `content` array. minimum: 0 - `title: string` - `text: string` ### Beta Text Block Param - `beta_text_block_param: object` - `type: "text"` - `text: string` minLength: 1 - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `"5m"` - `"1h"` - `citations: optional array of BetaTextCitationParam` - `beta_citation_char_location_param: object` - `type: "char_location"` - `cited_text: string` - `document_index: number` minimum: 0 - `document_title: string` minLength: 1, maxLength: 500 - `end_char_index: number` - `start_char_index: number` minimum: 0 - `beta_citation_page_location_param: object` - `type: "page_location"` - `cited_text: string` - `document_index: number` minimum: 0 - `document_title: string` minLength: 1, maxLength: 500 - `end_page_number: number` - `start_page_number: number` minimum: 1 - `beta_citation_content_block_location_param: object` - `type: "content_block_location"` - `cited_text: string` The full text of the cited block range, concatenated. Always equals the contents of `content[start_block_index:end_block_index]` joined together. The text block is the minimal citable unit; this field is never a substring of a single block. Not counted toward output tokens, and not counted toward input tokens when sent back in subsequent turns. - `document_index: number` minimum: 0 - `document_title: string` minLength: 1, maxLength: 500 - `end_block_index: number` Exclusive 0-based end index of the cited block range in the source's `content` array. Always greater than `start_block_index`; a single-block citation has `end_block_index = start_block_index + 1`. - `start_block_index: number` 0-based index of the first cited block in the source's `content` array. minimum: 0 - `beta_citation_web_search_result_location_param: object` - `type: "web_search_result_location"` - `cited_text: string` - `encrypted_index: string` - `title: string` minLength: 1, maxLength: 512 - `url: string` minLength: 1 - `beta_citation_search_result_location_param: object` - `type: "search_result_location"` - `cited_text: string` The full text of the cited block range, concatenated. Always equals the contents of `content[start_block_index:end_block_index]` joined together. The text block is the minimal citable unit; this field is never a substring of a single block. Not counted toward output tokens, and not counted toward input tokens when sent back in subsequent turns. - `end_block_index: number` Exclusive 0-based end index of the cited block range in the source's `content` array. Always greater than `start_block_index`; a single-block citation has `end_block_index = start_block_index + 1`. - `search_result_index: number` 0-based index of the cited search result among all `search_result` content blocks in the request, in the order they appear across messages and tool results. Counted separately from `document_index`; server-side web search results are not included in this count. minimum: 0 - `source: string` - `start_block_index: number` 0-based index of the first cited block in the source's `content` array. minimum: 0 - `title: string` ### Beta Text Citation - `beta_text_citation: BetaCitationCharLocation or BetaCitationPageLocation or BetaCitationContentBlockLocation or 2 more` - `beta_citation_char_location: object` - `type: "char_location"` - `cited_text: string` - `document_index: number` minimum: 0 - `document_title: string` - `end_char_index: number` - `file_id: string` - `start_char_index: number` minimum: 0 - `beta_citation_page_location: object` - `type: "page_location"` - `cited_text: string` - `document_index: number` minimum: 0 - `document_title: string` - `end_page_number: number` - `file_id: string` - `start_page_number: number` minimum: 1 - `beta_citation_content_block_location: object` - `type: "content_block_location"` - `cited_text: string` The full text of the cited block range, concatenated. Always equals the contents of `content[start_block_index:end_block_index]` joined together. The text block is the minimal citable unit; this field is never a substring of a single block. Not counted toward output tokens, and not counted toward input tokens when sent back in subsequent turns. - `document_index: number` minimum: 0 - `document_title: string` - `end_block_index: number` Exclusive 0-based end index of the cited block range in the source's `content` array. Always greater than `start_block_index`; a single-block citation has `end_block_index = start_block_index + 1`. - `file_id: string` - `start_block_index: number` 0-based index of the first cited block in the source's `content` array. minimum: 0 - `beta_citations_web_search_result_location: object` - `type: "web_search_result_location"` - `cited_text: string` - `encrypted_index: string` - `title: string` maxLength: 512 - `url: string` - `beta_citation_search_result_location: object` - `type: "search_result_location"` - `cited_text: string` The full text of the cited block range, concatenated. Always equals the contents of `content[start_block_index:end_block_index]` joined together. The text block is the minimal citable unit; this field is never a substring of a single block. Not counted toward output tokens, and not counted toward input tokens when sent back in subsequent turns. - `end_block_index: number` Exclusive 0-based end index of the cited block range in the source's `content` array. Always greater than `start_block_index`; a single-block citation has `end_block_index = start_block_index + 1`. - `search_result_index: number` 0-based index of the cited search result among all `search_result` content blocks in the request, in the order they appear across messages and tool results. Counted separately from `document_index`; server-side web search results are not included in this count. minimum: 0 - `source: string` - `start_block_index: number` 0-based index of the first cited block in the source's `content` array. minimum: 0 - `title: string` ### Beta Text Citation Param - `beta_text_citation_param: BetaCitationCharLocationParam or BetaCitationPageLocationParam or BetaCitationContentBlockLocationParam or 2 more` - `beta_citation_char_location_param: object` - `type: "char_location"` - `cited_text: string` - `document_index: number` minimum: 0 - `document_title: string` minLength: 1, maxLength: 500 - `end_char_index: number` - `start_char_index: number` minimum: 0 - `beta_citation_page_location_param: object` - `type: "page_location"` - `cited_text: string` - `document_index: number` minimum: 0 - `document_title: string` minLength: 1, maxLength: 500 - `end_page_number: number` - `start_page_number: number` minimum: 1 - `beta_citation_content_block_location_param: object` - `type: "content_block_location"` - `cited_text: string` The full text of the cited block range, concatenated. Always equals the contents of `content[start_block_index:end_block_index]` joined together. The text block is the minimal citable unit; this field is never a substring of a single block. Not counted toward output tokens, and not counted toward input tokens when sent back in subsequent turns. - `document_index: number` minimum: 0 - `document_title: string` minLength: 1, maxLength: 500 - `end_block_index: number` Exclusive 0-based end index of the cited block range in the source's `content` array. Always greater than `start_block_index`; a single-block citation has `end_block_index = start_block_index + 1`. - `start_block_index: number` 0-based index of the first cited block in the source's `content` array. minimum: 0 - `beta_citation_web_search_result_location_param: object` - `type: "web_search_result_location"` - `cited_text: string` - `encrypted_index: string` - `title: string` minLength: 1, maxLength: 512 - `url: string` minLength: 1 - `beta_citation_search_result_location_param: object` - `type: "search_result_location"` - `cited_text: string` The full text of the cited block range, concatenated. Always equals the contents of `content[start_block_index:end_block_index]` joined together. The text block is the minimal citable unit; this field is never a substring of a single block. Not counted toward output tokens, and not counted toward input tokens when sent back in subsequent turns. - `end_block_index: number` Exclusive 0-based end index of the cited block range in the source's `content` array. Always greater than `start_block_index`; a single-block citation has `end_block_index = start_block_index + 1`. - `search_result_index: number` 0-based index of the cited search result among all `search_result` content blocks in the request, in the order they appear across messages and tool results. Counted separately from `document_index`; server-side web search results are not included in this count. minimum: 0 - `source: string` - `start_block_index: number` 0-based index of the first cited block in the source's `content` array. minimum: 0 - `title: string` ### Beta Text Delta - `beta_text_delta: object` - `type: "text_delta"` - `text: string` ### Beta Text Editor Code Execution Create Result Block - `beta_text_editor_code_execution_create_result_block: object` - `type: "text_editor_code_execution_create_result"` - `is_file_update: boolean` ### Beta Text Editor Code Execution Create Result Block Param - `beta_text_editor_code_execution_create_result_block_param: object` - `type: "text_editor_code_execution_create_result"` - `is_file_update: boolean` ### Beta Text Editor Code Execution Str Replace Result Block - `beta_text_editor_code_execution_str_replace_result_block: object` - `type: "text_editor_code_execution_str_replace_result"` - `lines: array of string` - `new_lines: number` - `new_start: number` - `old_lines: number` - `old_start: number` ### Beta Text Editor Code Execution Str Replace Result Block Param - `beta_text_editor_code_execution_str_replace_result_block_param: object` - `type: "text_editor_code_execution_str_replace_result"` - `lines: optional array of string` - `new_lines: optional number` - `new_start: optional number` - `old_lines: optional number` - `old_start: optional number` ### Beta Text Editor Code Execution Tool Result Block - `beta_text_editor_code_execution_tool_result_block: object` - `type: "text_editor_code_execution_tool_result"` - `content: BetaTextEditorCodeExecutionToolResultError or BetaTextEditorCodeExecutionViewResultBlock or BetaTextEditorCodeExecutionCreateResultBlock or BetaTextEditorCodeExecutionStrReplaceResultBlock` - `beta_text_editor_code_execution_tool_result_error: object` - `type: "text_editor_code_execution_tool_result_error"` - `error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or 2 more` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `"file_not_found"` - `error_message: string` - `beta_text_editor_code_execution_view_result_block: object` - `type: "text_editor_code_execution_view_result"` - `content: string` - `file_type: "text" or "image" or "pdf"` - `"text"` - `"image"` - `"pdf"` - `num_lines: number` - `start_line: number` - `total_lines: number` - `beta_text_editor_code_execution_create_result_block: object` - `type: "text_editor_code_execution_create_result"` - `is_file_update: boolean` - `beta_text_editor_code_execution_str_replace_result_block: object` - `type: "text_editor_code_execution_str_replace_result"` - `lines: array of string` - `new_lines: number` - `new_start: number` - `old_lines: number` - `old_start: number` - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ ### Beta Text Editor Code Execution Tool Result Block Param - `beta_text_editor_code_execution_tool_result_block_param: object` - `type: "text_editor_code_execution_tool_result"` - `content: BetaTextEditorCodeExecutionToolResultErrorParam or BetaTextEditorCodeExecutionViewResultBlockParam or BetaTextEditorCodeExecutionCreateResultBlockParam or BetaTextEditorCodeExecutionStrReplaceResultBlockParam` - `beta_text_editor_code_execution_tool_result_error_param: object` - `type: "text_editor_code_execution_tool_result_error"` - `error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or 2 more` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `"file_not_found"` - `error_message: optional string` - `beta_text_editor_code_execution_view_result_block_param: object` - `type: "text_editor_code_execution_view_result"` - `content: string` - `file_type: "text" or "image" or "pdf"` - `"text"` - `"image"` - `"pdf"` - `num_lines: optional number` - `start_line: optional number` - `total_lines: optional number` - `beta_text_editor_code_execution_create_result_block_param: object` - `type: "text_editor_code_execution_create_result"` - `is_file_update: boolean` - `beta_text_editor_code_execution_str_replace_result_block_param: object` - `type: "text_editor_code_execution_str_replace_result"` - `lines: optional array of string` - `new_lines: optional number` - `new_start: optional number` - `old_lines: optional number` - `old_start: optional number` - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `"5m"` - `"1h"` ### Beta Text Editor Code Execution Tool Result Error - `beta_text_editor_code_execution_tool_result_error: object` - `type: "text_editor_code_execution_tool_result_error"` - `error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or 2 more` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `"file_not_found"` - `error_message: string` ### Beta Text Editor Code Execution Tool Result Error Param - `beta_text_editor_code_execution_tool_result_error_param: object` - `type: "text_editor_code_execution_tool_result_error"` - `error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or 2 more` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `"file_not_found"` - `error_message: optional string` ### Beta Text Editor Code Execution View Result Block - `beta_text_editor_code_execution_view_result_block: object` - `type: "text_editor_code_execution_view_result"` - `content: string` - `file_type: "text" or "image" or "pdf"` - `"text"` - `"image"` - `"pdf"` - `num_lines: number` - `start_line: number` - `total_lines: number` ### Beta Text Editor Code Execution View Result Block Param - `beta_text_editor_code_execution_view_result_block_param: object` - `type: "text_editor_code_execution_view_result"` - `content: string` - `file_type: "text" or "image" or "pdf"` - `"text"` - `"image"` - `"pdf"` - `num_lines: optional number` - `start_line: optional number` - `total_lines: optional number` ### Beta Thinking Block - `beta_thinking_block: object` - `type: "thinking"` - `signature: string` A value used to verify that this thinking block was generated by Claude when it is passed back to the API. This is an opaque field and should not be interpreted or parsed. When passing thinking blocks back to the API (required when using tools with extended thinking), pass them back exactly as received, with this field intact. See [extended thinking](https://platform.claude.com/docs/en/build-with-claude/extended-thinking?sdk_languages=cli) for details. - `thinking: string` The text of Claude's thinking process for this block. ### Beta Thinking Block Binding - `beta_thinking_block_binding: object` Controls for block binding: what happens when a thinking block this request sends back fails the conversation check. Every field is optional; an empty object means every default. - `prefix_mismatch_behavior: optional "error" or "drop_block"` "error" (default) | "drop_block". What happens when a thinking block in `messages` fails the conversation check (it was created in a different conversation, or the messages before it have changed since). "error" fails the request with a 400 error. "drop_block" removes the failing blocks and the request proceeds; each removal is reported in `input_transformations`. - `"error"` - `"drop_block"` ### Beta Thinking Block Param - `beta_thinking_block_param: object` - `type: "thinking"` - `signature: string` The `signature` value of this thinking block, exactly as returned by the API in a previous response. Used to verify that the block was generated by Claude. Thinking blocks must be passed back unmodified and in their original order; a modified block results in a 400 `invalid_request_error`. - `thinking: string` The `thinking` text of this block as returned by the API. ### Beta Thinking Config Adaptive - `beta_thinking_config_adaptive: object` - `type: "adaptive"` - `block_binding: optional object` Controls for block binding: what happens when a thinking block this request sends back fails the conversation check. `null`, absent or an empty object means every default. - `prefix_mismatch_behavior: optional "error" or "drop_block"` "error" (default) | "drop_block". What happens when a thinking block in `messages` fails the conversation check (it was created in a different conversation, or the messages before it have changed since). "error" fails the request with a 400 error. "drop_block" removes the failing blocks and the request proceeds; each removal is reported in `input_transformations`. - `"error"` - `"drop_block"` - `display: optional "summarized" or "omitted" or "updates"` Controls how thinking content appears in the response. When set to `summarized`, thinking is returned normally. When set to `omitted`, thinking content is redacted but a signature is returned for multi-turn continuity. The default depends on the model; see [Controlling thinking display](https://platform.claude.com/docs/en/build-with-claude/thinking?sdk_languages=cli#controlling-thinking-display). - `"summarized"` - `"omitted"` - `"updates"` ### Beta Thinking Config Between Tools - `beta_thinking_config_between_tools: object` - `type: "between_tools"` ### Beta Thinking Config Disabled - `beta_thinking_config_disabled: object` - `type: "disabled"` ### Beta Thinking Config Enabled - `beta_thinking_config_enabled: object` - `type: "enabled"` - `budget_tokens: number` Determines how many tokens Claude can use for its internal reasoning process. Larger budgets can enable more thorough analysis for complex problems, improving response quality. Must be ≥1024 and less than `max_tokens`. See [extended thinking](https://platform.claude.com/docs/en/build-with-claude/extended-thinking?sdk_languages=cli) for details. minimum: 1024 - `block_binding: optional object` Controls for block binding: what happens when a thinking block this request sends back fails the conversation check. `null`, absent or an empty object means every default. - `prefix_mismatch_behavior: optional "error" or "drop_block"` "error" (default) | "drop_block". What happens when a thinking block in `messages` fails the conversation check (it was created in a different conversation, or the messages before it have changed since). "error" fails the request with a 400 error. "drop_block" removes the failing blocks and the request proceeds; each removal is reported in `input_transformations`. - `"error"` - `"drop_block"` - `display: optional "summarized" or "omitted" or "updates"` Controls how thinking content appears in the response. When set to `summarized`, thinking is returned normally. When set to `omitted`, thinking content is redacted but a signature is returned for multi-turn continuity. The default depends on the model; see [Controlling thinking display](https://platform.claude.com/docs/en/build-with-claude/thinking?sdk_languages=cli#controlling-thinking-display). - `"summarized"` - `"omitted"` - `"updates"` ### Beta Thinking Config Param - `beta_thinking_config_param: BetaThinkingConfigEnabled or BetaThinkingConfigDisabled or BetaThinkingConfigBetweenTools or BetaThinkingConfigAdaptive` Configuration for Claude's thinking. With `{"type": "adaptive"}`, Claude decides when and how much to think. With `{"type": "enabled"}` (manual extended thinking), you set a `budget_tokens` of at least 1,024. Thinking tokens count toward your `max_tokens` limit. Which `type` values are accepted, and what happens when you omit `thinking`, depend on the model. See [thinking](https://platform.claude.com/docs/en/build-with-claude/thinking?sdk_languages=cli#configuring-thinking) for each model's behavior. - `beta_thinking_config_enabled: object` - `type: "enabled"` - `budget_tokens: number` Determines how many tokens Claude can use for its internal reasoning process. Larger budgets can enable more thorough analysis for complex problems, improving response quality. Must be ≥1024 and less than `max_tokens`. See [extended thinking](https://platform.claude.com/docs/en/build-with-claude/extended-thinking?sdk_languages=cli) for details. minimum: 1024 - `block_binding: optional object` Controls for block binding: what happens when a thinking block this request sends back fails the conversation check. `null`, absent or an empty object means every default. - `prefix_mismatch_behavior: optional "error" or "drop_block"` "error" (default) | "drop_block". What happens when a thinking block in `messages` fails the conversation check (it was created in a different conversation, or the messages before it have changed since). "error" fails the request with a 400 error. "drop_block" removes the failing blocks and the request proceeds; each removal is reported in `input_transformations`. - `"error"` - `"drop_block"` - `display: optional "summarized" or "omitted" or "updates"` Controls how thinking content appears in the response. When set to `summarized`, thinking is returned normally. When set to `omitted`, thinking content is redacted but a signature is returned for multi-turn continuity. The default depends on the model; see [Controlling thinking display](https://platform.claude.com/docs/en/build-with-claude/thinking?sdk_languages=cli#controlling-thinking-display). - `"summarized"` - `"omitted"` - `"updates"` - `beta_thinking_config_disabled: object` - `type: "disabled"` - `beta_thinking_config_between_tools: object` - `type: "between_tools"` - `beta_thinking_config_adaptive: object` - `type: "adaptive"` - `block_binding: optional object` Controls for block binding: what happens when a thinking block this request sends back fails the conversation check. `null`, absent or an empty object means every default. - `prefix_mismatch_behavior: optional "error" or "drop_block"` "error" (default) | "drop_block". What happens when a thinking block in `messages` fails the conversation check (it was created in a different conversation, or the messages before it have changed since). "error" fails the request with a 400 error. "drop_block" removes the failing blocks and the request proceeds; each removal is reported in `input_transformations`. - `display: optional "summarized" or "omitted" or "updates"` Controls how thinking content appears in the response. When set to `summarized`, thinking is returned normally. When set to `omitted`, thinking content is redacted but a signature is returned for multi-turn continuity. The default depends on the model; see [Controlling thinking display](https://platform.claude.com/docs/en/build-with-claude/thinking?sdk_languages=cli#controlling-thinking-display). - `"summarized"` - `"omitted"` - `"updates"` ### Beta Thinking Delta - `beta_thinking_delta: object` - `type: "thinking_delta"` - `estimated_tokens: number` Per-frame increment of a coarse, running estimate of the tokens this thinking block has produced so far. Present whenever the `thinking-token-count-2026-05-13` beta is set; `null` unless `thinking.display` resolves to `"omitted"` and a count is due this frame. Sum the increments across `thinking_delta` frames on this block for a progress indicator. Each increment is a non-negative multiple of a fixed quantum and the cadence is rate-limited, so this is a deliberately lossy display hint, not a billable count; `usage.output_tokens` remains authoritative. - `thinking: string` The incremental `thinking` text for this content block. Concatenate the `thinking` values of successive `thinking_delta` events to assemble the block's full `thinking` value. ### Beta Thinking Dropped Input Transformation - `beta_thinking_dropped_input_transformation: object` - `type: "thinking_dropped"` Always `thinking_dropped` for this entry type. - `path: string` Where the removed block was in your request, as `messages.{i}.content.{j}`: `i` indexes the `messages` array you sent and `j` that message's `content` array — the same form error messages use. - `reason: "model_binding_mismatch" or "prefix_binding_mismatch" or "organization_binding_mismatch" or "end_user_binding_mismatch"` Which binding check removed the block: `model_binding_mismatch` — it was created by a model whose reasoning the requested model may not read; `prefix_binding_mismatch` — the conversation before it differs from the conversation it was created in (the rest of that turn's consecutive thinking blocks are removed with it, each with this reason); `organization_binding_mismatch` — it was created under a different organization (an Anthropic organization, AWS account or Google Cloud project) and this organization is not one of its additional organizations; `end_user_binding_mismatch` — it was created for a different end user, or was removed by the consumer-organization binding. A block that would fail several checks reports one reason, in this order of precedence: `organization_binding_mismatch`, `end_user_binding_mismatch`, `model_binding_mismatch`, `prefix_binding_mismatch`. - `"model_binding_mismatch"` - `"prefix_binding_mismatch"` - `"organization_binding_mismatch"` - `"end_user_binding_mismatch"` ### Beta Thinking Mismatch Allowed Input Transformation - `beta_thinking_mismatch_allowed_input_transformation: object` - `type: "thinking_mismatch_allowed"` Always `thinking_mismatch_allowed` for this entry type. - `path: string` Where the block is in your request, as `messages.{i}.content.{j}`: `i` indexes the `messages` array you sent and `j` that message's `content` array — the same form error messages use. - `reason: "model_binding_mismatch" or "prefix_binding_mismatch" or "organization_binding_mismatch" or "end_user_binding_mismatch"` Which binding check the block failed; the block was shown to the model all the same. Always `prefix_binding_mismatch` today — the conversation before the block differs from the conversation it was created in, or the block carries no record of one on a model that requires it. Were the check enforced for this request, the block would have been removed or the request rejected (`thinking.block_binding.prefix_mismatch_behavior`). A removal also takes the rest of that turn's consecutive thinking blocks, whereas here each block is checked on its own, so `thinking_mismatch_allowed` entries are a lower bound on what enforcement would remove. - `"model_binding_mismatch"` - `"prefix_binding_mismatch"` - `"organization_binding_mismatch"` - `"end_user_binding_mismatch"` ### Beta Thinking Prefix Mismatch Behavior - `beta_thinking_prefix_mismatch_behavior: "error" or "drop_block"` What happens when a thinking block in `messages` fails the conversation check: it was created in a different conversation, or the messages before it have changed since. `"error"` (the default) fails the request with a 400 error. `"drop_block"` removes the failing blocks and the request proceeds; the model no longer sees the dropped reasoning. - `"error"` - `"drop_block"` ### Beta Thinking Turns - `beta_thinking_turns: object` - `type: "thinking_turns"` - `value: number` minimum: 1 ### Beta Token Task Budget - `beta_token_task_budget: object` User-configurable total token budget across contexts. - `type: "tokens"` The budget type. Currently only 'tokens' is supported. - `total: number` Total token budget across all contexts in the session. minimum: 1024 - `remaining: optional number` Remaining tokens in the budget. Use this to track usage across contexts when implementing compaction client-side. Defaults to total if not provided. minimum: 0 ### Beta Tool - `beta_tool: object` - `type: optional "custom"` - `input_schema: object` [JSON schema](https://json-schema.org/draft/2020-12) for this tool's input. This defines the shape of the `input` that your tool accepts and that the model will produce. - `type: "object"` - `properties: optional map[unknown]` - `required: optional array of string` - `name: string` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. minLength: 1, maxLength: 128, pattern: ^[a-zA-Z0-9_-]{1,128}$ - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `"5m"` - `"1h"` - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `description: optional string` Description of what this tool does. Tool descriptions should be as detailed as possible. The more information that the model has about what the tool is and how to use it, the better it will perform. You can use natural language descriptions to reinforce important aspects of the tool input JSON schema. - `eager_input_streaming: optional boolean` Enable eager input streaming for this tool. When true, tool input parameters will be streamed incrementally as they are generated, and types will be inferred on-the-fly rather than buffering the full JSON output. When false, streaming is disabled for this tool even if the fine-grained-tool-streaming beta is active. When null (default), uses the default behavior based on beta headers. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs ### Beta Tool Bash 20241022 - `beta_tool_bash_20241022: object` - `type: "bash_20241022"` - `name: "bash"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `"5m"` - `"1h"` - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs ### Beta Tool Bash 20250124 - `beta_tool_bash_20250124: object` - `type: "bash_20250124"` - `name: "bash"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `"5m"` - `"1h"` - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs ### Beta Tool Change MCP Tool Reference - `beta_tool_change_mcp_tool_reference: object` Reference to a single MCP tool by its server and remote name; the same `server_name`/`name` pair `mcp_tool_use` carries. - `type: "mcp_tool_reference"` - `name: string` - `server_name: string` ### Beta Tool Change MCP Toolset Reference - `beta_tool_change_mcp_toolset_reference: object` Reference to every tool in the named MCP server's toolset. - `type: "mcp_toolset_reference"` - `server_name: string` ### Beta Tool Change Tool Definition - `beta_tool_change_tool_definition: object` A tool defined by value, as a `compaction` block's `tool_changes` entry reports it: `definition` is the tool's definition as it was sent, in the form of a `tools` entry, without `cache_control`. Send it back unchanged with the block. - `type: "tool_definition"` - `definition: BetaResponseTool or BetaToolBash20241022 or BetaToolBash20250124 or 25 more` - `beta_response_tool: object` A custom tool definition, as sent. - `type: optional "custom"` - `input_schema: object` [JSON schema](https://json-schema.org/draft/2020-12) for this tool's input. This defines the shape of the `input` that your tool accepts and that the model will produce. - `type: "object"` - `properties: optional map[unknown]` - `required: optional array of string` - `name: string` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. minLength: 1, maxLength: 128, pattern: ^[a-zA-Z0-9_-]{1,128}$ - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `description: optional string` Description of what this tool does. Tool descriptions should be as detailed as possible. The more information that the model has about what the tool is and how to use it, the better it will perform. You can use natural language descriptions to reinforce important aspects of the tool input JSON schema. - `eager_input_streaming: optional boolean` Enable eager input streaming for this tool. When true, tool input parameters will be streamed incrementally as they are generated, and types will be inferred on-the-fly rather than buffering the full JSON output. When false, streaming is disabled for this tool even if the fine-grained-tool-streaming beta is active. When null (default), uses the default behavior based on beta headers. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_bash_20241022: object` - `type: "bash_20241022"` - `name: "bash"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `"5m"` - `"1h"` - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_bash_20250124: object` - `type: "bash_20250124"` - `name: "bash"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_code_execution_tool_20250522: object` - `type: "code_execution_20250522"` - `name: "code_execution"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_code_execution_tool_20250825: object` - `type: "code_execution_20250825"` - `name: "code_execution"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_code_execution_tool_20260120: object` Code execution tool with REPL state persistence (daemon mode + gVisor checkpoint). - `type: "code_execution_20260120"` - `name: "code_execution"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_code_execution_tool_20260521: object` Code execution tool with REPL state persistence. - `type: "code_execution_20260521"` - `name: "code_execution"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_browser_toolset_20260801: object` The browser toolset: a single `tools[]` entry (carrying no `name`) that declares the browser tool family. The model is served the family's tool with any members disabled via `configs` removed from its schema. - `type: "browser_toolset_20260801"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `configs: optional object` Sparse per-member overrides, keyed by member name. Absent, null, and {} are equivalent; a member's defaults apply wherever its key is absent. - `type: optional object` `type`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `close_tab: optional object` `close_tab`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `double_click: optional object` `double_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `file_upload: optional object` `file_upload`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `find: optional object` `find`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `form_input: optional object` `form_input`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `get_page_text: optional object` `get_page_text`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `hold_key: optional object` `hold_key`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `hover: optional object` `hover`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `javascript_exec: optional object` `javascript_exec`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `key: optional object` `key`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_click: optional object` `left_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_click_drag: optional object` `left_click_drag`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_mouse_down: optional object` `left_mouse_down`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_mouse_up: optional object` `left_mouse_up`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `list_tabs: optional object` `list_tabs`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `middle_click: optional object` `middle_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `mouse_move: optional object` `mouse_move`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `navigate: optional object` `navigate`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `new_tab: optional object` `new_tab`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `read_console: optional object` `read_console`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `read_network: optional object` `read_network`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `read_page: optional object` `read_page`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `right_click: optional object` `right_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `screenshot: optional object` `screenshot`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `scroll: optional object` `scroll`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `scroll_to: optional object` `scroll_to`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `switch_tab: optional object` `switch_tab`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `triple_click: optional object` `triple_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `wait: optional object` `wait`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `zoom: optional object` `zoom`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `beta_tool_computer_use_20241022: object` - `type: "computer_20241022"` - `display_height_px: number` The height of the display in pixels. minimum: 1 - `display_width_px: number` The width of the display in pixels. minimum: 1 - `name: "computer"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `display_number: optional number` The X11 display number (e.g. 0, 1) for the display. minimum: 0 - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_memory_tool_20250818: object` - `type: "memory_20250818"` - `name: "memory"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_computer_use_20250124: object` - `type: "computer_20250124"` - `display_height_px: number` The height of the display in pixels. minimum: 1 - `display_width_px: number` The width of the display in pixels. minimum: 1 - `name: "computer"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `display_number: optional number` The X11 display number (e.g. 0, 1) for the display. minimum: 0 - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_text_editor_20241022: object` - `type: "text_editor_20241022"` - `name: "str_replace_editor"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_computer_use_20251124: object` - `type: "computer_20251124"` - `display_height_px: number` The height of the display in pixels. minimum: 1 - `display_width_px: number` The width of the display in pixels. minimum: 1 - `name: "computer"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `display_number: optional number` The X11 display number (e.g. 0, 1) for the display. minimum: 0 - `enable_zoom: optional boolean` Whether to enable an action to take a zoomed-in screenshot of the screen. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_computer_toolset_20260801: object` The computer toolset: a single `tools[]` entry (carrying no `name`) that declares the computer tool family. The model is served the family's tool with any members disabled via `configs` removed from its schema. Every member is enabled by default, zoom included. The single-tool options `display_number` and `enable_zoom` are not fields of a toolset entry — it carries only `type`, `configs`, and `cache_control`; zoom is controlled via `configs.zoom.enabled`. - `type: "computer_toolset_20260801"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `configs: optional object` Sparse per-member overrides, keyed by member name. Absent, null, and {} are equivalent; a member's defaults apply wherever its key is absent. - `type: optional object` `type`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `cursor_position: optional object` `cursor_position`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `double_click: optional object` `double_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `hold_key: optional object` `hold_key`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `key: optional object` `key`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_click: optional object` `left_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_click_drag: optional object` `left_click_drag`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_mouse_down: optional object` `left_mouse_down`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_mouse_up: optional object` `left_mouse_up`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `middle_click: optional object` `middle_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `mouse_move: optional object` `mouse_move`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `right_click: optional object` `right_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `screenshot: optional object` `screenshot`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `scroll: optional object` `scroll`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `triple_click: optional object` `triple_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `wait: optional object` `wait`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `zoom: optional object` `zoom`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `beta_tool_text_editor_20250124: object` - `type: "text_editor_20250124"` - `name: "str_replace_editor"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_text_editor_20250429: object` - `type: "text_editor_20250429"` - `name: "str_replace_based_edit_tool"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_text_editor_20250728: object` - `type: "text_editor_20250728"` - `name: "str_replace_based_edit_tool"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: optional array of map[unknown]` - `max_characters: optional number` Maximum number of characters to display when viewing a file. If not specified, defaults to displaying the full file. minimum: 1 - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_web_search_tool_20250305: object` - `type: "web_search_20250305"` - `name: "web_search"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: optional array of string` If provided, only these domains will be included in results. Cannot be used alongside `blocked_domains`. - `blocked_domains: optional array of string` If provided, these domains will never appear in results. Cannot be used alongside `allowed_domains`. - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `user_location: optional object` Parameters for the user's location. Used to provide more relevant search results. - `type: "approximate"` - `city: optional string` The city of the user. minLength: 1, maxLength: 255 - `country: optional string` The two letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1_alpha-2) of the user. minLength: 2, maxLength: 2 - `region: optional string` The region of the user. minLength: 1, maxLength: 255 - `timezone: optional string` The [IANA timezone](https://nodatime.org/TimeZones) of the user. minLength: 1, maxLength: 255 - `beta_web_fetch_tool_20250910: object` - `type: "web_fetch_20250910"` - `name: "web_fetch"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: optional array of string` List of domains to allow fetching from - `blocked_domains: optional array of string` List of domains to block fetching from - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `citations: optional object` Citations configuration for fetched documents. Citations are disabled by default. - `enabled: optional boolean` - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_content_tokens: optional number` Maximum number of tokens used by including web page text content in the context. The limit is approximate and does not apply to binary content such as PDFs. minimum: 1 - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `url_sources: optional object` Which sources contribute to the set of URLs the tool may fetch. Omitted means every source. - `client_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which client tools' results contribute fetchable URLs: "all", "none", or an only or except list of client tool names from tools[]. - `beta_web_fetch_url_source_all: object` The `url_sources` variant under which a source contributes in full: every result of the tool filter's source, or all user input. - `type: "all"` - `beta_web_fetch_url_source_none: object` The `url_sources` variant under which a source contributes nothing: no result of the tool filter's source, or no user input. - `type: "none"` - `beta_web_fetch_url_source_only: object` The tool filter variant under which only the named tools' results contribute. - `type: "only"` - `tools: array of BetaWebFetchURLSourceToolReference` - `type: "tool_reference"` - `name: string` - `beta_web_fetch_url_source_except: object` The tool filter variant under which every result but the named tools' contributes. - `type: "except"` - `tools: array of BetaWebFetchURLSourceToolReference` - `type: "tool_reference"` - `name: string` - `server_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which server tools' results contribute fetchable URLs: "all", "none", or an only or except list of server tool names from tools[]; only web_search and web_fetch results ever contribute. - `beta_web_fetch_url_source_all: object` The `url_sources` variant under which a source contributes in full: every result of the tool filter's source, or all user input. - `beta_web_fetch_url_source_none: object` The `url_sources` variant under which a source contributes nothing: no result of the tool filter's source, or no user input. - `beta_web_fetch_url_source_only: object` The tool filter variant under which only the named tools' results contribute. - `beta_web_fetch_url_source_except: object` The tool filter variant under which every result but the named tools' contributes. - `user_input: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone` Whether URLs in user messages are fetchable: "all" or "none". - `beta_web_fetch_url_source_all: object` The `url_sources` variant under which a source contributes in full: every result of the tool filter's source, or all user input. - `beta_web_fetch_url_source_none: object` The `url_sources` variant under which a source contributes nothing: no result of the tool filter's source, or no user input. - `beta_web_search_tool_20260209: object` - `type: "web_search_20260209"` - `name: "web_search"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: optional array of string` If provided, only these domains will be included in results. Cannot be used alongside `blocked_domains`. - `blocked_domains: optional array of string` If provided, these domains will never appear in results. Cannot be used alongside `allowed_domains`. - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `user_location: optional object` Parameters for the user's location. Used to provide more relevant search results. - `type: "approximate"` - `city: optional string` The city of the user. minLength: 1, maxLength: 255 - `country: optional string` The two letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1_alpha-2) of the user. minLength: 2, maxLength: 2 - `region: optional string` The region of the user. minLength: 1, maxLength: 255 - `timezone: optional string` The [IANA timezone](https://nodatime.org/TimeZones) of the user. minLength: 1, maxLength: 255 - `beta_web_fetch_tool_20260209: object` - `type: "web_fetch_20260209"` - `name: "web_fetch"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: optional array of string` List of domains to allow fetching from - `blocked_domains: optional array of string` List of domains to block fetching from - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `citations: optional object` Citations configuration for fetched documents. Citations are disabled by default. - `enabled: optional boolean` - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_content_tokens: optional number` Maximum number of tokens used by including web page text content in the context. The limit is approximate and does not apply to binary content such as PDFs. minimum: 1 - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `url_sources: optional object` Which sources contribute to the set of URLs the tool may fetch. Omitted means every source. - `client_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which client tools' results contribute fetchable URLs: "all", "none", or an only or except list of client tool names from tools[]. - `server_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which server tools' results contribute fetchable URLs: "all", "none", or an only or except list of server tool names from tools[]; only web_search and web_fetch results ever contribute. - `user_input: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone` Whether URLs in user messages are fetchable: "all" or "none". - `beta_web_fetch_tool_20260309: object` Web fetch tool with use_cache parameter for bypassing cached content. - `type: "web_fetch_20260309"` - `name: "web_fetch"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: optional array of string` List of domains to allow fetching from - `blocked_domains: optional array of string` List of domains to block fetching from - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `citations: optional object` Citations configuration for fetched documents. Citations are disabled by default. - `enabled: optional boolean` - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_content_tokens: optional number` Maximum number of tokens used by including web page text content in the context. The limit is approximate and does not apply to binary content such as PDFs. minimum: 1 - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `url_sources: optional object` Which sources contribute to the set of URLs the tool may fetch. Omitted means every source. - `client_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which client tools' results contribute fetchable URLs: "all", "none", or an only or except list of client tool names from tools[]. - `server_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which server tools' results contribute fetchable URLs: "all", "none", or an only or except list of server tool names from tools[]; only web_search and web_fetch results ever contribute. - `user_input: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone` Whether URLs in user messages are fetchable: "all" or "none". - `use_cache: optional boolean` Whether to use cached content. Set to false to bypass the cache and fetch fresh content. Only set to false when the user explicitly requests fresh content or when fetching rapidly-changing sources. - `beta_web_search_tool_20260318: object` - `type: "web_search_20260318"` - `name: "web_search"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: optional array of string` If provided, only these domains will be included in results. Cannot be used alongside `blocked_domains`. - `blocked_domains: optional array of string` If provided, these domains will never appear in results. Cannot be used alongside `allowed_domains`. - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `response_inclusion: optional "full" or "excluded"` How this tool's result blocks appear in the API response when the result was consumed by a completed code_execution call in the same turn. 'full' returns the complete content (default). 'excluded' drops the nested server_tool_use and result block pair entirely. Results from direct calls, or from code_execution calls that paused before completing, are always returned in full so they can be sent back on the next turn. - `"full"` - `"excluded"` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `user_location: optional object` Parameters for the user's location. Used to provide more relevant search results. - `type: "approximate"` - `city: optional string` The city of the user. minLength: 1, maxLength: 255 - `country: optional string` The two letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1_alpha-2) of the user. minLength: 2, maxLength: 2 - `region: optional string` The region of the user. minLength: 1, maxLength: 255 - `timezone: optional string` The [IANA timezone](https://nodatime.org/TimeZones) of the user. minLength: 1, maxLength: 255 - `beta_web_fetch_tool_20260318: object` - `type: "web_fetch_20260318"` - `name: "web_fetch"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: optional array of string` List of domains to allow fetching from - `blocked_domains: optional array of string` List of domains to block fetching from - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `citations: optional object` Citations configuration for fetched documents. Citations are disabled by default. - `enabled: optional boolean` - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_content_tokens: optional number` Maximum number of tokens used by including web page text content in the context. The limit is approximate and does not apply to binary content such as PDFs. minimum: 1 - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `response_inclusion: optional "full" or "excluded"` How this tool's result blocks appear in the API response when the result was consumed by a completed code_execution call in the same turn. 'full' returns the complete content (default). 'excluded' drops the nested server_tool_use and result block pair entirely. Results from direct calls, or from code_execution calls that paused before completing, are always returned in full so they can be sent back on the next turn. - `"full"` - `"excluded"` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `url_sources: optional object` Which sources contribute to the set of URLs the tool may fetch. Omitted means every source. - `client_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which client tools' results contribute fetchable URLs: "all", "none", or an only or except list of client tool names from tools[]. - `server_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which server tools' results contribute fetchable URLs: "all", "none", or an only or except list of server tool names from tools[]; only web_search and web_fetch results ever contribute. - `user_input: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone` Whether URLs in user messages are fetchable: "all" or "none". - `use_cache: optional boolean` Whether to use cached content. Set to false to bypass the cache and fetch fresh content. Only set to false when the user explicitly requests fresh content or when fetching rapidly-changing sources. - `beta_advisor_tool_20260301: object` - `type: "advisor_20260301"` - `model: "claude-haiku-5-5" or "claude-sonnet-5-5" or "claude-fable-5-1" or 17 more or string` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-haiku-5-5"` Fastest model for high-volume, real-time tasks - `"claude-sonnet-5-5"` Efficient model for coding and agents - `"claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows - `"claude-opus-5-5"` Powerful intelligence for coding, knowledge work, and long-running agents - `"claude-mythos-5-1"` Our most capable model for cybersecurity and biology research, available through trusted access programs - `"claude-sonnet-5"` Efficient model for coding and agents - `"claude-fable-5"` Next generation of intelligence for the hardest knowledge work and coding problems - `"claude-mythos-5"` Most capable model for cybersecurity and biology research - `"claude-opus-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-8"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-7"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-6"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-6"` Best combination of speed and intelligence - `"claude-haiku-4-5"` - `"claude-haiku-4-5-20251001"` - `"claude-opus-4-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-5-20251101"` Powerful intelligence for long-running agents and coding - `"claude-mythos-preview"` **Deprecated**: Will reach end-of-life on June 30, 2026. Please migrate to claude-mythos-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. New class of intelligence, strongest in coding and cybersecurity - `"claude-sonnet-4-5"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `"claude-sonnet-4-5-20250929"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `name: "advisor"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `caching: optional object` Caching for the advisor's own prompt. When set, each advisor call writes a cache entry at the given TTL so subsequent calls in the same conversation read the stable prefix. When omitted, the advisor prompt is not cached. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_tokens: optional number` Bounds the advisor's total output (thinking + text) per call. When the advisor hits this cap, the returned advisor_result or advisor_redacted_result block carries stop_reason='max_tokens', and a truncation note is appended to the advice text the worker model sees (inside the encrypted blob in redacted mode). When set, the server also emits a remaining-tokens budget block in the advisor's prompt so the advisor self-shapes toward the cap. When omitted, the advisor model's default output cap applies and no budget block is emitted. minimum: 1024 - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_search_tool_bm25_20251119: object` - `type: "tool_search_tool_bm25_20251119" or "tool_search_tool_bm25"` - `"tool_search_tool_bm25_20251119"` - `"tool_search_tool_bm25"` - `name: "tool_search_tool_bm25"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_search_tool_regex_20251119: object` - `type: "tool_search_tool_regex_20251119" or "tool_search_tool_regex"` - `"tool_search_tool_regex_20251119"` - `"tool_search_tool_regex"` - `name: "tool_search_tool_regex"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_mcp_toolset: object` Configuration for a group of tools from an MCP server. Allows configuring enabled status and defer_loading for all tools from an MCP server, with optional per-tool overrides. - `type: "mcp_toolset"` - `mcp_server_name: string` Name of the MCP server to configure tools for minLength: 1, maxLength: 255 - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `configs: optional map[BetaMCPToolConfig]` Configuration overrides for specific tools, keyed by tool name - `defer_loading: optional boolean` - `enabled: optional boolean` - `default_config: optional object` Default configuration applied to all tools from this server - `defer_loading: optional boolean` - `enabled: optional boolean` - `tools: optional array of BetaMCPToolParam` The server's tool listing, pinned: when present, the server is not asked for its tools before sampling and exactly these entries, with `default_config` and `configs` applied, are the toolset's tools. Copy it from the `mcp_tool_listing` block of an earlier response. - `input_schema: map[unknown]` The tool's input schema as the MCP server lists it, verbatim. - `name: string` The tool's name as the MCP server lists it (not prefixed with the server name). minLength: 1 - `description: optional string` The tool's description as the MCP server lists it. ### Beta Tool Change Tool Definition Param - `beta_tool_change_tool_definition_param: object` A tool defined by value: `definition` is a `tools` entry (any kind `tools` accepts, an MCP toolset included). An `mcp_toolset` given here also requires the `mcp-client-2026-09-15` beta. - `type: "tool_definition"` - `definition: BetaTool or BetaToolBash20241022 or BetaToolBash20250124 or 25 more` - `beta_tool: object` - `type: optional "custom"` - `input_schema: object` [JSON schema](https://json-schema.org/draft/2020-12) for this tool's input. This defines the shape of the `input` that your tool accepts and that the model will produce. - `type: "object"` - `properties: optional map[unknown]` - `required: optional array of string` - `name: string` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. minLength: 1, maxLength: 128, pattern: ^[a-zA-Z0-9_-]{1,128}$ - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `"5m"` - `"1h"` - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `description: optional string` Description of what this tool does. Tool descriptions should be as detailed as possible. The more information that the model has about what the tool is and how to use it, the better it will perform. You can use natural language descriptions to reinforce important aspects of the tool input JSON schema. - `eager_input_streaming: optional boolean` Enable eager input streaming for this tool. When true, tool input parameters will be streamed incrementally as they are generated, and types will be inferred on-the-fly rather than buffering the full JSON output. When false, streaming is disabled for this tool even if the fine-grained-tool-streaming beta is active. When null (default), uses the default behavior based on beta headers. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_bash_20241022: object` - `type: "bash_20241022"` - `name: "bash"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_bash_20250124: object` - `type: "bash_20250124"` - `name: "bash"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_code_execution_tool_20250522: object` - `type: "code_execution_20250522"` - `name: "code_execution"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_code_execution_tool_20250825: object` - `type: "code_execution_20250825"` - `name: "code_execution"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_code_execution_tool_20260120: object` Code execution tool with REPL state persistence (daemon mode + gVisor checkpoint). - `type: "code_execution_20260120"` - `name: "code_execution"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_code_execution_tool_20260521: object` Code execution tool with REPL state persistence. - `type: "code_execution_20260521"` - `name: "code_execution"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_browser_toolset_20260801: object` The browser toolset: a single `tools[]` entry (carrying no `name`) that declares the browser tool family. The model is served the family's tool with any members disabled via `configs` removed from its schema. - `type: "browser_toolset_20260801"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `configs: optional object` Sparse per-member overrides, keyed by member name. Absent, null, and {} are equivalent; a member's defaults apply wherever its key is absent. - `type: optional object` `type`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `close_tab: optional object` `close_tab`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `double_click: optional object` `double_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `file_upload: optional object` `file_upload`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `find: optional object` `find`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `form_input: optional object` `form_input`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `get_page_text: optional object` `get_page_text`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `hold_key: optional object` `hold_key`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `hover: optional object` `hover`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `javascript_exec: optional object` `javascript_exec`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `key: optional object` `key`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_click: optional object` `left_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_click_drag: optional object` `left_click_drag`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_mouse_down: optional object` `left_mouse_down`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_mouse_up: optional object` `left_mouse_up`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `list_tabs: optional object` `list_tabs`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `middle_click: optional object` `middle_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `mouse_move: optional object` `mouse_move`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `navigate: optional object` `navigate`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `new_tab: optional object` `new_tab`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `read_console: optional object` `read_console`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `read_network: optional object` `read_network`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `read_page: optional object` `read_page`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `right_click: optional object` `right_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `screenshot: optional object` `screenshot`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `scroll: optional object` `scroll`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `scroll_to: optional object` `scroll_to`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `switch_tab: optional object` `switch_tab`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `triple_click: optional object` `triple_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `wait: optional object` `wait`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `zoom: optional object` `zoom`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `beta_tool_computer_use_20241022: object` - `type: "computer_20241022"` - `display_height_px: number` The height of the display in pixels. minimum: 1 - `display_width_px: number` The width of the display in pixels. minimum: 1 - `name: "computer"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `display_number: optional number` The X11 display number (e.g. 0, 1) for the display. minimum: 0 - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_memory_tool_20250818: object` - `type: "memory_20250818"` - `name: "memory"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_computer_use_20250124: object` - `type: "computer_20250124"` - `display_height_px: number` The height of the display in pixels. minimum: 1 - `display_width_px: number` The width of the display in pixels. minimum: 1 - `name: "computer"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `display_number: optional number` The X11 display number (e.g. 0, 1) for the display. minimum: 0 - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_text_editor_20241022: object` - `type: "text_editor_20241022"` - `name: "str_replace_editor"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_computer_use_20251124: object` - `type: "computer_20251124"` - `display_height_px: number` The height of the display in pixels. minimum: 1 - `display_width_px: number` The width of the display in pixels. minimum: 1 - `name: "computer"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `display_number: optional number` The X11 display number (e.g. 0, 1) for the display. minimum: 0 - `enable_zoom: optional boolean` Whether to enable an action to take a zoomed-in screenshot of the screen. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_computer_toolset_20260801: object` The computer toolset: a single `tools[]` entry (carrying no `name`) that declares the computer tool family. The model is served the family's tool with any members disabled via `configs` removed from its schema. Every member is enabled by default, zoom included. The single-tool options `display_number` and `enable_zoom` are not fields of a toolset entry — it carries only `type`, `configs`, and `cache_control`; zoom is controlled via `configs.zoom.enabled`. - `type: "computer_toolset_20260801"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `configs: optional object` Sparse per-member overrides, keyed by member name. Absent, null, and {} are equivalent; a member's defaults apply wherever its key is absent. - `type: optional object` `type`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `cursor_position: optional object` `cursor_position`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `double_click: optional object` `double_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `hold_key: optional object` `hold_key`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `key: optional object` `key`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_click: optional object` `left_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_click_drag: optional object` `left_click_drag`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_mouse_down: optional object` `left_mouse_down`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_mouse_up: optional object` `left_mouse_up`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `middle_click: optional object` `middle_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `mouse_move: optional object` `mouse_move`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `right_click: optional object` `right_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `screenshot: optional object` `screenshot`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `scroll: optional object` `scroll`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `triple_click: optional object` `triple_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `wait: optional object` `wait`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `zoom: optional object` `zoom`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `beta_tool_text_editor_20250124: object` - `type: "text_editor_20250124"` - `name: "str_replace_editor"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_text_editor_20250429: object` - `type: "text_editor_20250429"` - `name: "str_replace_based_edit_tool"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_text_editor_20250728: object` - `type: "text_editor_20250728"` - `name: "str_replace_based_edit_tool"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: optional array of map[unknown]` - `max_characters: optional number` Maximum number of characters to display when viewing a file. If not specified, defaults to displaying the full file. minimum: 1 - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_web_search_tool_20250305: object` - `type: "web_search_20250305"` - `name: "web_search"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: optional array of string` If provided, only these domains will be included in results. Cannot be used alongside `blocked_domains`. - `blocked_domains: optional array of string` If provided, these domains will never appear in results. Cannot be used alongside `allowed_domains`. - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `user_location: optional object` Parameters for the user's location. Used to provide more relevant search results. - `type: "approximate"` - `city: optional string` The city of the user. minLength: 1, maxLength: 255 - `country: optional string` The two letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1_alpha-2) of the user. minLength: 2, maxLength: 2 - `region: optional string` The region of the user. minLength: 1, maxLength: 255 - `timezone: optional string` The [IANA timezone](https://nodatime.org/TimeZones) of the user. minLength: 1, maxLength: 255 - `beta_web_fetch_tool_20250910: object` - `type: "web_fetch_20250910"` - `name: "web_fetch"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: optional array of string` List of domains to allow fetching from - `blocked_domains: optional array of string` List of domains to block fetching from - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `citations: optional object` Citations configuration for fetched documents. Citations are disabled by default. - `enabled: optional boolean` - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_content_tokens: optional number` Maximum number of tokens used by including web page text content in the context. The limit is approximate and does not apply to binary content such as PDFs. minimum: 1 - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `url_sources: optional object` Which sources contribute to the set of URLs the tool may fetch. Omitted means every source. - `client_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which client tools' results contribute fetchable URLs: "all", "none", or an only or except list of client tool names from tools[]. - `beta_web_fetch_url_source_all: object` The `url_sources` variant under which a source contributes in full: every result of the tool filter's source, or all user input. - `type: "all"` - `beta_web_fetch_url_source_none: object` The `url_sources` variant under which a source contributes nothing: no result of the tool filter's source, or no user input. - `type: "none"` - `beta_web_fetch_url_source_only: object` The tool filter variant under which only the named tools' results contribute. - `type: "only"` - `tools: array of BetaWebFetchURLSourceToolReference` - `type: "tool_reference"` - `name: string` - `beta_web_fetch_url_source_except: object` The tool filter variant under which every result but the named tools' contributes. - `type: "except"` - `tools: array of BetaWebFetchURLSourceToolReference` - `type: "tool_reference"` - `name: string` - `server_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which server tools' results contribute fetchable URLs: "all", "none", or an only or except list of server tool names from tools[]; only web_search and web_fetch results ever contribute. - `beta_web_fetch_url_source_all: object` The `url_sources` variant under which a source contributes in full: every result of the tool filter's source, or all user input. - `beta_web_fetch_url_source_none: object` The `url_sources` variant under which a source contributes nothing: no result of the tool filter's source, or no user input. - `beta_web_fetch_url_source_only: object` The tool filter variant under which only the named tools' results contribute. - `beta_web_fetch_url_source_except: object` The tool filter variant under which every result but the named tools' contributes. - `user_input: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone` Whether URLs in user messages are fetchable: "all" or "none". - `beta_web_fetch_url_source_all: object` The `url_sources` variant under which a source contributes in full: every result of the tool filter's source, or all user input. - `beta_web_fetch_url_source_none: object` The `url_sources` variant under which a source contributes nothing: no result of the tool filter's source, or no user input. - `beta_web_search_tool_20260209: object` - `type: "web_search_20260209"` - `name: "web_search"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: optional array of string` If provided, only these domains will be included in results. Cannot be used alongside `blocked_domains`. - `blocked_domains: optional array of string` If provided, these domains will never appear in results. Cannot be used alongside `allowed_domains`. - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `user_location: optional object` Parameters for the user's location. Used to provide more relevant search results. - `type: "approximate"` - `city: optional string` The city of the user. minLength: 1, maxLength: 255 - `country: optional string` The two letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1_alpha-2) of the user. minLength: 2, maxLength: 2 - `region: optional string` The region of the user. minLength: 1, maxLength: 255 - `timezone: optional string` The [IANA timezone](https://nodatime.org/TimeZones) of the user. minLength: 1, maxLength: 255 - `beta_web_fetch_tool_20260209: object` - `type: "web_fetch_20260209"` - `name: "web_fetch"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: optional array of string` List of domains to allow fetching from - `blocked_domains: optional array of string` List of domains to block fetching from - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `citations: optional object` Citations configuration for fetched documents. Citations are disabled by default. - `enabled: optional boolean` - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_content_tokens: optional number` Maximum number of tokens used by including web page text content in the context. The limit is approximate and does not apply to binary content such as PDFs. minimum: 1 - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `url_sources: optional object` Which sources contribute to the set of URLs the tool may fetch. Omitted means every source. - `client_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which client tools' results contribute fetchable URLs: "all", "none", or an only or except list of client tool names from tools[]. - `server_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which server tools' results contribute fetchable URLs: "all", "none", or an only or except list of server tool names from tools[]; only web_search and web_fetch results ever contribute. - `user_input: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone` Whether URLs in user messages are fetchable: "all" or "none". - `beta_web_fetch_tool_20260309: object` Web fetch tool with use_cache parameter for bypassing cached content. - `type: "web_fetch_20260309"` - `name: "web_fetch"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: optional array of string` List of domains to allow fetching from - `blocked_domains: optional array of string` List of domains to block fetching from - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `citations: optional object` Citations configuration for fetched documents. Citations are disabled by default. - `enabled: optional boolean` - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_content_tokens: optional number` Maximum number of tokens used by including web page text content in the context. The limit is approximate and does not apply to binary content such as PDFs. minimum: 1 - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `url_sources: optional object` Which sources contribute to the set of URLs the tool may fetch. Omitted means every source. - `client_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which client tools' results contribute fetchable URLs: "all", "none", or an only or except list of client tool names from tools[]. - `server_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which server tools' results contribute fetchable URLs: "all", "none", or an only or except list of server tool names from tools[]; only web_search and web_fetch results ever contribute. - `user_input: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone` Whether URLs in user messages are fetchable: "all" or "none". - `use_cache: optional boolean` Whether to use cached content. Set to false to bypass the cache and fetch fresh content. Only set to false when the user explicitly requests fresh content or when fetching rapidly-changing sources. - `beta_web_search_tool_20260318: object` - `type: "web_search_20260318"` - `name: "web_search"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: optional array of string` If provided, only these domains will be included in results. Cannot be used alongside `blocked_domains`. - `blocked_domains: optional array of string` If provided, these domains will never appear in results. Cannot be used alongside `allowed_domains`. - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `response_inclusion: optional "full" or "excluded"` How this tool's result blocks appear in the API response when the result was consumed by a completed code_execution call in the same turn. 'full' returns the complete content (default). 'excluded' drops the nested server_tool_use and result block pair entirely. Results from direct calls, or from code_execution calls that paused before completing, are always returned in full so they can be sent back on the next turn. - `"full"` - `"excluded"` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `user_location: optional object` Parameters for the user's location. Used to provide more relevant search results. - `type: "approximate"` - `city: optional string` The city of the user. minLength: 1, maxLength: 255 - `country: optional string` The two letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1_alpha-2) of the user. minLength: 2, maxLength: 2 - `region: optional string` The region of the user. minLength: 1, maxLength: 255 - `timezone: optional string` The [IANA timezone](https://nodatime.org/TimeZones) of the user. minLength: 1, maxLength: 255 - `beta_web_fetch_tool_20260318: object` - `type: "web_fetch_20260318"` - `name: "web_fetch"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: optional array of string` List of domains to allow fetching from - `blocked_domains: optional array of string` List of domains to block fetching from - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `citations: optional object` Citations configuration for fetched documents. Citations are disabled by default. - `enabled: optional boolean` - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_content_tokens: optional number` Maximum number of tokens used by including web page text content in the context. The limit is approximate and does not apply to binary content such as PDFs. minimum: 1 - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `response_inclusion: optional "full" or "excluded"` How this tool's result blocks appear in the API response when the result was consumed by a completed code_execution call in the same turn. 'full' returns the complete content (default). 'excluded' drops the nested server_tool_use and result block pair entirely. Results from direct calls, or from code_execution calls that paused before completing, are always returned in full so they can be sent back on the next turn. - `"full"` - `"excluded"` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `url_sources: optional object` Which sources contribute to the set of URLs the tool may fetch. Omitted means every source. - `client_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which client tools' results contribute fetchable URLs: "all", "none", or an only or except list of client tool names from tools[]. - `server_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which server tools' results contribute fetchable URLs: "all", "none", or an only or except list of server tool names from tools[]; only web_search and web_fetch results ever contribute. - `user_input: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone` Whether URLs in user messages are fetchable: "all" or "none". - `use_cache: optional boolean` Whether to use cached content. Set to false to bypass the cache and fetch fresh content. Only set to false when the user explicitly requests fresh content or when fetching rapidly-changing sources. - `beta_advisor_tool_20260301: object` - `type: "advisor_20260301"` - `model: "claude-haiku-5-5" or "claude-sonnet-5-5" or "claude-fable-5-1" or 17 more or string` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-haiku-5-5"` Fastest model for high-volume, real-time tasks - `"claude-sonnet-5-5"` Efficient model for coding and agents - `"claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows - `"claude-opus-5-5"` Powerful intelligence for coding, knowledge work, and long-running agents - `"claude-mythos-5-1"` Our most capable model for cybersecurity and biology research, available through trusted access programs - `"claude-sonnet-5"` Efficient model for coding and agents - `"claude-fable-5"` Next generation of intelligence for the hardest knowledge work and coding problems - `"claude-mythos-5"` Most capable model for cybersecurity and biology research - `"claude-opus-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-8"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-7"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-6"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-6"` Best combination of speed and intelligence - `"claude-haiku-4-5"` - `"claude-haiku-4-5-20251001"` - `"claude-opus-4-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-5-20251101"` Powerful intelligence for long-running agents and coding - `"claude-mythos-preview"` **Deprecated**: Will reach end-of-life on June 30, 2026. Please migrate to claude-mythos-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. New class of intelligence, strongest in coding and cybersecurity - `"claude-sonnet-4-5"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `"claude-sonnet-4-5-20250929"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `name: "advisor"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `caching: optional object` Caching for the advisor's own prompt. When set, each advisor call writes a cache entry at the given TTL so subsequent calls in the same conversation read the stable prefix. When omitted, the advisor prompt is not cached. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_tokens: optional number` Bounds the advisor's total output (thinking + text) per call. When the advisor hits this cap, the returned advisor_result or advisor_redacted_result block carries stop_reason='max_tokens', and a truncation note is appended to the advice text the worker model sees (inside the encrypted blob in redacted mode). When set, the server also emits a remaining-tokens budget block in the advisor's prompt so the advisor self-shapes toward the cap. When omitted, the advisor model's default output cap applies and no budget block is emitted. minimum: 1024 - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_search_tool_bm25_20251119: object` - `type: "tool_search_tool_bm25_20251119" or "tool_search_tool_bm25"` - `"tool_search_tool_bm25_20251119"` - `"tool_search_tool_bm25"` - `name: "tool_search_tool_bm25"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_search_tool_regex_20251119: object` - `type: "tool_search_tool_regex_20251119" or "tool_search_tool_regex"` - `"tool_search_tool_regex_20251119"` - `"tool_search_tool_regex"` - `name: "tool_search_tool_regex"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_mcp_toolset: object` Configuration for a group of tools from an MCP server. Allows configuring enabled status and defer_loading for all tools from an MCP server, with optional per-tool overrides. - `type: "mcp_toolset"` - `mcp_server_name: string` Name of the MCP server to configure tools for minLength: 1, maxLength: 255 - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `configs: optional map[BetaMCPToolConfig]` Configuration overrides for specific tools, keyed by tool name - `defer_loading: optional boolean` - `enabled: optional boolean` - `default_config: optional object` Default configuration applied to all tools from this server - `defer_loading: optional boolean` - `enabled: optional boolean` - `tools: optional array of BetaMCPToolParam` The server's tool listing, pinned: when present, the server is not asked for its tools before sampling and exactly these entries, with `default_config` and `configs` applied, are the toolset's tools. Copy it from the `mcp_tool_listing` block of an earlier response. - `input_schema: map[unknown]` The tool's input schema as the MCP server lists it, verbatim. - `name: string` The tool's name as the MCP server lists it (not prefixed with the server name). minLength: 1 - `description: optional string` The tool's description as the MCP server lists it. ### Beta Tool Change Tool Reference - `beta_tool_change_tool_reference: object` Reference to a single tool, by the name the model uses to call it: a tool declared in `tools` or defined by an earlier `tool_addition` block. Does not accept the composed `{server}_{name}` form the server assigns to MCP-resolved tools; use `mcp_tool_reference` or `mcp_toolset_reference` for those. - `type: "tool_reference"` - `name: string` pattern: ^[a-zA-Z0-9_-]{1,128}$ ### Beta Tool Choice - `beta_tool_choice: BetaToolChoiceAuto or BetaToolChoiceAny or BetaToolChoiceTool or BetaToolChoiceNone` How the model should use the provided tools. The model can use a specific tool, any available tool, decide by itself, or not use tools at all. - `beta_tool_choice_auto: object` The model will automatically decide whether to use tools. - `type: "auto"` - `disable_parallel_tool_use: optional boolean` Whether to disable parallel tool use. Defaults to `false`. If set to `true`, the model will output at most one tool use. - `beta_tool_choice_any: object` The model will use any available tools. - `type: "any"` - `disable_parallel_tool_use: optional boolean` Whether to disable parallel tool use. Defaults to `false`. If set to `true`, the model will output exactly one tool use. - `beta_tool_choice_tool: object` The model will use the specified tool with `tool_choice.name`. - `type: "tool"` - `name: string` The name of the tool to use. - `disable_parallel_tool_use: optional boolean` Whether to disable parallel tool use. Defaults to `false`. If set to `true`, the model will output exactly one tool use. - `beta_tool_choice_none: object` The model will not be allowed to use tools. - `type: "none"` ### Beta Tool Choice Any - `beta_tool_choice_any: object` The model will use any available tools. - `type: "any"` - `disable_parallel_tool_use: optional boolean` Whether to disable parallel tool use. Defaults to `false`. If set to `true`, the model will output exactly one tool use. ### Beta Tool Choice Auto - `beta_tool_choice_auto: object` The model will automatically decide whether to use tools. - `type: "auto"` - `disable_parallel_tool_use: optional boolean` Whether to disable parallel tool use. Defaults to `false`. If set to `true`, the model will output at most one tool use. ### Beta Tool Choice None - `beta_tool_choice_none: object` The model will not be allowed to use tools. - `type: "none"` ### Beta Tool Choice Tool - `beta_tool_choice_tool: object` The model will use the specified tool with `tool_choice.name`. - `type: "tool"` - `name: string` The name of the tool to use. - `disable_parallel_tool_use: optional boolean` Whether to disable parallel tool use. Defaults to `false`. If set to `true`, the model will output exactly one tool use. ### Beta Tool Computer Use 20241022 - `beta_tool_computer_use_20241022: object` - `type: "computer_20241022"` - `display_height_px: number` The height of the display in pixels. minimum: 1 - `display_width_px: number` The width of the display in pixels. minimum: 1 - `name: "computer"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `"5m"` - `"1h"` - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `display_number: optional number` The X11 display number (e.g. 0, 1) for the display. minimum: 0 - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs ### Beta Tool Computer Use 20250124 - `beta_tool_computer_use_20250124: object` - `type: "computer_20250124"` - `display_height_px: number` The height of the display in pixels. minimum: 1 - `display_width_px: number` The width of the display in pixels. minimum: 1 - `name: "computer"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `"5m"` - `"1h"` - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `display_number: optional number` The X11 display number (e.g. 0, 1) for the display. minimum: 0 - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs ### Beta Tool Computer Use 20251124 - `beta_tool_computer_use_20251124: object` - `type: "computer_20251124"` - `display_height_px: number` The height of the display in pixels. minimum: 1 - `display_width_px: number` The width of the display in pixels. minimum: 1 - `name: "computer"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `"5m"` - `"1h"` - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `display_number: optional number` The X11 display number (e.g. 0, 1) for the display. minimum: 0 - `enable_zoom: optional boolean` Whether to enable an action to take a zoomed-in screenshot of the screen. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs ### Beta Tool Reference Block - `beta_tool_reference_block: object` - `type: "tool_reference"` - `tool_name: string` minLength: 1, maxLength: 256, pattern: ^[a-zA-Z0-9_-]{1,256}$ ### Beta Tool Reference Block Param - `beta_tool_reference_block_param: object` Tool reference block that can be included in tool_result content. - `type: "tool_reference"` - `tool_name: string` minLength: 1, maxLength: 256, pattern: ^[a-zA-Z0-9_-]{1,256}$ - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `"5m"` - `"1h"` ### Beta Tool Result Block Param - `beta_tool_result_block_param: object` - `type: "tool_result"` - `tool_use_id: string` pattern: ^[a-zA-Z0-9_-]+$ - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `"5m"` - `"1h"` - `content: optional array of BetaTextBlockParam or BetaImageBlockParam or BetaSearchResultBlockParam or 3 more` - `beta_text_block_param: object` - `type: "text"` - `text: string` minLength: 1 - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `citations: optional array of BetaTextCitationParam` - `beta_citation_char_location_param: object` - `type: "char_location"` - `cited_text: string` - `document_index: number` minimum: 0 - `document_title: string` minLength: 1, maxLength: 500 - `end_char_index: number` - `start_char_index: number` minimum: 0 - `beta_citation_page_location_param: object` - `type: "page_location"` - `cited_text: string` - `document_index: number` minimum: 0 - `document_title: string` minLength: 1, maxLength: 500 - `end_page_number: number` - `start_page_number: number` minimum: 1 - `beta_citation_content_block_location_param: object` - `type: "content_block_location"` - `cited_text: string` The full text of the cited block range, concatenated. Always equals the contents of `content[start_block_index:end_block_index]` joined together. The text block is the minimal citable unit; this field is never a substring of a single block. Not counted toward output tokens, and not counted toward input tokens when sent back in subsequent turns. - `document_index: number` minimum: 0 - `document_title: string` minLength: 1, maxLength: 500 - `end_block_index: number` Exclusive 0-based end index of the cited block range in the source's `content` array. Always greater than `start_block_index`; a single-block citation has `end_block_index = start_block_index + 1`. - `start_block_index: number` 0-based index of the first cited block in the source's `content` array. minimum: 0 - `beta_citation_web_search_result_location_param: object` - `type: "web_search_result_location"` - `cited_text: string` - `encrypted_index: string` - `title: string` minLength: 1, maxLength: 512 - `url: string` minLength: 1 - `beta_citation_search_result_location_param: object` - `type: "search_result_location"` - `cited_text: string` The full text of the cited block range, concatenated. Always equals the contents of `content[start_block_index:end_block_index]` joined together. The text block is the minimal citable unit; this field is never a substring of a single block. Not counted toward output tokens, and not counted toward input tokens when sent back in subsequent turns. - `end_block_index: number` Exclusive 0-based end index of the cited block range in the source's `content` array. Always greater than `start_block_index`; a single-block citation has `end_block_index = start_block_index + 1`. - `search_result_index: number` 0-based index of the cited search result among all `search_result` content blocks in the request, in the order they appear across messages and tool results. Counted separately from `document_index`; server-side web search results are not included in this count. minimum: 0 - `source: string` - `start_block_index: number` 0-based index of the first cited block in the source's `content` array. minimum: 0 - `title: string` - `beta_image_block_param: object` - `type: "image"` - `source: BetaBase64ImageSource or BetaURLImageSource or BetaFileImageSource` - `beta_base64_image_source: object` - `type: "base64"` - `data: string` format: byte - `media_type: "image/jpeg" or "image/png" or "image/gif" or "image/webp"` - `"image/jpeg"` - `"image/png"` - `"image/gif"` - `"image/webp"` - `beta_url_image_source: object` - `type: "url"` - `url: string` - `beta_file_image_source: object` - `type: "file"` - `file_id: string` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `transformations: optional object` Configures the transformations the server applies to this image before the model observes it. Each key names a condition the server transforms images for; its value selects the transformation applied. Omitted keys keep their default behavior, and an empty object is equivalent to omitting the field. - `oversized_image: optional "downsize" or "error"` What the server does when this image exceeds the model's maximum image size. `"downsize"` (the default) scales the image down to fit, which changes the dimensions the model observes without telling you. `"error"` instead rejects the request with a 400 error naming the image's dimensions and the largest dimensions that fit, so you can scale the image deliberately — your image is never silently scaled down. - `"downsize"` - `"error"` - `beta_search_result_block_param: object` - `type: "search_result"` - `content: array of BetaTextBlockParam` - `type: "text"` - `text: string` minLength: 1 - `cache_control: optional object` Create a cache control breakpoint at this content block. - `citations: optional array of BetaTextCitationParam` - `source: string` - `title: string` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `citations: optional object` - `enabled: optional boolean` - `beta_request_document_block: object` - `type: "document"` - `source: BetaBase64PDFSource or BetaPlainTextSource or BetaContentBlockSource or 2 more` - `beta_base64_pdf_source: object` - `type: "base64"` - `data: string` format: byte - `media_type: "application/pdf"` - `beta_plain_text_source: object` - `type: "text"` - `data: string` - `media_type: "text/plain"` - `beta_content_block_source: object` - `type: "content"` - `content: string or array of BetaContentBlockSourceContent` - `union_member_0: string` - `beta_content_block_source_content: array of BetaContentBlockSourceContent` - `beta_text_block_param: object` - `type: "text"` - `text: string` minLength: 1 - `cache_control: optional object` Create a cache control breakpoint at this content block. - `citations: optional array of BetaTextCitationParam` - `beta_image_block_param: object` - `type: "image"` - `source: BetaBase64ImageSource or BetaURLImageSource or BetaFileImageSource` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `transformations: optional object` Configures the transformations the server applies to this image before the model observes it. Each key names a condition the server transforms images for; its value selects the transformation applied. Omitted keys keep their default behavior, and an empty object is equivalent to omitting the field. - `beta_url_pdf_source: object` - `type: "url"` - `url: string` - `beta_file_document_source: object` - `type: "file"` - `file_id: string` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `citations: optional object` - `enabled: optional boolean` - `context: optional string` minLength: 1 - `title: optional string` minLength: 1, maxLength: 500 - `beta_tool_reference_block_param: object` Tool reference block that can be included in tool_result content. - `type: "tool_reference"` - `tool_name: string` minLength: 1, maxLength: 256, pattern: ^[a-zA-Z0-9_-]{1,256}$ - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `beta_browser_state_block_param: object` The caller's browser state after a browser toolset member call — the full inventory of open tabs, which tab is active, and any side effects (tabs opened, download state changes) the call produced. At most one per `tool_result`, only on a non-error result answering a browser toolset member `tool_use`. The server renders the model-visible text from it; the model never sees the raw fields. - `type: "browser_state"` - `tabs: array of BetaBrowserStateTabEntry` All tabs open in the browser after this call — the full inventory, not a delta. May be empty. Whenever non-empty, exactly one entry carries `active: true`. maxItems: 100 - `tab_id: string` The caller-assigned identifier for this tab, unique within the inventory. minLength: 1, maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `title: string` The title of the page the tab is showing. May be empty. maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `url: string` The URL of the page the tab is showing. May be empty. maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `active: optional boolean` Whether this tab is the active tab after this call. Whenever `tabs` is non-empty, exactly one entry is marked `active: true`. - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `state_changes: optional array of BetaBrowserStateChange` Tabs opened and download state changes during this call. "Nothing to report" is expressed by omitting the field, never by an empty list. minItems: 1, maxItems: 200 - `beta_browser_state_change_tab_opened: object` A tab this call's execution opened that remains open at its end — the creation delta of the `tabs` inventory, not an event log. Carries only the `tab_id`; the tab's `title` and `url` live on its `tabs` entry, which must include the same `tab_id`. A tab opened during a failed call gets no deferred `tab_opened`; it simply appears in the next result's `tabs` inventory. - `type: "tab_opened"` - `tab_id: string` The `tab_id` of the opened tab, present in `tabs`. minLength: 1, maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `beta_browser_state_change_download_started: object` A file download that started during this call. - `type: "download_started"` - `download_id: string` The caller-assigned identifier for this download, stable across the state changes reporting it. minLength: 1, maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `url: string` The final post-redirect URL the download was served from. maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `beta_browser_state_change_download_completed: object` A file download that finished during this call, reported with the same `download_id` as its `download_started` — or without a prior `download_started`, when the download finished during the call that started it (at most one state change per `download_id` per result). - `type: "download_completed"` - `download_id: string` The caller-assigned identifier for this download, stable across the state changes reporting it. minLength: 1, maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `url: string` The final post-redirect URL the download was served from. maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `path: optional string` Where the executor saved the file, on the executor's filesystem. Only included when another tool in the same environment can read the file at that path. maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `size_bytes: optional number` The completed download's size. minimum: 0 - `beta_browser_state_change_download_failed: object` A file download that failed — or was cancelled — during this call. - `type: "download_failed"` - `download_id: string` The caller-assigned identifier for this download, stable across the state changes reporting it. minLength: 1, maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `url: string` The final post-redirect URL the download was served from. maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `error: optional string` The failure or cancellation detail, when known. maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `is_error: optional boolean` - `toolset_name: optional string` For a toolset member tool_result, the toolset family of the paired tool_use. minLength: 1, maxLength: 64, pattern: ^[a-zA-Z0-9_-]+$ ### Beta Tool Search Tool Bm25 20251119 - `beta_tool_search_tool_bm25_20251119: object` - `type: "tool_search_tool_bm25_20251119" or "tool_search_tool_bm25"` - `"tool_search_tool_bm25_20251119"` - `"tool_search_tool_bm25"` - `name: "tool_search_tool_bm25"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `"5m"` - `"1h"` - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs ### Beta Tool Search Tool Regex 20251119 - `beta_tool_search_tool_regex_20251119: object` - `type: "tool_search_tool_regex_20251119" or "tool_search_tool_regex"` - `"tool_search_tool_regex_20251119"` - `"tool_search_tool_regex"` - `name: "tool_search_tool_regex"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `"5m"` - `"1h"` - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs ### Beta Tool Search Tool Result Block - `beta_tool_search_tool_result_block: object` - `type: "tool_search_tool_result"` - `content: BetaToolSearchToolResultError or BetaToolSearchToolSearchResultBlock` - `beta_tool_search_tool_result_error: object` - `type: "tool_search_tool_result_error"` - `error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or "execution_time_exceeded"` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `error_message: string` - `beta_tool_search_tool_search_result_block: object` - `type: "tool_search_tool_search_result"` - `tool_references: array of BetaToolReferenceBlock` - `type: "tool_reference"` - `tool_name: string` minLength: 1, maxLength: 256, pattern: ^[a-zA-Z0-9_-]{1,256}$ - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ ### Beta Tool Search Tool Result Block Param - `beta_tool_search_tool_result_block_param: object` - `type: "tool_search_tool_result"` - `content: BetaToolSearchToolResultErrorParam or BetaToolSearchToolSearchResultBlockParam` - `beta_tool_search_tool_result_error_param: object` - `type: "tool_search_tool_result_error"` - `error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or "execution_time_exceeded"` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `error_message: optional string` - `beta_tool_search_tool_search_result_block_param: object` - `type: "tool_search_tool_search_result"` - `tool_references: array of BetaToolReferenceBlockParam` - `type: "tool_reference"` - `tool_name: string` minLength: 1, maxLength: 256, pattern: ^[a-zA-Z0-9_-]{1,256}$ - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `"5m"` - `"1h"` - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. ### Beta Tool Search Tool Result Error - `beta_tool_search_tool_result_error: object` - `type: "tool_search_tool_result_error"` - `error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or "execution_time_exceeded"` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `error_message: string` ### Beta Tool Search Tool Result Error Param - `beta_tool_search_tool_result_error_param: object` - `type: "tool_search_tool_result_error"` - `error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or "execution_time_exceeded"` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `error_message: optional string` ### Beta Tool Search Tool Search Result Block - `beta_tool_search_tool_search_result_block: object` - `type: "tool_search_tool_search_result"` - `tool_references: array of BetaToolReferenceBlock` - `type: "tool_reference"` - `tool_name: string` minLength: 1, maxLength: 256, pattern: ^[a-zA-Z0-9_-]{1,256}$ ### Beta Tool Search Tool Search Result Block Param - `beta_tool_search_tool_search_result_block_param: object` - `type: "tool_search_tool_search_result"` - `tool_references: array of BetaToolReferenceBlockParam` - `type: "tool_reference"` - `tool_name: string` minLength: 1, maxLength: 256, pattern: ^[a-zA-Z0-9_-]{1,256}$ - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `"5m"` - `"1h"` ### Beta Tool Text Editor 20241022 - `beta_tool_text_editor_20241022: object` - `type: "text_editor_20241022"` - `name: "str_replace_editor"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `"5m"` - `"1h"` - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs ### Beta Tool Text Editor 20250124 - `beta_tool_text_editor_20250124: object` - `type: "text_editor_20250124"` - `name: "str_replace_editor"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `"5m"` - `"1h"` - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs ### Beta Tool Text Editor 20250429 - `beta_tool_text_editor_20250429: object` - `type: "text_editor_20250429"` - `name: "str_replace_based_edit_tool"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `"5m"` - `"1h"` - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs ### Beta Tool Text Editor 20250728 - `beta_tool_text_editor_20250728: object` - `type: "text_editor_20250728"` - `name: "str_replace_based_edit_tool"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `"5m"` - `"1h"` - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: optional array of map[unknown]` - `max_characters: optional number` Maximum number of characters to display when viewing a file. If not specified, defaults to displaying the full file. minimum: 1 - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs ### Beta Tool Union - `beta_tool_union: BetaTool or BetaToolBash20241022 or BetaToolBash20250124 or 25 more` - `beta_tool: object` - `type: optional "custom"` - `input_schema: object` [JSON schema](https://json-schema.org/draft/2020-12) for this tool's input. This defines the shape of the `input` that your tool accepts and that the model will produce. - `type: "object"` - `properties: optional map[unknown]` - `required: optional array of string` - `name: string` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. minLength: 1, maxLength: 128, pattern: ^[a-zA-Z0-9_-]{1,128}$ - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `"5m"` - `"1h"` - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `description: optional string` Description of what this tool does. Tool descriptions should be as detailed as possible. The more information that the model has about what the tool is and how to use it, the better it will perform. You can use natural language descriptions to reinforce important aspects of the tool input JSON schema. - `eager_input_streaming: optional boolean` Enable eager input streaming for this tool. When true, tool input parameters will be streamed incrementally as they are generated, and types will be inferred on-the-fly rather than buffering the full JSON output. When false, streaming is disabled for this tool even if the fine-grained-tool-streaming beta is active. When null (default), uses the default behavior based on beta headers. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_bash_20241022: object` - `type: "bash_20241022"` - `name: "bash"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_bash_20250124: object` - `type: "bash_20250124"` - `name: "bash"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_code_execution_tool_20250522: object` - `type: "code_execution_20250522"` - `name: "code_execution"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_code_execution_tool_20250825: object` - `type: "code_execution_20250825"` - `name: "code_execution"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_code_execution_tool_20260120: object` Code execution tool with REPL state persistence (daemon mode + gVisor checkpoint). - `type: "code_execution_20260120"` - `name: "code_execution"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_code_execution_tool_20260521: object` Code execution tool with REPL state persistence. - `type: "code_execution_20260521"` - `name: "code_execution"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_browser_toolset_20260801: object` The browser toolset: a single `tools[]` entry (carrying no `name`) that declares the browser tool family. The model is served the family's tool with any members disabled via `configs` removed from its schema. - `type: "browser_toolset_20260801"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `configs: optional object` Sparse per-member overrides, keyed by member name. Absent, null, and {} are equivalent; a member's defaults apply wherever its key is absent. - `type: optional object` `type`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `close_tab: optional object` `close_tab`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `double_click: optional object` `double_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `file_upload: optional object` `file_upload`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `find: optional object` `find`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `form_input: optional object` `form_input`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `get_page_text: optional object` `get_page_text`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `hold_key: optional object` `hold_key`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `hover: optional object` `hover`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `javascript_exec: optional object` `javascript_exec`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `key: optional object` `key`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_click: optional object` `left_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_click_drag: optional object` `left_click_drag`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_mouse_down: optional object` `left_mouse_down`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_mouse_up: optional object` `left_mouse_up`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `list_tabs: optional object` `list_tabs`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `middle_click: optional object` `middle_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `mouse_move: optional object` `mouse_move`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `navigate: optional object` `navigate`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `new_tab: optional object` `new_tab`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `read_console: optional object` `read_console`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `read_network: optional object` `read_network`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `read_page: optional object` `read_page`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `right_click: optional object` `right_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `screenshot: optional object` `screenshot`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `scroll: optional object` `scroll`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `scroll_to: optional object` `scroll_to`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `switch_tab: optional object` `switch_tab`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `triple_click: optional object` `triple_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `wait: optional object` `wait`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `zoom: optional object` `zoom`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `beta_tool_computer_use_20241022: object` - `type: "computer_20241022"` - `display_height_px: number` The height of the display in pixels. minimum: 1 - `display_width_px: number` The width of the display in pixels. minimum: 1 - `name: "computer"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `display_number: optional number` The X11 display number (e.g. 0, 1) for the display. minimum: 0 - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_memory_tool_20250818: object` - `type: "memory_20250818"` - `name: "memory"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_computer_use_20250124: object` - `type: "computer_20250124"` - `display_height_px: number` The height of the display in pixels. minimum: 1 - `display_width_px: number` The width of the display in pixels. minimum: 1 - `name: "computer"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `display_number: optional number` The X11 display number (e.g. 0, 1) for the display. minimum: 0 - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_text_editor_20241022: object` - `type: "text_editor_20241022"` - `name: "str_replace_editor"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_computer_use_20251124: object` - `type: "computer_20251124"` - `display_height_px: number` The height of the display in pixels. minimum: 1 - `display_width_px: number` The width of the display in pixels. minimum: 1 - `name: "computer"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `display_number: optional number` The X11 display number (e.g. 0, 1) for the display. minimum: 0 - `enable_zoom: optional boolean` Whether to enable an action to take a zoomed-in screenshot of the screen. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_computer_toolset_20260801: object` The computer toolset: a single `tools[]` entry (carrying no `name`) that declares the computer tool family. The model is served the family's tool with any members disabled via `configs` removed from its schema. Every member is enabled by default, zoom included. The single-tool options `display_number` and `enable_zoom` are not fields of a toolset entry — it carries only `type`, `configs`, and `cache_control`; zoom is controlled via `configs.zoom.enabled`. - `type: "computer_toolset_20260801"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `configs: optional object` Sparse per-member overrides, keyed by member name. Absent, null, and {} are equivalent; a member's defaults apply wherever its key is absent. - `type: optional object` `type`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `cursor_position: optional object` `cursor_position`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `double_click: optional object` `double_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `hold_key: optional object` `hold_key`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `key: optional object` `key`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_click: optional object` `left_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_click_drag: optional object` `left_click_drag`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_mouse_down: optional object` `left_mouse_down`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_mouse_up: optional object` `left_mouse_up`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `middle_click: optional object` `middle_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `mouse_move: optional object` `mouse_move`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `right_click: optional object` `right_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `screenshot: optional object` `screenshot`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `scroll: optional object` `scroll`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `triple_click: optional object` `triple_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `wait: optional object` `wait`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `zoom: optional object` `zoom`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `beta_tool_text_editor_20250124: object` - `type: "text_editor_20250124"` - `name: "str_replace_editor"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_text_editor_20250429: object` - `type: "text_editor_20250429"` - `name: "str_replace_based_edit_tool"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_text_editor_20250728: object` - `type: "text_editor_20250728"` - `name: "str_replace_based_edit_tool"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: optional array of map[unknown]` - `max_characters: optional number` Maximum number of characters to display when viewing a file. If not specified, defaults to displaying the full file. minimum: 1 - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_web_search_tool_20250305: object` - `type: "web_search_20250305"` - `name: "web_search"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: optional array of string` If provided, only these domains will be included in results. Cannot be used alongside `blocked_domains`. - `blocked_domains: optional array of string` If provided, these domains will never appear in results. Cannot be used alongside `allowed_domains`. - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `user_location: optional object` Parameters for the user's location. Used to provide more relevant search results. - `type: "approximate"` - `city: optional string` The city of the user. minLength: 1, maxLength: 255 - `country: optional string` The two letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1_alpha-2) of the user. minLength: 2, maxLength: 2 - `region: optional string` The region of the user. minLength: 1, maxLength: 255 - `timezone: optional string` The [IANA timezone](https://nodatime.org/TimeZones) of the user. minLength: 1, maxLength: 255 - `beta_web_fetch_tool_20250910: object` - `type: "web_fetch_20250910"` - `name: "web_fetch"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: optional array of string` List of domains to allow fetching from - `blocked_domains: optional array of string` List of domains to block fetching from - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `citations: optional object` Citations configuration for fetched documents. Citations are disabled by default. - `enabled: optional boolean` - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_content_tokens: optional number` Maximum number of tokens used by including web page text content in the context. The limit is approximate and does not apply to binary content such as PDFs. minimum: 1 - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `url_sources: optional object` Which sources contribute to the set of URLs the tool may fetch. Omitted means every source. - `client_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which client tools' results contribute fetchable URLs: "all", "none", or an only or except list of client tool names from tools[]. - `beta_web_fetch_url_source_all: object` The `url_sources` variant under which a source contributes in full: every result of the tool filter's source, or all user input. - `type: "all"` - `beta_web_fetch_url_source_none: object` The `url_sources` variant under which a source contributes nothing: no result of the tool filter's source, or no user input. - `type: "none"` - `beta_web_fetch_url_source_only: object` The tool filter variant under which only the named tools' results contribute. - `type: "only"` - `tools: array of BetaWebFetchURLSourceToolReference` - `type: "tool_reference"` - `name: string` - `beta_web_fetch_url_source_except: object` The tool filter variant under which every result but the named tools' contributes. - `type: "except"` - `tools: array of BetaWebFetchURLSourceToolReference` - `type: "tool_reference"` - `name: string` - `server_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which server tools' results contribute fetchable URLs: "all", "none", or an only or except list of server tool names from tools[]; only web_search and web_fetch results ever contribute. - `beta_web_fetch_url_source_all: object` The `url_sources` variant under which a source contributes in full: every result of the tool filter's source, or all user input. - `beta_web_fetch_url_source_none: object` The `url_sources` variant under which a source contributes nothing: no result of the tool filter's source, or no user input. - `beta_web_fetch_url_source_only: object` The tool filter variant under which only the named tools' results contribute. - `beta_web_fetch_url_source_except: object` The tool filter variant under which every result but the named tools' contributes. - `user_input: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone` Whether URLs in user messages are fetchable: "all" or "none". - `beta_web_fetch_url_source_all: object` The `url_sources` variant under which a source contributes in full: every result of the tool filter's source, or all user input. - `beta_web_fetch_url_source_none: object` The `url_sources` variant under which a source contributes nothing: no result of the tool filter's source, or no user input. - `beta_web_search_tool_20260209: object` - `type: "web_search_20260209"` - `name: "web_search"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: optional array of string` If provided, only these domains will be included in results. Cannot be used alongside `blocked_domains`. - `blocked_domains: optional array of string` If provided, these domains will never appear in results. Cannot be used alongside `allowed_domains`. - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `user_location: optional object` Parameters for the user's location. Used to provide more relevant search results. - `type: "approximate"` - `city: optional string` The city of the user. minLength: 1, maxLength: 255 - `country: optional string` The two letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1_alpha-2) of the user. minLength: 2, maxLength: 2 - `region: optional string` The region of the user. minLength: 1, maxLength: 255 - `timezone: optional string` The [IANA timezone](https://nodatime.org/TimeZones) of the user. minLength: 1, maxLength: 255 - `beta_web_fetch_tool_20260209: object` - `type: "web_fetch_20260209"` - `name: "web_fetch"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: optional array of string` List of domains to allow fetching from - `blocked_domains: optional array of string` List of domains to block fetching from - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `citations: optional object` Citations configuration for fetched documents. Citations are disabled by default. - `enabled: optional boolean` - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_content_tokens: optional number` Maximum number of tokens used by including web page text content in the context. The limit is approximate and does not apply to binary content such as PDFs. minimum: 1 - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `url_sources: optional object` Which sources contribute to the set of URLs the tool may fetch. Omitted means every source. - `client_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which client tools' results contribute fetchable URLs: "all", "none", or an only or except list of client tool names from tools[]. - `server_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which server tools' results contribute fetchable URLs: "all", "none", or an only or except list of server tool names from tools[]; only web_search and web_fetch results ever contribute. - `user_input: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone` Whether URLs in user messages are fetchable: "all" or "none". - `beta_web_fetch_tool_20260309: object` Web fetch tool with use_cache parameter for bypassing cached content. - `type: "web_fetch_20260309"` - `name: "web_fetch"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: optional array of string` List of domains to allow fetching from - `blocked_domains: optional array of string` List of domains to block fetching from - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `citations: optional object` Citations configuration for fetched documents. Citations are disabled by default. - `enabled: optional boolean` - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_content_tokens: optional number` Maximum number of tokens used by including web page text content in the context. The limit is approximate and does not apply to binary content such as PDFs. minimum: 1 - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `url_sources: optional object` Which sources contribute to the set of URLs the tool may fetch. Omitted means every source. - `client_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which client tools' results contribute fetchable URLs: "all", "none", or an only or except list of client tool names from tools[]. - `server_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which server tools' results contribute fetchable URLs: "all", "none", or an only or except list of server tool names from tools[]; only web_search and web_fetch results ever contribute. - `user_input: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone` Whether URLs in user messages are fetchable: "all" or "none". - `use_cache: optional boolean` Whether to use cached content. Set to false to bypass the cache and fetch fresh content. Only set to false when the user explicitly requests fresh content or when fetching rapidly-changing sources. - `beta_web_search_tool_20260318: object` - `type: "web_search_20260318"` - `name: "web_search"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: optional array of string` If provided, only these domains will be included in results. Cannot be used alongside `blocked_domains`. - `blocked_domains: optional array of string` If provided, these domains will never appear in results. Cannot be used alongside `allowed_domains`. - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `response_inclusion: optional "full" or "excluded"` How this tool's result blocks appear in the API response when the result was consumed by a completed code_execution call in the same turn. 'full' returns the complete content (default). 'excluded' drops the nested server_tool_use and result block pair entirely. Results from direct calls, or from code_execution calls that paused before completing, are always returned in full so they can be sent back on the next turn. - `"full"` - `"excluded"` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `user_location: optional object` Parameters for the user's location. Used to provide more relevant search results. - `type: "approximate"` - `city: optional string` The city of the user. minLength: 1, maxLength: 255 - `country: optional string` The two letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1_alpha-2) of the user. minLength: 2, maxLength: 2 - `region: optional string` The region of the user. minLength: 1, maxLength: 255 - `timezone: optional string` The [IANA timezone](https://nodatime.org/TimeZones) of the user. minLength: 1, maxLength: 255 - `beta_web_fetch_tool_20260318: object` - `type: "web_fetch_20260318"` - `name: "web_fetch"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: optional array of string` List of domains to allow fetching from - `blocked_domains: optional array of string` List of domains to block fetching from - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `citations: optional object` Citations configuration for fetched documents. Citations are disabled by default. - `enabled: optional boolean` - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_content_tokens: optional number` Maximum number of tokens used by including web page text content in the context. The limit is approximate and does not apply to binary content such as PDFs. minimum: 1 - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `response_inclusion: optional "full" or "excluded"` How this tool's result blocks appear in the API response when the result was consumed by a completed code_execution call in the same turn. 'full' returns the complete content (default). 'excluded' drops the nested server_tool_use and result block pair entirely. Results from direct calls, or from code_execution calls that paused before completing, are always returned in full so they can be sent back on the next turn. - `"full"` - `"excluded"` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `url_sources: optional object` Which sources contribute to the set of URLs the tool may fetch. Omitted means every source. - `client_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which client tools' results contribute fetchable URLs: "all", "none", or an only or except list of client tool names from tools[]. - `server_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which server tools' results contribute fetchable URLs: "all", "none", or an only or except list of server tool names from tools[]; only web_search and web_fetch results ever contribute. - `user_input: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone` Whether URLs in user messages are fetchable: "all" or "none". - `use_cache: optional boolean` Whether to use cached content. Set to false to bypass the cache and fetch fresh content. Only set to false when the user explicitly requests fresh content or when fetching rapidly-changing sources. - `beta_advisor_tool_20260301: object` - `type: "advisor_20260301"` - `model: "claude-haiku-5-5" or "claude-sonnet-5-5" or "claude-fable-5-1" or 17 more or string` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-haiku-5-5"` Fastest model for high-volume, real-time tasks - `"claude-sonnet-5-5"` Efficient model for coding and agents - `"claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows - `"claude-opus-5-5"` Powerful intelligence for coding, knowledge work, and long-running agents - `"claude-mythos-5-1"` Our most capable model for cybersecurity and biology research, available through trusted access programs - `"claude-sonnet-5"` Efficient model for coding and agents - `"claude-fable-5"` Next generation of intelligence for the hardest knowledge work and coding problems - `"claude-mythos-5"` Most capable model for cybersecurity and biology research - `"claude-opus-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-8"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-7"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-6"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-6"` Best combination of speed and intelligence - `"claude-haiku-4-5"` - `"claude-haiku-4-5-20251001"` - `"claude-opus-4-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-5-20251101"` Powerful intelligence for long-running agents and coding - `"claude-mythos-preview"` **Deprecated**: Will reach end-of-life on June 30, 2026. Please migrate to claude-mythos-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. New class of intelligence, strongest in coding and cybersecurity - `"claude-sonnet-4-5"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `"claude-sonnet-4-5-20250929"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `name: "advisor"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `caching: optional object` Caching for the advisor's own prompt. When set, each advisor call writes a cache entry at the given TTL so subsequent calls in the same conversation read the stable prefix. When omitted, the advisor prompt is not cached. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_tokens: optional number` Bounds the advisor's total output (thinking + text) per call. When the advisor hits this cap, the returned advisor_result or advisor_redacted_result block carries stop_reason='max_tokens', and a truncation note is appended to the advice text the worker model sees (inside the encrypted blob in redacted mode). When set, the server also emits a remaining-tokens budget block in the advisor's prompt so the advisor self-shapes toward the cap. When omitted, the advisor model's default output cap applies and no budget block is emitted. minimum: 1024 - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_search_tool_bm25_20251119: object` - `type: "tool_search_tool_bm25_20251119" or "tool_search_tool_bm25"` - `"tool_search_tool_bm25_20251119"` - `"tool_search_tool_bm25"` - `name: "tool_search_tool_bm25"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_search_tool_regex_20251119: object` - `type: "tool_search_tool_regex_20251119" or "tool_search_tool_regex"` - `"tool_search_tool_regex_20251119"` - `"tool_search_tool_regex"` - `name: "tool_search_tool_regex"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_mcp_toolset: object` Configuration for a group of tools from an MCP server. Allows configuring enabled status and defer_loading for all tools from an MCP server, with optional per-tool overrides. - `type: "mcp_toolset"` - `mcp_server_name: string` Name of the MCP server to configure tools for minLength: 1, maxLength: 255 - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `configs: optional map[BetaMCPToolConfig]` Configuration overrides for specific tools, keyed by tool name - `defer_loading: optional boolean` - `enabled: optional boolean` - `default_config: optional object` Default configuration applied to all tools from this server - `defer_loading: optional boolean` - `enabled: optional boolean` - `tools: optional array of BetaMCPToolParam` The server's tool listing, pinned: when present, the server is not asked for its tools before sampling and exactly these entries, with `default_config` and `configs` applied, are the toolset's tools. Copy it from the `mcp_tool_listing` block of an earlier response. - `input_schema: map[unknown]` The tool's input schema as the MCP server lists it, verbatim. - `name: string` The tool's name as the MCP server lists it (not prefixed with the server name). minLength: 1 - `description: optional string` The tool's description as the MCP server lists it. ### Beta Tool Use Block - `beta_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: map[unknown]` - `name: string` minLength: 1 - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` - `beta_direct_caller: object` Tool invocation directly from the model. - `type: "direct"` - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `type: "code_execution_20250825"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `beta_server_tool_caller_20260120: object` - `type: "code_execution_20260120"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `toolset_name: optional string` For a toolset member tool_use, the toolset family. minLength: 1, maxLength: 64, pattern: ^[a-zA-Z0-9_-]+$ ### Beta Tool Use Block Param - `beta_tool_use_block_param: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: map[unknown]` - `name: string` minLength: 1, maxLength: 200 - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `"5m"` - `"1h"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` - `beta_direct_caller: object` Tool invocation directly from the model. - `type: "direct"` - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `type: "code_execution_20250825"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `beta_server_tool_caller_20260120: object` - `type: "code_execution_20260120"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `toolset_name: optional string` For a toolset member tool_use, the toolset family this member belongs to. minLength: 1, maxLength: 64, pattern: ^[a-zA-Z0-9_-]+$ ### Beta Tool Use Caller - `beta_tool_use_caller: BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `type: "direct"` - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `type: "code_execution_20250825"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `beta_server_tool_caller_20260120: object` - `type: "code_execution_20260120"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ ### Beta Tool Uses Keep - `beta_tool_uses_keep: object` - `type: "tool_uses"` - `value: number` minimum: 0 ### Beta Tool Uses Trigger - `beta_tool_uses_trigger: object` - `type: "tool_uses"` - `value: number` minimum: 1 ### Beta Toolset Tool Use Block - `beta_toolset_tool_use_block: BetaBrowserToolUseBlock or BetaComputerToolUseBlock or BetaToolUseBlock` - `beta_browser_tool_use_block: BetaBrowserNavigateToolUseBlock or BetaBrowserListTabsToolUseBlock or BetaBrowserNewTabToolUseBlock or 28 more` - `beta_browser_navigate_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Navigate to a URL, or go back/forward/reload in history. The protocol may be omitted (defaults to https://). - `url: string` The URL to navigate to, or "back" / "forward" / "reload" for history navigation. - `tab_id: optional string` Tab to act on. Defaults to the active tab when omitted. - `name: "navigate"` - `toolset_name: "browser"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `type: "direct"` - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `type: "code_execution_20250825"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `beta_server_tool_caller_20260120: object` - `type: "code_execution_20260120"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `beta_browser_list_tabs_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` List all open tabs with each tab's tab_id, title, and URL. - `name: "list_tabs"` - `toolset_name: "browser"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `beta_server_tool_caller_20260120: object` - `beta_browser_new_tab_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Open a new empty tab and return its tab_id. - `name: "new_tab"` - `toolset_name: "browser"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `beta_server_tool_caller_20260120: object` - `beta_browser_switch_tab_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Make the tab with the given tab_id the active tab — the tab that actions without a tab_id apply to. - `tab_id: string` The tab to switch to. - `name: "switch_tab"` - `toolset_name: "browser"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `beta_server_tool_caller_20260120: object` - `beta_browser_close_tab_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Close the tab with the given tab_id. - `tab_id: string` The tab to close. - `name: "close_tab"` - `toolset_name: "browser"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `beta_server_tool_caller_20260120: object` - `beta_browser_read_page_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Return a structured accessibility tree of the page (or the subtree rooted at `ref`), with element references like [ref_7] that can be used as targets on later actions. Output is capped at 50,000 characters — narrow with `ref` or a smaller `depth` when exceeded. - `depth: optional number` Maximum tree depth. Default 15. minimum: 1 - `filter: optional "all" or "interactive"` Which elements to include. Omitted: every visible element. "interactive": interactive elements only. "all": additionally includes off-viewport elements. - `"all"` - `"interactive"` - `ref: optional string` Element reference to read a subtree from. Omit to read from the page root. - `tab_id: optional string` Tab to act on. Defaults to the active tab when omitted. - `name: "read_page"` - `toolset_name: "browser"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `beta_server_tool_caller_20260120: object` - `beta_browser_get_page_text_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Return the page's visible text content as plain text, prioritizing article content. Suited to articles, documentation, and other text-heavy pages. - `tab_id: optional string` Tab to act on. Defaults to the active tab when omitted. - `name: "get_page_text"` - `toolset_name: "browser"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `beta_server_tool_caller_20260120: object` - `beta_browser_read_console_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Return console output (log entries, errors, warnings) accumulated since the driver attached to the tab and since the last read, one line per entry. An empty result does not mean no traffic for a tab that predates attach. - `tab_id: optional string` Tab to act on. Defaults to the active tab when omitted. - `name: "read_console"` - `toolset_name: "browser"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `beta_server_tool_caller_20260120: object` - `beta_browser_read_network_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Return the network requests (method, URL, status, MIME type, timing) recorded since the driver attached to the tab and since the last read, one line per entry. An empty result does not mean no traffic for a tab that predates attach. - `tab_id: optional string` Tab to act on. Defaults to the active tab when omitted. - `name: "read_network"` - `toolset_name: "browser"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `beta_server_tool_caller_20260120: object` - `beta_browser_find_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Find elements matching a natural-language description (e.g. "search bar", "add to cart button") and return up to 20 matches with element references. - `query: string` Natural-language description of the element(s) to find. - `tab_id: optional string` Tab to act on. Defaults to the active tab when omitted. - `name: "find"` - `toolset_name: "browser"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `beta_server_tool_caller_20260120: object` - `beta_browser_form_input_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Set the value of a form element (input, textarea, select, checkbox). Use a boolean for checkboxes, an option value or text for selects. - `target: object` An element on the page, identified by a reference from a prior `read_page` or `find` result. References are scoped to the tab that produced them and become stale after navigation or a major re-render. - `type: "ref"` - `ref: string` An element reference (e.g. "ref_7") returned by a prior `read_page` or `find` result. - `value: string or number or boolean` The value to set. - `union_member_0: string` - `union_member_1: number` - `union_member_2: boolean` - `tab_id: optional string` Tab to act on. Defaults to the active tab when omitted. - `name: "form_input"` - `toolset_name: "browser"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `beta_server_tool_caller_20260120: object` - `beta_browser_file_upload_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Set the value of a file-input element to one or more files. The target must be an element reference; at least one of paths or document_ids is required. - `target: object` An element on the page, identified by a reference from a prior `read_page` or `find` result. References are scoped to the tab that produced them and become stale after navigation or a major re-render. - `type: "ref"` - `ref: string` An element reference (e.g. "ref_7") returned by a prior `read_page` or `find` result. - `document_ids: optional array of string` References to files the harness has staged, for deployments where the browser executor cannot read the caller's filesystem. minItems: 1 - `paths: optional array of string` File paths on the browser executor's filesystem. minItems: 1 - `tab_id: optional string` Tab to act on. Defaults to the active tab when omitted. - `name: "file_upload"` - `toolset_name: "browser"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `beta_server_tool_caller_20260120: object` - `beta_browser_scroll_to_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Scroll an element into view. - `target: object` An element on the page, identified by a reference from a prior `read_page` or `find` result. References are scoped to the tab that produced them and become stale after navigation or a major re-render. - `type: "ref"` - `ref: string` An element reference (e.g. "ref_7") returned by a prior `read_page` or `find` result. - `tab_id: optional string` Tab to act on. Defaults to the active tab when omitted. - `name: "scroll_to"` - `toolset_name: "browser"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `beta_server_tool_caller_20260120: object` - `beta_browser_screenshot_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Capture the current browser viewport. - `tab_id: optional string` Tab to act on. Defaults to the active tab when omitted. - `name: "screenshot"` - `toolset_name: "browser"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `beta_server_tool_caller_20260120: object` - `beta_browser_zoom_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Return a cropped screenshot of the given viewport region, scaled up for closer inspection — useful for small icons, buttons, or text. Coordinates are in the same viewport-pixel space as a full screenshot. - `region: array of number` [x0, y0, x1, y1] in viewport pixels. minItems: 4, maxItems: 4 - `tab_id: optional string` Tab to act on. Defaults to the active tab when omitted. - `name: "zoom"` - `toolset_name: "browser"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `beta_server_tool_caller_20260120: object` - `beta_browser_left_click_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Left-click at a viewport coordinate or on an element by reference. - `target: BetaBrowserCoordinateTarget or BetaBrowserRefTarget` Where to act: either a viewport coordinate or an element reference. - `beta_browser_coordinate_target: object` A point in the browser viewport, in viewport pixels (the same frame as a full-viewport screenshot). - `type: "coordinate"` - `x: number` Pixels from the left edge of the viewport. minimum: 0 - `y: number` Pixels from the top edge of the viewport. minimum: 0 - `beta_browser_ref_target: object` An element on the page, identified by a reference from a prior `read_page` or `find` result. References are scoped to the tab that produced them and become stale after navigation or a major re-render. - `type: "ref"` - `ref: string` An element reference (e.g. "ref_7") returned by a prior `read_page` or `find` result. - `modifiers: optional string` Optional modifier key chord to hold for the duration of this action (e.g. "shift", "ctrl+shift", "cmd+alt"). - `tab_id: optional string` Tab to act on. Defaults to the active tab when omitted. - `name: "left_click"` - `toolset_name: "browser"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `beta_server_tool_caller_20260120: object` - `beta_browser_right_click_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Right-click at a viewport coordinate or on an element by reference. - `target: BetaBrowserCoordinateTarget or BetaBrowserRefTarget` Where to act: either a viewport coordinate or an element reference. - `beta_browser_coordinate_target: object` A point in the browser viewport, in viewport pixels (the same frame as a full-viewport screenshot). - `beta_browser_ref_target: object` An element on the page, identified by a reference from a prior `read_page` or `find` result. References are scoped to the tab that produced them and become stale after navigation or a major re-render. - `modifiers: optional string` Optional modifier key chord to hold for the duration of this action (e.g. "shift", "ctrl+shift", "cmd+alt"). - `tab_id: optional string` Tab to act on. Defaults to the active tab when omitted. - `name: "right_click"` - `toolset_name: "browser"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `beta_server_tool_caller_20260120: object` - `beta_browser_middle_click_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Middle-click at a viewport coordinate or on an element by reference. - `target: BetaBrowserCoordinateTarget or BetaBrowserRefTarget` Where to act: either a viewport coordinate or an element reference. - `beta_browser_coordinate_target: object` A point in the browser viewport, in viewport pixels (the same frame as a full-viewport screenshot). - `beta_browser_ref_target: object` An element on the page, identified by a reference from a prior `read_page` or `find` result. References are scoped to the tab that produced them and become stale after navigation or a major re-render. - `modifiers: optional string` Optional modifier key chord to hold for the duration of this action (e.g. "shift", "ctrl+shift", "cmd+alt"). - `tab_id: optional string` Tab to act on. Defaults to the active tab when omitted. - `name: "middle_click"` - `toolset_name: "browser"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `beta_server_tool_caller_20260120: object` - `beta_browser_double_click_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Double left-click at a viewport coordinate or on an element by reference. - `target: BetaBrowserCoordinateTarget or BetaBrowserRefTarget` Where to act: either a viewport coordinate or an element reference. - `beta_browser_coordinate_target: object` A point in the browser viewport, in viewport pixels (the same frame as a full-viewport screenshot). - `beta_browser_ref_target: object` An element on the page, identified by a reference from a prior `read_page` or `find` result. References are scoped to the tab that produced them and become stale after navigation or a major re-render. - `modifiers: optional string` Optional modifier key chord to hold for the duration of this action (e.g. "shift", "ctrl+shift", "cmd+alt"). - `tab_id: optional string` Tab to act on. Defaults to the active tab when omitted. - `name: "double_click"` - `toolset_name: "browser"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `beta_server_tool_caller_20260120: object` - `beta_browser_triple_click_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Triple left-click at a viewport coordinate or on an element by reference (typically selects a line or paragraph). - `target: BetaBrowserCoordinateTarget or BetaBrowserRefTarget` Where to act: either a viewport coordinate or an element reference. - `beta_browser_coordinate_target: object` A point in the browser viewport, in viewport pixels (the same frame as a full-viewport screenshot). - `beta_browser_ref_target: object` An element on the page, identified by a reference from a prior `read_page` or `find` result. References are scoped to the tab that produced them and become stale after navigation or a major re-render. - `modifiers: optional string` Optional modifier key chord to hold for the duration of this action (e.g. "shift", "ctrl+shift", "cmd+alt"). - `tab_id: optional string` Tab to act on. Defaults to the active tab when omitted. - `name: "triple_click"` - `toolset_name: "browser"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `beta_server_tool_caller_20260120: object` - `beta_browser_hover_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Move the cursor to a coordinate or element without clicking. - `target: BetaBrowserCoordinateTarget or BetaBrowserRefTarget` Where to act: either a viewport coordinate or an element reference. - `beta_browser_coordinate_target: object` A point in the browser viewport, in viewport pixels (the same frame as a full-viewport screenshot). - `beta_browser_ref_target: object` An element on the page, identified by a reference from a prior `read_page` or `find` result. References are scoped to the tab that produced them and become stale after navigation or a major re-render. - `tab_id: optional string` Tab to act on. Defaults to the active tab when omitted. - `name: "hover"` - `toolset_name: "browser"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `beta_server_tool_caller_20260120: object` - `beta_browser_left_click_drag_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Press at `from`, drag to `target`, release. Both must be coordinate targets. - `from: object` A point in the browser viewport, in viewport pixels (the same frame as a full-viewport screenshot). - `type: "coordinate"` - `x: number` Pixels from the left edge of the viewport. minimum: 0 - `y: number` Pixels from the top edge of the viewport. minimum: 0 - `target: object` A point in the browser viewport, in viewport pixels (the same frame as a full-viewport screenshot). - `type: "coordinate"` - `x: number` Pixels from the left edge of the viewport. minimum: 0 - `y: number` Pixels from the top edge of the viewport. minimum: 0 - `tab_id: optional string` Tab to act on. Defaults to the active tab when omitted. - `name: "left_click_drag"` - `toolset_name: "browser"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `beta_server_tool_caller_20260120: object` - `beta_browser_left_mouse_down_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Press and hold the left mouse button at a viewport coordinate. Pair with left_mouse_up to perform a custom drag. - `target: object` A point in the browser viewport, in viewport pixels (the same frame as a full-viewport screenshot). - `type: "coordinate"` - `x: number` Pixels from the left edge of the viewport. minimum: 0 - `y: number` Pixels from the top edge of the viewport. minimum: 0 - `tab_id: optional string` Tab to act on. Defaults to the active tab when omitted. - `name: "left_mouse_down"` - `toolset_name: "browser"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `beta_server_tool_caller_20260120: object` - `beta_browser_left_mouse_up_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Release the left mouse button at a viewport coordinate. - `target: object` A point in the browser viewport, in viewport pixels (the same frame as a full-viewport screenshot). - `type: "coordinate"` - `x: number` Pixels from the left edge of the viewport. minimum: 0 - `y: number` Pixels from the top edge of the viewport. minimum: 0 - `tab_id: optional string` Tab to act on. Defaults to the active tab when omitted. - `name: "left_mouse_up"` - `toolset_name: "browser"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `beta_server_tool_caller_20260120: object` - `beta_browser_mouse_move_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Move the pointer to a viewport coordinate without clicking. - `target: object` A point in the browser viewport, in viewport pixels (the same frame as a full-viewport screenshot). - `type: "coordinate"` - `x: number` Pixels from the left edge of the viewport. minimum: 0 - `y: number` Pixels from the top edge of the viewport. minimum: 0 - `tab_id: optional string` Tab to act on. Defaults to the active tab when omitted. - `name: "mouse_move"` - `toolset_name: "browser"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `beta_server_tool_caller_20260120: object` - `beta_browser_scroll_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Scroll at a viewport position. `target` must be a coordinate target. - `scroll_direction: "up" or "down" or "left" or "right"` - `"up"` - `"down"` - `"left"` - `"right"` - `target: object` A point in the browser viewport, in viewport pixels (the same frame as a full-viewport screenshot). - `type: "coordinate"` - `x: number` Pixels from the left edge of the viewport. minimum: 0 - `y: number` Pixels from the top edge of the viewport. minimum: 0 - `scroll_amount: optional number` Scroll-wheel notches (1–10). Default 3. minimum: 1, maximum: 10 - `tab_id: optional string` Tab to act on. Defaults to the active tab when omitted. - `name: "scroll"` - `toolset_name: "browser"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `beta_server_tool_caller_20260120: object` - `beta_browser_type_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Type a literal string at the current focus. - `text: string` The text to type. - `tab_id: optional string` Tab to act on. Defaults to the active tab when omitted. - `name: "type"` - `toolset_name: "browser"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `beta_server_tool_caller_20260120: object` - `beta_browser_key_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Press a key or key chord. Use "+" to combine modifiers with a key (e.g. "ctrl+a", "cmd+shift+p") and space to sequence presses (e.g. "Backspace Backspace Delete"). Common names like "Return", "Tab", "Escape", "BackSpace" are supported. - `text: string` The key, chord, or space-separated sequence to press. - `repeat: optional number` Number of times to repeat. Default 1. minimum: 1, maximum: 100 - `tab_id: optional string` Tab to act on. Defaults to the active tab when omitted. - `name: "key"` - `toolset_name: "browser"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `beta_server_tool_caller_20260120: object` - `beta_browser_hold_key_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Hold a key or key chord down for a duration, then release it. Uses the same key names and "+" chord syntax as the key action. - `duration: number` Seconds to hold the key down (maximum 30). minimum: 0, maximum: 30 - `text: string` The key or chord to hold. - `tab_id: optional string` Tab to act on. Defaults to the active tab when omitted. - `name: "hold_key"` - `toolset_name: "browser"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `beta_server_tool_caller_20260120: object` - `beta_browser_wait_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Pause for the given duration. - `duration: number` Seconds to wait (maximum 30). minimum: 0, maximum: 30 - `tab_id: optional string` Tab to act on. Defaults to the active tab when omitted. - `name: "wait"` - `toolset_name: "browser"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `beta_server_tool_caller_20260120: object` - `beta_browser_javascript_exec_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Execute JavaScript in the page context and return the value of the last expression. The code runs with access to the DOM, `window`, and page variables. Write the expression you want evaluated — do NOT use `return`. - `text: string` JavaScript to execute in the page context. - `tab_id: optional string` Tab to act on. Defaults to the active tab when omitted. - `name: "javascript_exec"` - `toolset_name: "browser"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `beta_server_tool_caller_20260120: object` - `beta_computer_tool_use_block: BetaComputerKeyToolUseBlock or BetaComputerHoldKeyToolUseBlock or BetaComputerTypeToolUseBlock or 14 more` - `beta_computer_key_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Press a key or key-combination on the keyboard. Use "+" to combine modifiers with a key (e.g. "ctrl+s", "alt+Tab", "ctrl+shift+Escape"). Key names are case-insensitive; common names like "Return", "Tab", "Escape", "Up", "Down", "Left", "Right", "Home", "End", "Page_Up", "Page_Down", "Delete", "BackSpace" are supported. - `text: string` The key or key-combination to press. - `repeat: optional number` Number of times to repeat the key press. Default is 1. minimum: 1, maximum: 100 - `name: "key"` - `toolset_name: "computer"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `beta_server_tool_caller_20260120: object` - `beta_computer_hold_key_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Hold down a key or key-combination for a specified duration. Uses the same key syntax as `key`. - `duration: number` Duration to hold the key, in seconds. maximum: 300 - `text: string` The key or key-combination to hold. - `name: "hold_key"` - `toolset_name: "computer"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `beta_server_tool_caller_20260120: object` - `beta_computer_type_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Type a string of text on the keyboard. - `text: string` The text to type. - `name: "type"` - `toolset_name: "computer"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `beta_server_tool_caller_20260120: object` - `beta_computer_cursor_position_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Get the current (x, y) pixel coordinate of the cursor. - `name: "cursor_position"` - `toolset_name: "computer"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `beta_server_tool_caller_20260120: object` - `beta_computer_mouse_move_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Move the cursor to a specified (x, y) pixel coordinate. Use this ONLY to hover without clicking; otherwise use a click action directly. - `coordinate: array of number` (x, y): x pixels from the left edge, y pixels from the top edge. minItems: 2, maxItems: 2 - `name: "mouse_move"` - `toolset_name: "computer"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `beta_server_tool_caller_20260120: object` - `beta_computer_left_mouse_down_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Press and hold the left mouse button at the current cursor position. - `name: "left_mouse_down"` - `toolset_name: "computer"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `beta_server_tool_caller_20260120: object` - `beta_computer_left_mouse_up_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Release the left mouse button. - `name: "left_mouse_up"` - `toolset_name: "computer"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `beta_server_tool_caller_20260120: object` - `beta_computer_left_click_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Click the left mouse button at the specified (x, y) pixel coordinate, or the current cursor position if `coordinate` is omitted. - `coordinate: optional array of number` (x, y): x pixels from the left edge, y pixels from the top edge. minItems: 2, maxItems: 2 - `text: optional string` Optional key combination to hold down during this action (e.g. "ctrl", "shift", "ctrl+shift"). - `name: "left_click"` - `toolset_name: "computer"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `beta_server_tool_caller_20260120: object` - `beta_computer_left_click_drag_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Click and drag the cursor from `start_coordinate` to `coordinate`. - `coordinate: array of number` (x, y): x pixels from the left edge, y pixels from the top edge. minItems: 2, maxItems: 2 - `start_coordinate: array of number` (x, y): x pixels from the left edge, y pixels from the top edge. minItems: 2, maxItems: 2 - `text: optional string` Optional key combination to hold down during this action (e.g. "ctrl", "shift", "ctrl+shift"). - `name: "left_click_drag"` - `toolset_name: "computer"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `beta_server_tool_caller_20260120: object` - `beta_computer_right_click_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Click the right mouse button at the specified (x, y) pixel coordinate, or the current cursor position if `coordinate` is omitted. - `coordinate: optional array of number` (x, y): x pixels from the left edge, y pixels from the top edge. minItems: 2, maxItems: 2 - `text: optional string` Optional key combination to hold down during this action (e.g. "ctrl", "shift", "ctrl+shift"). - `name: "right_click"` - `toolset_name: "computer"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `beta_server_tool_caller_20260120: object` - `beta_computer_middle_click_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Click the middle mouse button at the specified (x, y) pixel coordinate, or the current cursor position if `coordinate` is omitted. - `coordinate: optional array of number` (x, y): x pixels from the left edge, y pixels from the top edge. minItems: 2, maxItems: 2 - `text: optional string` Optional key combination to hold down during this action (e.g. "ctrl", "shift", "ctrl+shift"). - `name: "middle_click"` - `toolset_name: "computer"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `beta_server_tool_caller_20260120: object` - `beta_computer_double_click_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Double-click the left mouse button at the specified (x, y) pixel coordinate, or the current cursor position if `coordinate` is omitted. - `coordinate: optional array of number` (x, y): x pixels from the left edge, y pixels from the top edge. minItems: 2, maxItems: 2 - `text: optional string` Optional key combination to hold down during this action (e.g. "ctrl", "shift", "ctrl+shift"). - `name: "double_click"` - `toolset_name: "computer"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `beta_server_tool_caller_20260120: object` - `beta_computer_triple_click_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Triple-click the left mouse button at the specified (x, y) pixel coordinate, or the current cursor position if `coordinate` is omitted. - `coordinate: optional array of number` (x, y): x pixels from the left edge, y pixels from the top edge. minItems: 2, maxItems: 2 - `text: optional string` Optional key combination to hold down during this action (e.g. "ctrl", "shift", "ctrl+shift"). - `name: "triple_click"` - `toolset_name: "computer"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `beta_server_tool_caller_20260120: object` - `beta_computer_scroll_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Scroll the screen at the specified (x, y) pixel coordinate, or the current cursor position if `coordinate` is omitted. Do NOT use PageUp/PageDown to scroll. - `scroll_amount: number` Number of 'clicks' of the scroll wheel. - `scroll_direction: "up" or "down" or "left" or "right"` - `"up"` - `"down"` - `"left"` - `"right"` - `coordinate: optional array of number` (x, y): x pixels from the left edge, y pixels from the top edge. minItems: 2, maxItems: 2 - `text: optional string` Optional key combination to hold down during this action (e.g. "ctrl", "shift", "ctrl+shift"). - `name: "scroll"` - `toolset_name: "computer"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `beta_server_tool_caller_20260120: object` - `beta_computer_wait_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Wait for a specified duration. - `duration: number` Duration to wait, in seconds. maximum: 300 - `name: "wait"` - `toolset_name: "computer"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `beta_server_tool_caller_20260120: object` - `beta_computer_screenshot_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Take a screenshot of the screen. - `name: "screenshot"` - `toolset_name: "computer"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `beta_server_tool_caller_20260120: object` - `beta_computer_zoom_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: object` Take a screenshot of a rectangular region. Region coordinates are in the full-screenshot space (not physical display pixels). The crop is scaled up to fill the image budget so fine details become legible. - `region: array of number` (x0, y0, x1, y1): The region to capture. minItems: 4, maxItems: 4 - `name: "zoom"` - `toolset_name: "computer"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Which party invoked the tool call: the model directly, or a server tool on its behalf. - `beta_direct_caller: object` Tool invocation directly from the model. - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `beta_server_tool_caller_20260120: object` - `beta_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: map[unknown]` - `name: string` minLength: 1 - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` - `beta_direct_caller: object` Tool invocation directly from the model. - `type: "direct"` - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `type: "code_execution_20250825"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `beta_server_tool_caller_20260120: object` - `type: "code_execution_20260120"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `toolset_name: optional string` For a toolset member tool_use, the toolset family. minLength: 1, maxLength: 64, pattern: ^[a-zA-Z0-9_-]+$ ### Beta URL Image Source - `beta_url_image_source: object` - `type: "url"` - `url: string` ### Beta URL PDF Source - `beta_url_pdf_source: object` - `type: "url"` - `url: string` ### Beta Usage - `beta_usage: object` - `cache_creation: object` Breakdown of cached tokens by TTL - `ephemeral_1h_input_tokens: number` The number of input tokens used to create the 1 hour cache entry. minimum: 0 - `ephemeral_5m_input_tokens: number` The number of input tokens used to create the 5 minute cache entry. minimum: 0 - `cache_creation_input_tokens: number` The number of input tokens used to create the cache entry. minimum: 0 - `cache_read_input_tokens: number` The number of input tokens read from the cache. minimum: 0 - `fallback_credit: object` Outcome of the `fallback_credit_token` presented on this request. Present on every response to a non-batch request that carried a `fallback_credit_token`, in either redemption mode; absent otherwise (batch items accept and ignore the token and carry no outcome object). - `status: BetaFallbackCreditRedeemed or BetaFallbackCreditNotApplied` Whether the fallback-credit reprice was applied to this response's billing. A union discriminated on `type`. `redeemed`: the retry is billed as if the conversation had been on the retry model all along — including when the resulting shift is zero because there was nothing to move. `not_applied`: no reprice was applied; the arm's `reason` says why. - `beta_fallback_credit_redeemed: object` The reprice was applied: the retry is billed as if the conversation had been on the retry model all along. - `type: "redeemed"` - `beta_fallback_credit_not_applied: object` No reprice was applied; `reason` says why. - `type: "not_applied"` - `reason: "body_mismatch" or "continuation_excluded" or "continuation_only" or 9 more` Why the reprice was not applied. A closed enum; additions to the redemption-check vocabulary arrive as deliberate schema updates. - `"body_mismatch"` - `"continuation_excluded"` - `"continuation_only"` - `"expired"` - `"invalid_target_model"` - `"not_enabled"` - `"reprice_unavailable"` - `"temporarily_unavailable"` - `"variant_fields_present"` - `"wrong_organization"` - `"wrong_platform"` - `"wrong_workspace"` - `remove_to_redeem: optional array of string` Request fields to remove before retrying, so the retry can redeem this token. Present exactly when `reason` is `variant_fields_present` — never null, never an empty array; absent otherwise. Fields are named only from your own request, and only after the sealed variant hash matched. A served best-effort retry has already been billed at normal price; nothing redeems retroactively, but a corrected re-send inside the token's five-minute window can still redeem. - `inference_geo: string` The geographic region where inference was performed for this request. - `input_tokens: number` The number of input tokens which were used. minimum: 0 - `iterations: array of BetaMessageIterationUsage or BetaCompactionIterationUsage or BetaAdvisorMessageIterationUsage or BetaFallbackMessageIterationUsage` Per-iteration token usage breakdown. Each entry represents one sampling iteration, with its own input/output token counts and cache statistics, discriminated by `type`. For `message` entries (model sampling iterations, such as the turns of a server-side tool use loop), this allows you to: - Calculate the context window size from the last `message` entry - Understand token accumulation across server-side tool use loops A `compaction` entry reports the token usage of the compaction operation itself — the server-side request that summarizes the context being closed — NOT the size of the context that was compacted away, and its token counts can be much smaller than that closed context (for example, a compaction that closes a ~200k-token context can report only a few thousand tokens). Do not derive the context window size from a `compaction` entry, even when it is the last entry. A `compaction` entry's tokens are not included in the top-level `usage` fields. When an input-token trigger is in effect (the default — 150,000 tokens unless configured otherwise), each `compaction` entry closes a context that had reached at least that threshold, though the context can exceed it by the final iteration's output and tool results. - `beta_message_iteration_usage: object` Token usage for a sampling iteration. - `type: "message"` Usage for a sampling iteration - `cache_creation: object` Breakdown of cached tokens by TTL - `ephemeral_1h_input_tokens: number` The number of input tokens used to create the 1 hour cache entry. minimum: 0 - `ephemeral_5m_input_tokens: number` The number of input tokens used to create the 5 minute cache entry. minimum: 0 - `cache_creation_input_tokens: number` The number of input tokens used to create the cache entry. minimum: 0 - `cache_read_input_tokens: number` The number of input tokens read from the cache. minimum: 0 - `input_tokens: number` The number of input tokens which were used. minimum: 0 - `model: "claude-haiku-5-5" or "claude-sonnet-5-5" or "claude-fable-5-1" or 17 more or string` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-haiku-5-5"` Fastest model for high-volume, real-time tasks - `"claude-sonnet-5-5"` Efficient model for coding and agents - `"claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows - `"claude-opus-5-5"` Powerful intelligence for coding, knowledge work, and long-running agents - `"claude-mythos-5-1"` Our most capable model for cybersecurity and biology research, available through trusted access programs - `"claude-sonnet-5"` Efficient model for coding and agents - `"claude-fable-5"` Next generation of intelligence for the hardest knowledge work and coding problems - `"claude-mythos-5"` Most capable model for cybersecurity and biology research - `"claude-opus-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-8"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-7"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-6"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-6"` Best combination of speed and intelligence - `"claude-haiku-4-5"` - `"claude-haiku-4-5-20251001"` - `"claude-opus-4-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-5-20251101"` Powerful intelligence for long-running agents and coding - `"claude-mythos-preview"` **Deprecated**: Will reach end-of-life on June 30, 2026. Please migrate to claude-mythos-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. New class of intelligence, strongest in coding and cybersecurity - `"claude-sonnet-4-5"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `"claude-sonnet-4-5-20250929"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `output_tokens: number` The number of output tokens which were used. minimum: 0 - `beta_compaction_iteration_usage: object` Token usage for a compaction iteration. - `type: "compaction"` Usage for a compaction iteration - `cache_creation: object` Breakdown of cached tokens by TTL - `ephemeral_1h_input_tokens: number` The number of input tokens used to create the 1 hour cache entry. minimum: 0 - `ephemeral_5m_input_tokens: number` The number of input tokens used to create the 5 minute cache entry. minimum: 0 - `cache_creation_input_tokens: number` The number of input tokens used to create the cache entry. minimum: 0 - `cache_read_input_tokens: number` The number of input tokens read from the cache. minimum: 0 - `input_tokens: number` The number of input tokens which were used. minimum: 0 - `output_tokens: number` The number of output tokens which were used. minimum: 0 - `beta_advisor_message_iteration_usage: object` Token usage for an advisor sub-inference iteration. - `type: "advisor_message"` Usage for an advisor sub-inference iteration - `cache_creation: object` Breakdown of cached tokens by TTL - `ephemeral_1h_input_tokens: number` The number of input tokens used to create the 1 hour cache entry. minimum: 0 - `ephemeral_5m_input_tokens: number` The number of input tokens used to create the 5 minute cache entry. minimum: 0 - `cache_creation_input_tokens: number` The number of input tokens used to create the cache entry. minimum: 0 - `cache_read_input_tokens: number` The number of input tokens read from the cache. minimum: 0 - `input_tokens: number` The number of input tokens which were used. minimum: 0 - `model: "claude-haiku-5-5" or "claude-sonnet-5-5" or "claude-fable-5-1" or 17 more or string` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-haiku-5-5"` Fastest model for high-volume, real-time tasks - `"claude-sonnet-5-5"` Efficient model for coding and agents - `"claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows - `"claude-opus-5-5"` Powerful intelligence for coding, knowledge work, and long-running agents - `"claude-mythos-5-1"` Our most capable model for cybersecurity and biology research, available through trusted access programs - `"claude-sonnet-5"` Efficient model for coding and agents - `"claude-fable-5"` Next generation of intelligence for the hardest knowledge work and coding problems - `"claude-mythos-5"` Most capable model for cybersecurity and biology research - `"claude-opus-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-8"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-7"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-6"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-6"` Best combination of speed and intelligence - `"claude-haiku-4-5"` - `"claude-haiku-4-5-20251001"` - `"claude-opus-4-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-5-20251101"` Powerful intelligence for long-running agents and coding - `"claude-mythos-preview"` **Deprecated**: Will reach end-of-life on June 30, 2026. Please migrate to claude-mythos-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. New class of intelligence, strongest in coding and cybersecurity - `"claude-sonnet-4-5"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `"claude-sonnet-4-5-20250929"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `output_tokens: number` The number of output tokens which were used. minimum: 0 - `beta_fallback_message_iteration_usage: object` Token usage for the fallback-model attempt of a server-side fallback request. The terminal entry of a fallback-served turn: when a fallback hop's output is the returned message, the entry for the iteration that completed it carries this type in place of `message`. A declined hop and the serving hop's earlier tool-loop iterations produce `message` entries. Whether a fallback model served the response is signalled by the presence of this entry in `usage.iterations`. - `type: "fallback_message"` Usage for the fallback-model attempt that served the response - `cache_creation: object` Breakdown of cached tokens by TTL - `ephemeral_1h_input_tokens: number` The number of input tokens used to create the 1 hour cache entry. minimum: 0 - `ephemeral_5m_input_tokens: number` The number of input tokens used to create the 5 minute cache entry. minimum: 0 - `cache_creation_input_tokens: number` The number of input tokens used to create the cache entry. minimum: 0 - `cache_read_input_tokens: number` The number of input tokens read from the cache. minimum: 0 - `input_tokens: number` The number of input tokens which were used. minimum: 0 - `model: "claude-haiku-5-5" or "claude-sonnet-5-5" or "claude-fable-5-1" or 17 more or string` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-haiku-5-5"` Fastest model for high-volume, real-time tasks - `"claude-sonnet-5-5"` Efficient model for coding and agents - `"claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows - `"claude-opus-5-5"` Powerful intelligence for coding, knowledge work, and long-running agents - `"claude-mythos-5-1"` Our most capable model for cybersecurity and biology research, available through trusted access programs - `"claude-sonnet-5"` Efficient model for coding and agents - `"claude-fable-5"` Next generation of intelligence for the hardest knowledge work and coding problems - `"claude-mythos-5"` Most capable model for cybersecurity and biology research - `"claude-opus-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-8"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-7"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-6"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-6"` Best combination of speed and intelligence - `"claude-haiku-4-5"` - `"claude-haiku-4-5-20251001"` - `"claude-opus-4-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-5-20251101"` Powerful intelligence for long-running agents and coding - `"claude-mythos-preview"` **Deprecated**: Will reach end-of-life on June 30, 2026. Please migrate to claude-mythos-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. New class of intelligence, strongest in coding and cybersecurity - `"claude-sonnet-4-5"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `"claude-sonnet-4-5-20250929"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `output_tokens: number` The number of output tokens which were used. minimum: 0 - `output_tokens: number` The number of output tokens which were used. minimum: 0 - `output_tokens_details: object` Breakdown of output tokens by category. `output_tokens` remains the inclusive, authoritative total used for billing. This object provides a read-only decomposition for observability — for example, how many of the billed output tokens were spent on internal reasoning that may have been summarized before being returned to you. - `thinking_tokens: number` Number of output tokens the model generated as internal reasoning, including the thinking-block delimiter tokens. Reflects the raw reasoning the model produced, not the (possibly shorter) summarized thinking text returned in the response body. Computed by re-tokenizing the raw reasoning text, so it may differ from the model's exact generation count by a small number of tokens. Always ≤ `output_tokens`; `output_tokens - thinking_tokens` approximates the non-reasoning output. minimum: 0 - `server_tool_use: object` The number of server tool requests. - `web_fetch_requests: number` The number of web fetch tool requests. minimum: 0 - `web_search_requests: number` The number of web search tool requests. minimum: 0 - `service_tier: "standard" or "priority" or "batch"` If the request used the priority, standard, or batch tier. - `"standard"` - `"priority"` - `"batch"` - `speed: "standard" or "fast"` The inference speed mode used for this request. - `"standard"` - `"fast"` ### Beta User Location - `beta_user_location: object` - `type: "approximate"` - `city: optional string` The city of the user. minLength: 1, maxLength: 255 - `country: optional string` The two letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1_alpha-2) of the user. minLength: 2, maxLength: 2 - `region: optional string` The region of the user. minLength: 1, maxLength: 255 - `timezone: optional string` The [IANA timezone](https://nodatime.org/TimeZones) of the user. minLength: 1, maxLength: 255 ### Beta Web Fetch Block - `beta_web_fetch_block: object` - `type: "web_fetch_result"` - `content: object` - `type: "document"` - `citations: object` Citation configuration for the document - `enabled: boolean` - `source: BetaBase64PDFSource or BetaPlainTextSource` - `beta_base64_pdf_source: object` - `type: "base64"` - `data: string` format: byte - `media_type: "application/pdf"` - `beta_plain_text_source: object` - `type: "text"` - `data: string` - `media_type: "text/plain"` - `title: string` The title of the document - `retrieved_at: string` ISO 8601 timestamp when the content was retrieved - `url: string` Fetched content URL ### Beta Web Fetch Block Param - `beta_web_fetch_block_param: object` - `type: "web_fetch_result"` - `content: object` - `type: "document"` - `source: BetaBase64PDFSource or BetaPlainTextSource or BetaContentBlockSource or 2 more` - `beta_base64_pdf_source: object` - `type: "base64"` - `data: string` format: byte - `media_type: "application/pdf"` - `beta_plain_text_source: object` - `type: "text"` - `data: string` - `media_type: "text/plain"` - `beta_content_block_source: object` - `type: "content"` - `content: string or array of BetaContentBlockSourceContent` - `union_member_0: string` - `beta_content_block_source_content: array of BetaContentBlockSourceContent` - `beta_text_block_param: object` - `type: "text"` - `text: string` minLength: 1 - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `"5m"` - `"1h"` - `citations: optional array of BetaTextCitationParam` - `beta_citation_char_location_param: object` - `type: "char_location"` - `cited_text: string` - `document_index: number` minimum: 0 - `document_title: string` minLength: 1, maxLength: 500 - `end_char_index: number` - `start_char_index: number` minimum: 0 - `beta_citation_page_location_param: object` - `type: "page_location"` - `cited_text: string` - `document_index: number` minimum: 0 - `document_title: string` minLength: 1, maxLength: 500 - `end_page_number: number` - `start_page_number: number` minimum: 1 - `beta_citation_content_block_location_param: object` - `type: "content_block_location"` - `cited_text: string` The full text of the cited block range, concatenated. Always equals the contents of `content[start_block_index:end_block_index]` joined together. The text block is the minimal citable unit; this field is never a substring of a single block. Not counted toward output tokens, and not counted toward input tokens when sent back in subsequent turns. - `document_index: number` minimum: 0 - `document_title: string` minLength: 1, maxLength: 500 - `end_block_index: number` Exclusive 0-based end index of the cited block range in the source's `content` array. Always greater than `start_block_index`; a single-block citation has `end_block_index = start_block_index + 1`. - `start_block_index: number` 0-based index of the first cited block in the source's `content` array. minimum: 0 - `beta_citation_web_search_result_location_param: object` - `type: "web_search_result_location"` - `cited_text: string` - `encrypted_index: string` - `title: string` minLength: 1, maxLength: 512 - `url: string` minLength: 1 - `beta_citation_search_result_location_param: object` - `type: "search_result_location"` - `cited_text: string` The full text of the cited block range, concatenated. Always equals the contents of `content[start_block_index:end_block_index]` joined together. The text block is the minimal citable unit; this field is never a substring of a single block. Not counted toward output tokens, and not counted toward input tokens when sent back in subsequent turns. - `end_block_index: number` Exclusive 0-based end index of the cited block range in the source's `content` array. Always greater than `start_block_index`; a single-block citation has `end_block_index = start_block_index + 1`. - `search_result_index: number` 0-based index of the cited search result among all `search_result` content blocks in the request, in the order they appear across messages and tool results. Counted separately from `document_index`; server-side web search results are not included in this count. minimum: 0 - `source: string` - `start_block_index: number` 0-based index of the first cited block in the source's `content` array. minimum: 0 - `title: string` - `beta_image_block_param: object` - `type: "image"` - `source: BetaBase64ImageSource or BetaURLImageSource or BetaFileImageSource` - `beta_base64_image_source: object` - `type: "base64"` - `data: string` format: byte - `media_type: "image/jpeg" or "image/png" or "image/gif" or "image/webp"` - `"image/jpeg"` - `"image/png"` - `"image/gif"` - `"image/webp"` - `beta_url_image_source: object` - `type: "url"` - `url: string` - `beta_file_image_source: object` - `type: "file"` - `file_id: string` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `transformations: optional object` Configures the transformations the server applies to this image before the model observes it. Each key names a condition the server transforms images for; its value selects the transformation applied. Omitted keys keep their default behavior, and an empty object is equivalent to omitting the field. - `oversized_image: optional "downsize" or "error"` What the server does when this image exceeds the model's maximum image size. `"downsize"` (the default) scales the image down to fit, which changes the dimensions the model observes without telling you. `"error"` instead rejects the request with a 400 error naming the image's dimensions and the largest dimensions that fit, so you can scale the image deliberately — your image is never silently scaled down. - `"downsize"` - `"error"` - `beta_url_pdf_source: object` - `type: "url"` - `url: string` - `beta_file_document_source: object` - `type: "file"` - `file_id: string` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `citations: optional object` - `enabled: optional boolean` - `context: optional string` minLength: 1 - `title: optional string` minLength: 1, maxLength: 500 - `url: string` Fetched content URL - `retrieved_at: optional string` ISO 8601 timestamp when the content was retrieved ### Beta Web Fetch Tool 20250910 - `beta_web_fetch_tool_20250910: object` - `type: "web_fetch_20250910"` - `name: "web_fetch"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: optional array of string` List of domains to allow fetching from - `blocked_domains: optional array of string` List of domains to block fetching from - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `"5m"` - `"1h"` - `citations: optional object` Citations configuration for fetched documents. Citations are disabled by default. - `enabled: optional boolean` - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_content_tokens: optional number` Maximum number of tokens used by including web page text content in the context. The limit is approximate and does not apply to binary content such as PDFs. minimum: 1 - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `url_sources: optional object` Which sources contribute to the set of URLs the tool may fetch. Omitted means every source. - `client_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which client tools' results contribute fetchable URLs: "all", "none", or an only or except list of client tool names from tools[]. - `beta_web_fetch_url_source_all: object` The `url_sources` variant under which a source contributes in full: every result of the tool filter's source, or all user input. - `type: "all"` - `beta_web_fetch_url_source_none: object` The `url_sources` variant under which a source contributes nothing: no result of the tool filter's source, or no user input. - `type: "none"` - `beta_web_fetch_url_source_only: object` The tool filter variant under which only the named tools' results contribute. - `type: "only"` - `tools: array of BetaWebFetchURLSourceToolReference` - `type: "tool_reference"` - `name: string` - `beta_web_fetch_url_source_except: object` The tool filter variant under which every result but the named tools' contributes. - `type: "except"` - `tools: array of BetaWebFetchURLSourceToolReference` - `type: "tool_reference"` - `name: string` - `server_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which server tools' results contribute fetchable URLs: "all", "none", or an only or except list of server tool names from tools[]; only web_search and web_fetch results ever contribute. - `beta_web_fetch_url_source_all: object` The `url_sources` variant under which a source contributes in full: every result of the tool filter's source, or all user input. - `beta_web_fetch_url_source_none: object` The `url_sources` variant under which a source contributes nothing: no result of the tool filter's source, or no user input. - `beta_web_fetch_url_source_only: object` The tool filter variant under which only the named tools' results contribute. - `beta_web_fetch_url_source_except: object` The tool filter variant under which every result but the named tools' contributes. - `user_input: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone` Whether URLs in user messages are fetchable: "all" or "none". - `beta_web_fetch_url_source_all: object` The `url_sources` variant under which a source contributes in full: every result of the tool filter's source, or all user input. - `beta_web_fetch_url_source_none: object` The `url_sources` variant under which a source contributes nothing: no result of the tool filter's source, or no user input. ### Beta Web Fetch Tool 20260209 - `beta_web_fetch_tool_20260209: object` - `type: "web_fetch_20260209"` - `name: "web_fetch"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: optional array of string` List of domains to allow fetching from - `blocked_domains: optional array of string` List of domains to block fetching from - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `"5m"` - `"1h"` - `citations: optional object` Citations configuration for fetched documents. Citations are disabled by default. - `enabled: optional boolean` - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_content_tokens: optional number` Maximum number of tokens used by including web page text content in the context. The limit is approximate and does not apply to binary content such as PDFs. minimum: 1 - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `url_sources: optional object` Which sources contribute to the set of URLs the tool may fetch. Omitted means every source. - `client_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which client tools' results contribute fetchable URLs: "all", "none", or an only or except list of client tool names from tools[]. - `beta_web_fetch_url_source_all: object` The `url_sources` variant under which a source contributes in full: every result of the tool filter's source, or all user input. - `type: "all"` - `beta_web_fetch_url_source_none: object` The `url_sources` variant under which a source contributes nothing: no result of the tool filter's source, or no user input. - `type: "none"` - `beta_web_fetch_url_source_only: object` The tool filter variant under which only the named tools' results contribute. - `type: "only"` - `tools: array of BetaWebFetchURLSourceToolReference` - `type: "tool_reference"` - `name: string` - `beta_web_fetch_url_source_except: object` The tool filter variant under which every result but the named tools' contributes. - `type: "except"` - `tools: array of BetaWebFetchURLSourceToolReference` - `type: "tool_reference"` - `name: string` - `server_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which server tools' results contribute fetchable URLs: "all", "none", or an only or except list of server tool names from tools[]; only web_search and web_fetch results ever contribute. - `beta_web_fetch_url_source_all: object` The `url_sources` variant under which a source contributes in full: every result of the tool filter's source, or all user input. - `beta_web_fetch_url_source_none: object` The `url_sources` variant under which a source contributes nothing: no result of the tool filter's source, or no user input. - `beta_web_fetch_url_source_only: object` The tool filter variant under which only the named tools' results contribute. - `beta_web_fetch_url_source_except: object` The tool filter variant under which every result but the named tools' contributes. - `user_input: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone` Whether URLs in user messages are fetchable: "all" or "none". - `beta_web_fetch_url_source_all: object` The `url_sources` variant under which a source contributes in full: every result of the tool filter's source, or all user input. - `beta_web_fetch_url_source_none: object` The `url_sources` variant under which a source contributes nothing: no result of the tool filter's source, or no user input. ### Beta Web Fetch Tool 20260309 - `beta_web_fetch_tool_20260309: object` Web fetch tool with use_cache parameter for bypassing cached content. - `type: "web_fetch_20260309"` - `name: "web_fetch"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: optional array of string` List of domains to allow fetching from - `blocked_domains: optional array of string` List of domains to block fetching from - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `"5m"` - `"1h"` - `citations: optional object` Citations configuration for fetched documents. Citations are disabled by default. - `enabled: optional boolean` - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_content_tokens: optional number` Maximum number of tokens used by including web page text content in the context. The limit is approximate and does not apply to binary content such as PDFs. minimum: 1 - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `url_sources: optional object` Which sources contribute to the set of URLs the tool may fetch. Omitted means every source. - `client_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which client tools' results contribute fetchable URLs: "all", "none", or an only or except list of client tool names from tools[]. - `beta_web_fetch_url_source_all: object` The `url_sources` variant under which a source contributes in full: every result of the tool filter's source, or all user input. - `type: "all"` - `beta_web_fetch_url_source_none: object` The `url_sources` variant under which a source contributes nothing: no result of the tool filter's source, or no user input. - `type: "none"` - `beta_web_fetch_url_source_only: object` The tool filter variant under which only the named tools' results contribute. - `type: "only"` - `tools: array of BetaWebFetchURLSourceToolReference` - `type: "tool_reference"` - `name: string` - `beta_web_fetch_url_source_except: object` The tool filter variant under which every result but the named tools' contributes. - `type: "except"` - `tools: array of BetaWebFetchURLSourceToolReference` - `type: "tool_reference"` - `name: string` - `server_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which server tools' results contribute fetchable URLs: "all", "none", or an only or except list of server tool names from tools[]; only web_search and web_fetch results ever contribute. - `beta_web_fetch_url_source_all: object` The `url_sources` variant under which a source contributes in full: every result of the tool filter's source, or all user input. - `beta_web_fetch_url_source_none: object` The `url_sources` variant under which a source contributes nothing: no result of the tool filter's source, or no user input. - `beta_web_fetch_url_source_only: object` The tool filter variant under which only the named tools' results contribute. - `beta_web_fetch_url_source_except: object` The tool filter variant under which every result but the named tools' contributes. - `user_input: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone` Whether URLs in user messages are fetchable: "all" or "none". - `beta_web_fetch_url_source_all: object` The `url_sources` variant under which a source contributes in full: every result of the tool filter's source, or all user input. - `beta_web_fetch_url_source_none: object` The `url_sources` variant under which a source contributes nothing: no result of the tool filter's source, or no user input. - `use_cache: optional boolean` Whether to use cached content. Set to false to bypass the cache and fetch fresh content. Only set to false when the user explicitly requests fresh content or when fetching rapidly-changing sources. ### Beta Web Fetch Tool 20260318 - `beta_web_fetch_tool_20260318: object` - `type: "web_fetch_20260318"` - `name: "web_fetch"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: optional array of string` List of domains to allow fetching from - `blocked_domains: optional array of string` List of domains to block fetching from - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `"5m"` - `"1h"` - `citations: optional object` Citations configuration for fetched documents. Citations are disabled by default. - `enabled: optional boolean` - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_content_tokens: optional number` Maximum number of tokens used by including web page text content in the context. The limit is approximate and does not apply to binary content such as PDFs. minimum: 1 - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `response_inclusion: optional "full" or "excluded"` How this tool's result blocks appear in the API response when the result was consumed by a completed code_execution call in the same turn. 'full' returns the complete content (default). 'excluded' drops the nested server_tool_use and result block pair entirely. Results from direct calls, or from code_execution calls that paused before completing, are always returned in full so they can be sent back on the next turn. - `"full"` - `"excluded"` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `url_sources: optional object` Which sources contribute to the set of URLs the tool may fetch. Omitted means every source. - `client_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which client tools' results contribute fetchable URLs: "all", "none", or an only or except list of client tool names from tools[]. - `beta_web_fetch_url_source_all: object` The `url_sources` variant under which a source contributes in full: every result of the tool filter's source, or all user input. - `type: "all"` - `beta_web_fetch_url_source_none: object` The `url_sources` variant under which a source contributes nothing: no result of the tool filter's source, or no user input. - `type: "none"` - `beta_web_fetch_url_source_only: object` The tool filter variant under which only the named tools' results contribute. - `type: "only"` - `tools: array of BetaWebFetchURLSourceToolReference` - `type: "tool_reference"` - `name: string` - `beta_web_fetch_url_source_except: object` The tool filter variant under which every result but the named tools' contributes. - `type: "except"` - `tools: array of BetaWebFetchURLSourceToolReference` - `type: "tool_reference"` - `name: string` - `server_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which server tools' results contribute fetchable URLs: "all", "none", or an only or except list of server tool names from tools[]; only web_search and web_fetch results ever contribute. - `beta_web_fetch_url_source_all: object` The `url_sources` variant under which a source contributes in full: every result of the tool filter's source, or all user input. - `beta_web_fetch_url_source_none: object` The `url_sources` variant under which a source contributes nothing: no result of the tool filter's source, or no user input. - `beta_web_fetch_url_source_only: object` The tool filter variant under which only the named tools' results contribute. - `beta_web_fetch_url_source_except: object` The tool filter variant under which every result but the named tools' contributes. - `user_input: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone` Whether URLs in user messages are fetchable: "all" or "none". - `beta_web_fetch_url_source_all: object` The `url_sources` variant under which a source contributes in full: every result of the tool filter's source, or all user input. - `beta_web_fetch_url_source_none: object` The `url_sources` variant under which a source contributes nothing: no result of the tool filter's source, or no user input. - `use_cache: optional boolean` Whether to use cached content. Set to false to bypass the cache and fetch fresh content. Only set to false when the user explicitly requests fresh content or when fetching rapidly-changing sources. ### Beta Web Fetch Tool Result Block - `beta_web_fetch_tool_result_block: object` - `type: "web_fetch_tool_result"` - `content: BetaWebFetchToolResultErrorBlock or BetaWebFetchBlock` - `beta_web_fetch_tool_result_error_block: object` - `type: "web_fetch_tool_result_error"` - `error_code: "invalid_tool_input" or "url_too_long" or "url_not_allowed" or 7 more` - `"invalid_tool_input"` - `"url_too_long"` - `"url_not_allowed"` - `"url_not_in_prior_context"` - `"url_not_accessible"` - `"unsupported_content_type"` - `"too_many_requests"` - `"max_uses_exceeded"` - `"unavailable"` - `"content_too_large"` - `beta_web_fetch_block: object` - `type: "web_fetch_result"` - `content: object` - `type: "document"` - `citations: object` Citation configuration for the document - `enabled: boolean` - `source: BetaBase64PDFSource or BetaPlainTextSource` - `beta_base64_pdf_source: object` - `type: "base64"` - `data: string` format: byte - `media_type: "application/pdf"` - `beta_plain_text_source: object` - `type: "text"` - `data: string` - `media_type: "text/plain"` - `title: string` The title of the document - `retrieved_at: string` ISO 8601 timestamp when the content was retrieved - `url: string` Fetched content URL - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` - `beta_direct_caller: object` Tool invocation directly from the model. - `type: "direct"` - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `type: "code_execution_20250825"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `beta_server_tool_caller_20260120: object` - `type: "code_execution_20260120"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ ### Beta Web Fetch Tool Result Block Param - `beta_web_fetch_tool_result_block_param: object` - `type: "web_fetch_tool_result"` - `content: BetaWebFetchToolResultErrorBlockParam or BetaWebFetchBlockParam` - `beta_web_fetch_tool_result_error_block_param: object` - `type: "web_fetch_tool_result_error"` - `error_code: "invalid_tool_input" or "url_too_long" or "url_not_allowed" or 7 more` - `"invalid_tool_input"` - `"url_too_long"` - `"url_not_allowed"` - `"url_not_in_prior_context"` - `"url_not_accessible"` - `"unsupported_content_type"` - `"too_many_requests"` - `"max_uses_exceeded"` - `"unavailable"` - `"content_too_large"` - `beta_web_fetch_block_param: object` - `type: "web_fetch_result"` - `content: object` - `type: "document"` - `source: BetaBase64PDFSource or BetaPlainTextSource or BetaContentBlockSource or 2 more` - `beta_base64_pdf_source: object` - `type: "base64"` - `data: string` format: byte - `media_type: "application/pdf"` - `beta_plain_text_source: object` - `type: "text"` - `data: string` - `media_type: "text/plain"` - `beta_content_block_source: object` - `type: "content"` - `content: string or array of BetaContentBlockSourceContent` - `union_member_0: string` - `beta_content_block_source_content: array of BetaContentBlockSourceContent` - `beta_text_block_param: object` - `type: "text"` - `text: string` minLength: 1 - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `"5m"` - `"1h"` - `citations: optional array of BetaTextCitationParam` - `beta_citation_char_location_param: object` - `type: "char_location"` - `cited_text: string` - `document_index: number` minimum: 0 - `document_title: string` minLength: 1, maxLength: 500 - `end_char_index: number` - `start_char_index: number` minimum: 0 - `beta_citation_page_location_param: object` - `type: "page_location"` - `cited_text: string` - `document_index: number` minimum: 0 - `document_title: string` minLength: 1, maxLength: 500 - `end_page_number: number` - `start_page_number: number` minimum: 1 - `beta_citation_content_block_location_param: object` - `type: "content_block_location"` - `cited_text: string` The full text of the cited block range, concatenated. Always equals the contents of `content[start_block_index:end_block_index]` joined together. The text block is the minimal citable unit; this field is never a substring of a single block. Not counted toward output tokens, and not counted toward input tokens when sent back in subsequent turns. - `document_index: number` minimum: 0 - `document_title: string` minLength: 1, maxLength: 500 - `end_block_index: number` Exclusive 0-based end index of the cited block range in the source's `content` array. Always greater than `start_block_index`; a single-block citation has `end_block_index = start_block_index + 1`. - `start_block_index: number` 0-based index of the first cited block in the source's `content` array. minimum: 0 - `beta_citation_web_search_result_location_param: object` - `type: "web_search_result_location"` - `cited_text: string` - `encrypted_index: string` - `title: string` minLength: 1, maxLength: 512 - `url: string` minLength: 1 - `beta_citation_search_result_location_param: object` - `type: "search_result_location"` - `cited_text: string` The full text of the cited block range, concatenated. Always equals the contents of `content[start_block_index:end_block_index]` joined together. The text block is the minimal citable unit; this field is never a substring of a single block. Not counted toward output tokens, and not counted toward input tokens when sent back in subsequent turns. - `end_block_index: number` Exclusive 0-based end index of the cited block range in the source's `content` array. Always greater than `start_block_index`; a single-block citation has `end_block_index = start_block_index + 1`. - `search_result_index: number` 0-based index of the cited search result among all `search_result` content blocks in the request, in the order they appear across messages and tool results. Counted separately from `document_index`; server-side web search results are not included in this count. minimum: 0 - `source: string` - `start_block_index: number` 0-based index of the first cited block in the source's `content` array. minimum: 0 - `title: string` - `beta_image_block_param: object` - `type: "image"` - `source: BetaBase64ImageSource or BetaURLImageSource or BetaFileImageSource` - `beta_base64_image_source: object` - `type: "base64"` - `data: string` format: byte - `media_type: "image/jpeg" or "image/png" or "image/gif" or "image/webp"` - `"image/jpeg"` - `"image/png"` - `"image/gif"` - `"image/webp"` - `beta_url_image_source: object` - `type: "url"` - `url: string` - `beta_file_image_source: object` - `type: "file"` - `file_id: string` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `transformations: optional object` Configures the transformations the server applies to this image before the model observes it. Each key names a condition the server transforms images for; its value selects the transformation applied. Omitted keys keep their default behavior, and an empty object is equivalent to omitting the field. - `oversized_image: optional "downsize" or "error"` What the server does when this image exceeds the model's maximum image size. `"downsize"` (the default) scales the image down to fit, which changes the dimensions the model observes without telling you. `"error"` instead rejects the request with a 400 error naming the image's dimensions and the largest dimensions that fit, so you can scale the image deliberately — your image is never silently scaled down. - `"downsize"` - `"error"` - `beta_url_pdf_source: object` - `type: "url"` - `url: string` - `beta_file_document_source: object` - `type: "file"` - `file_id: string` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `citations: optional object` - `enabled: optional boolean` - `context: optional string` minLength: 1 - `title: optional string` minLength: 1, maxLength: 500 - `url: string` Fetched content URL - `retrieved_at: optional string` ISO 8601 timestamp when the content was retrieved - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` - `beta_direct_caller: object` Tool invocation directly from the model. - `type: "direct"` - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `type: "code_execution_20250825"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `beta_server_tool_caller_20260120: object` - `type: "code_execution_20260120"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ ### Beta Web Fetch Tool Result Error Block - `beta_web_fetch_tool_result_error_block: object` - `type: "web_fetch_tool_result_error"` - `error_code: "invalid_tool_input" or "url_too_long" or "url_not_allowed" or 7 more` - `"invalid_tool_input"` - `"url_too_long"` - `"url_not_allowed"` - `"url_not_in_prior_context"` - `"url_not_accessible"` - `"unsupported_content_type"` - `"too_many_requests"` - `"max_uses_exceeded"` - `"unavailable"` - `"content_too_large"` ### Beta Web Fetch Tool Result Error Block Param - `beta_web_fetch_tool_result_error_block_param: object` - `type: "web_fetch_tool_result_error"` - `error_code: "invalid_tool_input" or "url_too_long" or "url_not_allowed" or 7 more` - `"invalid_tool_input"` - `"url_too_long"` - `"url_not_allowed"` - `"url_not_in_prior_context"` - `"url_not_accessible"` - `"unsupported_content_type"` - `"too_many_requests"` - `"max_uses_exceeded"` - `"unavailable"` - `"content_too_large"` ### Beta Web Fetch Tool Result Error Code - `beta_web_fetch_tool_result_error_code: "invalid_tool_input" or "url_too_long" or "url_not_allowed" or 7 more` - `"invalid_tool_input"` - `"url_too_long"` - `"url_not_allowed"` - `"url_not_in_prior_context"` - `"url_not_accessible"` - `"unsupported_content_type"` - `"too_many_requests"` - `"max_uses_exceeded"` - `"unavailable"` - `"content_too_large"` ### Beta Web Fetch URL Source All - `beta_web_fetch_url_source_all: object` The `url_sources` variant under which a source contributes in full: every result of the tool filter's source, or all user input. - `type: "all"` ### Beta Web Fetch URL Source Except - `beta_web_fetch_url_source_except: object` The tool filter variant under which every result but the named tools' contributes. - `type: "except"` - `tools: array of BetaWebFetchURLSourceToolReference` - `type: "tool_reference"` - `name: string` ### Beta Web Fetch URL Source None - `beta_web_fetch_url_source_none: object` The `url_sources` variant under which a source contributes nothing: no result of the tool filter's source, or no user input. - `type: "none"` ### Beta Web Fetch URL Source Only - `beta_web_fetch_url_source_only: object` The tool filter variant under which only the named tools' results contribute. - `type: "only"` - `tools: array of BetaWebFetchURLSourceToolReference` - `type: "tool_reference"` - `name: string` ### Beta Web Fetch URL Source Tool Reference - `beta_web_fetch_url_source_tool_reference: object` One entry of a tool filter's `tools`: it must name a tool declared in this request's `tools[]`. - `type: "tool_reference"` - `name: string` ### Beta Web Fetch URL Sources - `beta_web_fetch_url_sources: object` Which sources contribute to the set of URLs web fetch may fetch. Each key is a tagged variant: `user_input` is `all` or `none`; the two tool filters are `all`, `none`, `only` (only the named tools' results) or `except` (every result but the named tools'). A named tool must be declared in this request's `tools[]`. - `client_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which client tools' results contribute fetchable URLs: "all", "none", or an only or except list of client tool names from tools[]. - `beta_web_fetch_url_source_all: object` The `url_sources` variant under which a source contributes in full: every result of the tool filter's source, or all user input. - `type: "all"` - `beta_web_fetch_url_source_none: object` The `url_sources` variant under which a source contributes nothing: no result of the tool filter's source, or no user input. - `type: "none"` - `beta_web_fetch_url_source_only: object` The tool filter variant under which only the named tools' results contribute. - `type: "only"` - `tools: array of BetaWebFetchURLSourceToolReference` - `type: "tool_reference"` - `name: string` - `beta_web_fetch_url_source_except: object` The tool filter variant under which every result but the named tools' contributes. - `type: "except"` - `tools: array of BetaWebFetchURLSourceToolReference` - `type: "tool_reference"` - `name: string` - `server_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which server tools' results contribute fetchable URLs: "all", "none", or an only or except list of server tool names from tools[]; only web_search and web_fetch results ever contribute. - `beta_web_fetch_url_source_all: object` The `url_sources` variant under which a source contributes in full: every result of the tool filter's source, or all user input. - `beta_web_fetch_url_source_none: object` The `url_sources` variant under which a source contributes nothing: no result of the tool filter's source, or no user input. - `beta_web_fetch_url_source_only: object` The tool filter variant under which only the named tools' results contribute. - `beta_web_fetch_url_source_except: object` The tool filter variant under which every result but the named tools' contributes. - `user_input: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone` Whether URLs in user messages are fetchable: "all" or "none". - `beta_web_fetch_url_source_all: object` The `url_sources` variant under which a source contributes in full: every result of the tool filter's source, or all user input. - `beta_web_fetch_url_source_none: object` The `url_sources` variant under which a source contributes nothing: no result of the tool filter's source, or no user input. ### Beta Web Search Result Block - `beta_web_search_result_block: object` - `type: "web_search_result"` - `encrypted_content: string` - `page_age: string` - `title: string` - `url: string` ### Beta Web Search Result Block Param - `beta_web_search_result_block_param: object` - `type: "web_search_result"` - `encrypted_content: string` - `title: string` - `url: string` - `page_age: optional string` ### Beta Web Search Tool 20250305 - `beta_web_search_tool_20250305: object` - `type: "web_search_20250305"` - `name: "web_search"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: optional array of string` If provided, only these domains will be included in results. Cannot be used alongside `blocked_domains`. - `blocked_domains: optional array of string` If provided, these domains will never appear in results. Cannot be used alongside `allowed_domains`. - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `"5m"` - `"1h"` - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `user_location: optional object` Parameters for the user's location. Used to provide more relevant search results. - `type: "approximate"` - `city: optional string` The city of the user. minLength: 1, maxLength: 255 - `country: optional string` The two letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1_alpha-2) of the user. minLength: 2, maxLength: 2 - `region: optional string` The region of the user. minLength: 1, maxLength: 255 - `timezone: optional string` The [IANA timezone](https://nodatime.org/TimeZones) of the user. minLength: 1, maxLength: 255 ### Beta Web Search Tool 20260209 - `beta_web_search_tool_20260209: object` - `type: "web_search_20260209"` - `name: "web_search"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: optional array of string` If provided, only these domains will be included in results. Cannot be used alongside `blocked_domains`. - `blocked_domains: optional array of string` If provided, these domains will never appear in results. Cannot be used alongside `allowed_domains`. - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `"5m"` - `"1h"` - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `user_location: optional object` Parameters for the user's location. Used to provide more relevant search results. - `type: "approximate"` - `city: optional string` The city of the user. minLength: 1, maxLength: 255 - `country: optional string` The two letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1_alpha-2) of the user. minLength: 2, maxLength: 2 - `region: optional string` The region of the user. minLength: 1, maxLength: 255 - `timezone: optional string` The [IANA timezone](https://nodatime.org/TimeZones) of the user. minLength: 1, maxLength: 255 ### Beta Web Search Tool 20260318 - `beta_web_search_tool_20260318: object` - `type: "web_search_20260318"` - `name: "web_search"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: optional array of string` If provided, only these domains will be included in results. Cannot be used alongside `blocked_domains`. - `blocked_domains: optional array of string` If provided, these domains will never appear in results. Cannot be used alongside `allowed_domains`. - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `"5m"` - `"1h"` - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `response_inclusion: optional "full" or "excluded"` How this tool's result blocks appear in the API response when the result was consumed by a completed code_execution call in the same turn. 'full' returns the complete content (default). 'excluded' drops the nested server_tool_use and result block pair entirely. Results from direct calls, or from code_execution calls that paused before completing, are always returned in full so they can be sent back on the next turn. - `"full"` - `"excluded"` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `user_location: optional object` Parameters for the user's location. Used to provide more relevant search results. - `type: "approximate"` - `city: optional string` The city of the user. minLength: 1, maxLength: 255 - `country: optional string` The two letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1_alpha-2) of the user. minLength: 2, maxLength: 2 - `region: optional string` The region of the user. minLength: 1, maxLength: 255 - `timezone: optional string` The [IANA timezone](https://nodatime.org/TimeZones) of the user. minLength: 1, maxLength: 255 ### Beta Web Search Tool Request Error - `beta_web_search_tool_request_error: object` - `type: "web_search_tool_result_error"` - `error_code: "invalid_tool_input" or "unavailable" or "max_uses_exceeded" or 3 more` - `"invalid_tool_input"` - `"unavailable"` - `"max_uses_exceeded"` - `"too_many_requests"` - `"query_too_long"` - `"request_too_large"` ### Beta Web Search Tool Result Block - `beta_web_search_tool_result_block: object` - `type: "web_search_tool_result"` - `content: BetaWebSearchToolResultError or array of BetaWebSearchResultBlock` - `beta_web_search_tool_result_error: object` - `type: "web_search_tool_result_error"` - `error_code: "invalid_tool_input" or "unavailable" or "max_uses_exceeded" or 3 more` - `"invalid_tool_input"` - `"unavailable"` - `"max_uses_exceeded"` - `"too_many_requests"` - `"query_too_long"` - `"request_too_large"` - `union_member_1: array of BetaWebSearchResultBlock` - `type: "web_search_result"` - `encrypted_content: string` - `page_age: string` - `title: string` - `url: string` - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` - `beta_direct_caller: object` Tool invocation directly from the model. - `type: "direct"` - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `type: "code_execution_20250825"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `beta_server_tool_caller_20260120: object` - `type: "code_execution_20260120"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ ### Beta Web Search Tool Result Block Content - `beta_web_search_tool_result_block_content: BetaWebSearchToolResultError or array of BetaWebSearchResultBlock` - `beta_web_search_tool_result_error: object` - `type: "web_search_tool_result_error"` - `error_code: "invalid_tool_input" or "unavailable" or "max_uses_exceeded" or 3 more` - `"invalid_tool_input"` - `"unavailable"` - `"max_uses_exceeded"` - `"too_many_requests"` - `"query_too_long"` - `"request_too_large"` - `union_member_1: array of BetaWebSearchResultBlock` - `type: "web_search_result"` - `encrypted_content: string` - `page_age: string` - `title: string` - `url: string` ### Beta Web Search Tool Result Block Param - `beta_web_search_tool_result_block_param: object` - `type: "web_search_tool_result"` - `content: array of BetaWebSearchResultBlockParam or BetaWebSearchToolRequestError` - `Result Block: array of BetaWebSearchResultBlockParam` - `type: "web_search_result"` - `encrypted_content: string` - `title: string` - `url: string` - `page_age: optional string` - `beta_web_search_tool_request_error: object` - `type: "web_search_tool_result_error"` - `error_code: "invalid_tool_input" or "unavailable" or "max_uses_exceeded" or 3 more` - `"invalid_tool_input"` - `"unavailable"` - `"max_uses_exceeded"` - `"too_many_requests"` - `"query_too_long"` - `"request_too_large"` - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `"5m"` - `"1h"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` - `beta_direct_caller: object` Tool invocation directly from the model. - `type: "direct"` - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `type: "code_execution_20250825"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `beta_server_tool_caller_20260120: object` - `type: "code_execution_20260120"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ ### Beta Web Search Tool Result Block Param Content - `beta_web_search_tool_result_block_param_content: array of BetaWebSearchResultBlockParam or BetaWebSearchToolRequestError` - `Result Block: array of BetaWebSearchResultBlockParam` - `type: "web_search_result"` - `encrypted_content: string` - `title: string` - `url: string` - `page_age: optional string` - `beta_web_search_tool_request_error: object` - `type: "web_search_tool_result_error"` - `error_code: "invalid_tool_input" or "unavailable" or "max_uses_exceeded" or 3 more` - `"invalid_tool_input"` - `"unavailable"` - `"max_uses_exceeded"` - `"too_many_requests"` - `"query_too_long"` - `"request_too_large"` ### Beta Web Search Tool Result Error - `beta_web_search_tool_result_error: object` - `type: "web_search_tool_result_error"` - `error_code: "invalid_tool_input" or "unavailable" or "max_uses_exceeded" or 3 more` - `"invalid_tool_input"` - `"unavailable"` - `"max_uses_exceeded"` - `"too_many_requests"` - `"query_too_long"` - `"request_too_large"` ### Beta Web Search Tool Result Error Code - `beta_web_search_tool_result_error_code: "invalid_tool_input" or "unavailable" or "max_uses_exceeded" or 3 more` - `"invalid_tool_input"` - `"unavailable"` - `"max_uses_exceeded"` - `"too_many_requests"` - `"query_too_long"` - `"request_too_large"` ## Messages › Batches ### Create a Message Batch `$ ant beta:messages:batches create` **POST** `/v1/messages/batches` Send a batch of Message creation requests. The Message Batches API can be used to process multiple Messages API requests at once. Once a Message Batch is created, it begins processing immediately. Batches can take up to 24 hours to complete. Learn more about the Message Batches API in our [user guide](https://platform.claude.com/docs/en/build-with-claude/batch-processing?sdk_languages=cli) #### Parameters - `--request: array of object` List of requests for prompt completion. Each is an individual request to create a Message. minItems: 1, maxItems: 100000 - `--beta: optional array of AnthropicBeta` (header parameter) Optional header to specify the beta version(s) you want to use. - `--user-profile-id: optional string` (header parameter) The user profile ID to attribute the requests in this batch to. Use when acting on behalf of a party other than your organization. Requires the `user-profiles` beta header. Applies to every request in the batch; an individual request whose `user_profile_id` body field conflicts with this header is errored. - `--workspace-id: optional string` (header parameter) Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`). Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace. #### Returns - `beta_message_batch: object` - `type: "message_batch"` Object type. For Message Batches, this is always `"message_batch"`. - `id: string` Unique object identifier. The format and length of IDs may change over time. - `archived_at: string` RFC 3339 datetime string representing the time at which the Message Batch was archived and its results became unavailable. format: date-time - `cancel_initiated_at: string` RFC 3339 datetime string representing the time at which cancellation was initiated for the Message Batch. Specified only if cancellation was initiated. format: date-time - `created_at: string` RFC 3339 datetime string representing the time at which the Message Batch was created. format: date-time - `ended_at: string` RFC 3339 datetime string representing the time at which processing for the Message Batch ended. Specified only once processing ends. Processing ends when every request in a Message Batch has either succeeded, errored, canceled, or expired. format: date-time - `expires_at: string` RFC 3339 datetime string representing the time at which the Message Batch will expire and end processing, which is 24 hours after creation. format: date-time - `processing_status: "in_progress" or "canceling" or "ended"` Processing status of the Message Batch. - `"in_progress"` - `"canceling"` - `"ended"` - `request_counts: object` Tallies requests within the Message Batch, categorized by their status. Requests start as `processing` and move to one of the other statuses only once processing of the entire batch ends. The sum of all values always matches the total number of requests in the batch. - `canceled: number` Number of requests in the Message Batch that have been canceled. This is zero until processing of the entire Message Batch has ended. - `errored: number` Number of requests in the Message Batch that encountered an error. This is zero until processing of the entire Message Batch has ended. - `expired: number` Number of requests in the Message Batch that have expired. This is zero until processing of the entire Message Batch has ended. - `processing: number` Number of requests in the Message Batch that are processing. - `succeeded: number` Number of requests in the Message Batch that have completed successfully. This is zero until processing of the entire Message Batch has ended. - `results_url: string` URL to a `.jsonl` file containing the results of the Message Batch requests. Specified only once processing ends. Results in the file are not guaranteed to be in the same order as requests. Use the `custom_id` field to match results to requests. #### Example ```bash ant beta:messages:batches create \ --api-key my-anthropic-api-key \ --request '{custom_id: my-custom-id-1, params: {max_tokens: 1024, messages: [{content: [{text: x, type: text}], role: user}], model: claude-opus-5-5}}' ``` ##### Response (200) ```json { "id": "msgbatch_013Zva2CMHLNnXjNJJKqJ2EF", "archived_at": "2024-08-20T18:37:24.100435Z", "cancel_initiated_at": "2024-08-20T18:37:24.100435Z", "created_at": "2024-08-20T18:37:24.100435Z", "ended_at": "2024-08-20T18:37:24.100435Z", "expires_at": "2024-08-20T18:37:24.100435Z", "processing_status": "in_progress", "request_counts": { "canceled": 10, "errored": 30, "expired": 10, "processing": 100, "succeeded": 50 }, "results_url": "https://api.anthropic.com/v1/messages/batches/msgbatch_013Zva2CMHLNnXjNJJKqJ2EF/results", "type": "message_batch" } ``` ### Retrieve a Message Batch `$ ant beta:messages:batches retrieve` **GET** `/v1/messages/batches/{message_batch_id}` This endpoint is idempotent and can be used to poll for Message Batch completion. To access the results of a Message Batch, make a request to the `results_url` field in the response. Learn more about the Message Batches API in our [user guide](https://platform.claude.com/docs/en/build-with-claude/batch-processing?sdk_languages=cli) #### Parameters - `--message-batch-id: string` (path parameter) ID of the Message Batch. - `--beta: optional array of AnthropicBeta` (header parameter) Optional header to specify the beta version(s) you want to use. - `--workspace-id: optional string` (header parameter) Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`). Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace. #### Returns - `beta_message_batch: object` - `type: "message_batch"` Object type. For Message Batches, this is always `"message_batch"`. - `id: string` Unique object identifier. The format and length of IDs may change over time. - `archived_at: string` RFC 3339 datetime string representing the time at which the Message Batch was archived and its results became unavailable. format: date-time - `cancel_initiated_at: string` RFC 3339 datetime string representing the time at which cancellation was initiated for the Message Batch. Specified only if cancellation was initiated. format: date-time - `created_at: string` RFC 3339 datetime string representing the time at which the Message Batch was created. format: date-time - `ended_at: string` RFC 3339 datetime string representing the time at which processing for the Message Batch ended. Specified only once processing ends. Processing ends when every request in a Message Batch has either succeeded, errored, canceled, or expired. format: date-time - `expires_at: string` RFC 3339 datetime string representing the time at which the Message Batch will expire and end processing, which is 24 hours after creation. format: date-time - `processing_status: "in_progress" or "canceling" or "ended"` Processing status of the Message Batch. - `"in_progress"` - `"canceling"` - `"ended"` - `request_counts: object` Tallies requests within the Message Batch, categorized by their status. Requests start as `processing` and move to one of the other statuses only once processing of the entire batch ends. The sum of all values always matches the total number of requests in the batch. - `canceled: number` Number of requests in the Message Batch that have been canceled. This is zero until processing of the entire Message Batch has ended. - `errored: number` Number of requests in the Message Batch that encountered an error. This is zero until processing of the entire Message Batch has ended. - `expired: number` Number of requests in the Message Batch that have expired. This is zero until processing of the entire Message Batch has ended. - `processing: number` Number of requests in the Message Batch that are processing. - `succeeded: number` Number of requests in the Message Batch that have completed successfully. This is zero until processing of the entire Message Batch has ended. - `results_url: string` URL to a `.jsonl` file containing the results of the Message Batch requests. Specified only once processing ends. Results in the file are not guaranteed to be in the same order as requests. Use the `custom_id` field to match results to requests. #### Example ```bash ant beta:messages:batches retrieve \ --api-key my-anthropic-api-key \ --message-batch-id message_batch_id ``` ##### Response (200) ```json { "id": "msgbatch_013Zva2CMHLNnXjNJJKqJ2EF", "archived_at": "2024-08-20T18:37:24.100435Z", "cancel_initiated_at": "2024-08-20T18:37:24.100435Z", "created_at": "2024-08-20T18:37:24.100435Z", "ended_at": "2024-08-20T18:37:24.100435Z", "expires_at": "2024-08-20T18:37:24.100435Z", "processing_status": "in_progress", "request_counts": { "canceled": 10, "errored": 30, "expired": 10, "processing": 100, "succeeded": 50 }, "results_url": "https://api.anthropic.com/v1/messages/batches/msgbatch_013Zva2CMHLNnXjNJJKqJ2EF/results", "type": "message_batch" } ``` ### List Message Batches `$ ant beta:messages:batches list` **GET** `/v1/messages/batches` List all Message Batches within a Workspace. Most recently created batches are returned first. Learn more about the Message Batches API in our [user guide](https://platform.claude.com/docs/en/build-with-claude/batch-processing?sdk_languages=cli) #### Parameters - `--after-id: optional string` (query parameter) ID of the object to use as a cursor for pagination. When provided, returns the page of results immediately after this object. - `--before-id: optional string` (query parameter) ID of the object to use as a cursor for pagination. When provided, returns the page of results immediately before this object. - `--limit: optional number` (query parameter) Number of items to return per page. Defaults to `20`. Ranges from `1` to `1000`. minimum: 1, maximum: 1000 - `--beta: optional array of AnthropicBeta` (header parameter) Optional header to specify the beta version(s) you want to use. - `--workspace-id: optional string` (header parameter) Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`). Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace. #### Returns - `BetaListResponse_MessageBatch_: object` - `data: array of BetaMessageBatch` - `type: "message_batch"` Object type. For Message Batches, this is always `"message_batch"`. - `id: string` Unique object identifier. The format and length of IDs may change over time. - `archived_at: string` RFC 3339 datetime string representing the time at which the Message Batch was archived and its results became unavailable. format: date-time - `cancel_initiated_at: string` RFC 3339 datetime string representing the time at which cancellation was initiated for the Message Batch. Specified only if cancellation was initiated. format: date-time - `created_at: string` RFC 3339 datetime string representing the time at which the Message Batch was created. format: date-time - `ended_at: string` RFC 3339 datetime string representing the time at which processing for the Message Batch ended. Specified only once processing ends. Processing ends when every request in a Message Batch has either succeeded, errored, canceled, or expired. format: date-time - `expires_at: string` RFC 3339 datetime string representing the time at which the Message Batch will expire and end processing, which is 24 hours after creation. format: date-time - `processing_status: "in_progress" or "canceling" or "ended"` Processing status of the Message Batch. - `"in_progress"` - `"canceling"` - `"ended"` - `request_counts: object` Tallies requests within the Message Batch, categorized by their status. Requests start as `processing` and move to one of the other statuses only once processing of the entire batch ends. The sum of all values always matches the total number of requests in the batch. - `canceled: number` Number of requests in the Message Batch that have been canceled. This is zero until processing of the entire Message Batch has ended. - `errored: number` Number of requests in the Message Batch that encountered an error. This is zero until processing of the entire Message Batch has ended. - `expired: number` Number of requests in the Message Batch that have expired. This is zero until processing of the entire Message Batch has ended. - `processing: number` Number of requests in the Message Batch that are processing. - `succeeded: number` Number of requests in the Message Batch that have completed successfully. This is zero until processing of the entire Message Batch has ended. - `results_url: string` URL to a `.jsonl` file containing the results of the Message Batch requests. Specified only once processing ends. Results in the file are not guaranteed to be in the same order as requests. Use the `custom_id` field to match results to requests. - `first_id: string` First ID in the `data` list. Can be used as the `before_id` for the previous page. - `has_more: boolean` Indicates if there are more results in the requested page direction. - `last_id: string` Last ID in the `data` list. Can be used as the `after_id` for the next page. #### Example ```bash ant beta:messages:batches list \ --api-key my-anthropic-api-key ``` ##### Response (200) ```json { "data": [ { "id": "msgbatch_013Zva2CMHLNnXjNJJKqJ2EF", "archived_at": "2024-08-20T18:37:24.100435Z", "cancel_initiated_at": "2024-08-20T18:37:24.100435Z", "created_at": "2024-08-20T18:37:24.100435Z", "ended_at": "2024-08-20T18:37:24.100435Z", "expires_at": "2024-08-20T18:37:24.100435Z", "processing_status": "in_progress", "request_counts": { "canceled": 10, "errored": 30, "expired": 10, "processing": 100, "succeeded": 50 }, "results_url": "https://api.anthropic.com/v1/messages/batches/msgbatch_013Zva2CMHLNnXjNJJKqJ2EF/results", "type": "message_batch" } ], "first_id": "first_id", "has_more": true, "last_id": "last_id" } ``` ### Cancel a Message Batch `$ ant beta:messages:batches cancel` **POST** `/v1/messages/batches/{message_batch_id}/cancel` Batches may be canceled any time before processing ends. Once cancellation is initiated, the batch enters a `canceling` state, at which time the system may complete any in-progress, non-interruptible requests before finalizing cancellation. The number of canceled requests is specified in `request_counts`. To determine which requests were canceled, check the individual results within the batch. Note that cancellation may not result in any canceled requests if they were non-interruptible. Learn more about the Message Batches API in our [user guide](https://platform.claude.com/docs/en/build-with-claude/batch-processing?sdk_languages=cli) #### Parameters - `--message-batch-id: string` (path parameter) ID of the Message Batch. - `--beta: optional array of AnthropicBeta` (header parameter) Optional header to specify the beta version(s) you want to use. - `--workspace-id: optional string` (header parameter) Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`). Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace. #### Returns - `beta_message_batch: object` - `type: "message_batch"` Object type. For Message Batches, this is always `"message_batch"`. - `id: string` Unique object identifier. The format and length of IDs may change over time. - `archived_at: string` RFC 3339 datetime string representing the time at which the Message Batch was archived and its results became unavailable. format: date-time - `cancel_initiated_at: string` RFC 3339 datetime string representing the time at which cancellation was initiated for the Message Batch. Specified only if cancellation was initiated. format: date-time - `created_at: string` RFC 3339 datetime string representing the time at which the Message Batch was created. format: date-time - `ended_at: string` RFC 3339 datetime string representing the time at which processing for the Message Batch ended. Specified only once processing ends. Processing ends when every request in a Message Batch has either succeeded, errored, canceled, or expired. format: date-time - `expires_at: string` RFC 3339 datetime string representing the time at which the Message Batch will expire and end processing, which is 24 hours after creation. format: date-time - `processing_status: "in_progress" or "canceling" or "ended"` Processing status of the Message Batch. - `"in_progress"` - `"canceling"` - `"ended"` - `request_counts: object` Tallies requests within the Message Batch, categorized by their status. Requests start as `processing` and move to one of the other statuses only once processing of the entire batch ends. The sum of all values always matches the total number of requests in the batch. - `canceled: number` Number of requests in the Message Batch that have been canceled. This is zero until processing of the entire Message Batch has ended. - `errored: number` Number of requests in the Message Batch that encountered an error. This is zero until processing of the entire Message Batch has ended. - `expired: number` Number of requests in the Message Batch that have expired. This is zero until processing of the entire Message Batch has ended. - `processing: number` Number of requests in the Message Batch that are processing. - `succeeded: number` Number of requests in the Message Batch that have completed successfully. This is zero until processing of the entire Message Batch has ended. - `results_url: string` URL to a `.jsonl` file containing the results of the Message Batch requests. Specified only once processing ends. Results in the file are not guaranteed to be in the same order as requests. Use the `custom_id` field to match results to requests. #### Example ```bash ant beta:messages:batches cancel \ --api-key my-anthropic-api-key \ --message-batch-id message_batch_id ``` ##### Response (200) ```json { "id": "msgbatch_013Zva2CMHLNnXjNJJKqJ2EF", "archived_at": "2024-08-20T18:37:24.100435Z", "cancel_initiated_at": "2024-08-20T18:37:24.100435Z", "created_at": "2024-08-20T18:37:24.100435Z", "ended_at": "2024-08-20T18:37:24.100435Z", "expires_at": "2024-08-20T18:37:24.100435Z", "processing_status": "in_progress", "request_counts": { "canceled": 10, "errored": 30, "expired": 10, "processing": 100, "succeeded": 50 }, "results_url": "https://api.anthropic.com/v1/messages/batches/msgbatch_013Zva2CMHLNnXjNJJKqJ2EF/results", "type": "message_batch" } ``` ### Delete a Message Batch `$ ant beta:messages:batches delete` **DELETE** `/v1/messages/batches/{message_batch_id}` Delete a Message Batch. Message Batches can only be deleted once they've finished processing. If you'd like to delete an in-progress batch, you must first cancel it. Learn more about the Message Batches API in our [user guide](https://platform.claude.com/docs/en/build-with-claude/batch-processing?sdk_languages=cli) #### Parameters - `--message-batch-id: string` (path parameter) ID of the Message Batch. - `--beta: optional array of AnthropicBeta` (header parameter) Optional header to specify the beta version(s) you want to use. - `--workspace-id: optional string` (header parameter) Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`). Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace. #### Returns - `beta_deleted_message_batch: object` - `type: "message_batch_deleted"` Deleted object type. For Message Batches, this is always `"message_batch_deleted"`. - `id: string` ID of the Message Batch. #### Example ```bash ant beta:messages:batches delete \ --api-key my-anthropic-api-key \ --message-batch-id message_batch_id ``` ##### Response (200) ```json { "id": "msgbatch_013Zva2CMHLNnXjNJJKqJ2EF", "type": "message_batch_deleted" } ``` ### Retrieve Message Batch results `$ ant beta:messages:batches results` **GET** `/v1/messages/batches/{message_batch_id}/results` Streams the results of a Message Batch as a `.jsonl` file. Each line in the file is a JSON object containing the result of a single request in the Message Batch. Results are not guaranteed to be in the same order as requests. Use the `custom_id` field to match results to requests. Learn more about the Message Batches API in our [user guide](https://platform.claude.com/docs/en/build-with-claude/batch-processing?sdk_languages=cli) #### Parameters - `--message-batch-id: string` (path parameter) ID of the Message Batch. - `--beta: optional array of AnthropicBeta` (header parameter) Optional header to specify the beta version(s) you want to use. - `--workspace-id: optional string` (header parameter) Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`). Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace. #### Returns - `beta_message_batch_individual_response: object` This is a single line in the response `.jsonl` file and does not represent the response as a whole. - `custom_id: string` Developer-provided ID created for each request in a Message Batch. Useful for matching results to requests, as results may be given out of request order. Must be unique for each request within the Message Batch. - `result: BetaMessageBatchSucceededResult or BetaMessageBatchErroredResult or BetaMessageBatchCanceledResult or BetaMessageBatchExpiredResult` Processing result for this request. Contains a Message output if processing was successful, an error response if processing failed, or the reason why processing was not attempted, such as cancellation or expiration. - `beta_message_batch_succeeded_result: object` - `type: "succeeded"` - `message: object` - `type: "message"` Object type. For Messages, this is always `"message"`. - `id: string` Unique object identifier. The format and length of IDs may change over time. - `container: object` Information about the container used in this request. This will be non-null if a container tool (e.g. code execution) was used. - `id: string` Identifier for the container used in this request - `expires_at: string` The time at which the container will expire. format: date-time - `skills: array of BetaContainerSkill` Skills loaded in the container - `type: "anthropic" or "custom"` Type of skill - either 'anthropic' (built-in) or 'custom' (user-defined) - `"anthropic"` - `"custom"` - `skill_id: string` Skill ID minLength: 1, maxLength: 64 - `version: string` The resolved version: a skill version ID for custom skills. minLength: 1, maxLength: 64 - `content: array of BetaContentBlock` Content generated by the model. This is an array of content blocks, each of which has a `type` that determines its shape. Example: ```json [{"type": "text", "text": "Hi, I'm Claude."}] ``` If the request input `messages` ended with an `assistant` turn, then the response `content` will continue directly from that last turn. You can use this to constrain the model's output. For example, if the input `messages` were: ```json [ {"role": "user", "content": "What's the Greek name for Sun? (A) Sol (B) Helios (C) Sun"}, {"role": "assistant", "content": "The best answer is ("} ] ``` Then the response `content` might be: ```json [{"type": "text", "text": "B)"}] ``` - `beta_text_block: object` - `type: "text"` - `citations: array of BetaTextCitation` Citations supporting the text block. The type of citation returned will depend on the type of document being cited. Citing a PDF results in `page_location`, plain text results in `char_location`, and content document results in `content_block_location`. - `beta_citation_char_location: object` - `type: "char_location"` - `cited_text: string` - `document_index: number` minimum: 0 - `document_title: string` - `end_char_index: number` - `file_id: string` - `start_char_index: number` minimum: 0 - `beta_citation_page_location: object` - `type: "page_location"` - `cited_text: string` - `document_index: number` minimum: 0 - `document_title: string` - `end_page_number: number` - `file_id: string` - `start_page_number: number` minimum: 1 - `beta_citation_content_block_location: object` - `type: "content_block_location"` - `cited_text: string` The full text of the cited block range, concatenated. Always equals the contents of `content[start_block_index:end_block_index]` joined together. The text block is the minimal citable unit; this field is never a substring of a single block. Not counted toward output tokens, and not counted toward input tokens when sent back in subsequent turns. - `document_index: number` minimum: 0 - `document_title: string` - `end_block_index: number` Exclusive 0-based end index of the cited block range in the source's `content` array. Always greater than `start_block_index`; a single-block citation has `end_block_index = start_block_index + 1`. - `file_id: string` - `start_block_index: number` 0-based index of the first cited block in the source's `content` array. minimum: 0 - `beta_citations_web_search_result_location: object` - `type: "web_search_result_location"` - `cited_text: string` - `encrypted_index: string` - `title: string` maxLength: 512 - `url: string` - `beta_citation_search_result_location: object` - `type: "search_result_location"` - `cited_text: string` The full text of the cited block range, concatenated. Always equals the contents of `content[start_block_index:end_block_index]` joined together. The text block is the minimal citable unit; this field is never a substring of a single block. Not counted toward output tokens, and not counted toward input tokens when sent back in subsequent turns. - `end_block_index: number` Exclusive 0-based end index of the cited block range in the source's `content` array. Always greater than `start_block_index`; a single-block citation has `end_block_index = start_block_index + 1`. - `search_result_index: number` 0-based index of the cited search result among all `search_result` content blocks in the request, in the order they appear across messages and tool results. Counted separately from `document_index`; server-side web search results are not included in this count. minimum: 0 - `source: string` - `start_block_index: number` 0-based index of the first cited block in the source's `content` array. minimum: 0 - `title: string` - `text: string` - `beta_thinking_block: object` - `type: "thinking"` - `signature: string` A value used to verify that this thinking block was generated by Claude when it is passed back to the API. This is an opaque field and should not be interpreted or parsed. When passing thinking blocks back to the API (required when using tools with extended thinking), pass them back exactly as received, with this field intact. See [extended thinking](https://platform.claude.com/docs/en/build-with-claude/extended-thinking?sdk_languages=cli) for details. - `thinking: string` The text of Claude's thinking process for this block. - `beta_redacted_thinking_block: object` - `type: "redacted_thinking"` - `data: string` The contents of this redacted thinking block, returned when portions of the model's thinking were safety-redacted. This field is opaque and encrypted, with no readable content. Pass `redacted_thinking` blocks back to the API unchanged when continuing a multi-turn conversation. See [extended thinking](https://platform.claude.com/docs/en/build-with-claude/extended-thinking?sdk_languages=cli#redacted-thinking-blocks) for details. - `beta_tool_use_block: object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: map[unknown]` - `name: string` minLength: 1 - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` - `beta_direct_caller: object` Tool invocation directly from the model. - `type: "direct"` - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `type: "code_execution_20250825"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `beta_server_tool_caller_20260120: object` - `type: "code_execution_20260120"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `toolset_name: optional string` For a toolset member tool_use, the toolset family. minLength: 1, maxLength: 64, pattern: ^[a-zA-Z0-9_-]+$ - `beta_server_tool_use_block: object` - `type: "server_tool_use"` - `id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `input: map[unknown]` - `name: "advisor" or "web_search" or "web_fetch" or 5 more` - `"advisor"` - `"web_search"` - `"web_fetch"` - `"code_execution"` - `"bash_code_execution"` - `"text_editor_code_execution"` - `"tool_search_tool_regex"` - `"tool_search_tool_bm25"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` - `beta_direct_caller: object` Tool invocation directly from the model. - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `beta_server_tool_caller_20260120: object` - `beta_web_search_tool_result_block: object` - `type: "web_search_tool_result"` - `content: BetaWebSearchToolResultError or array of BetaWebSearchResultBlock` - `beta_web_search_tool_result_error: object` - `type: "web_search_tool_result_error"` - `error_code: "invalid_tool_input" or "unavailable" or "max_uses_exceeded" or 3 more` - `"invalid_tool_input"` - `"unavailable"` - `"max_uses_exceeded"` - `"too_many_requests"` - `"query_too_long"` - `"request_too_large"` - `union_member_1: array of BetaWebSearchResultBlock` - `type: "web_search_result"` - `encrypted_content: string` - `page_age: string` - `title: string` - `url: string` - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` - `beta_direct_caller: object` Tool invocation directly from the model. - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `beta_server_tool_caller_20260120: object` - `beta_web_fetch_tool_result_block: object` - `type: "web_fetch_tool_result"` - `content: BetaWebFetchToolResultErrorBlock or BetaWebFetchBlock` - `beta_web_fetch_tool_result_error_block: object` - `type: "web_fetch_tool_result_error"` - `error_code: "invalid_tool_input" or "url_too_long" or "url_not_allowed" or 7 more` - `"invalid_tool_input"` - `"url_too_long"` - `"url_not_allowed"` - `"url_not_in_prior_context"` - `"url_not_accessible"` - `"unsupported_content_type"` - `"too_many_requests"` - `"max_uses_exceeded"` - `"unavailable"` - `"content_too_large"` - `beta_web_fetch_block: object` - `type: "web_fetch_result"` - `content: object` - `type: "document"` - `citations: object` Citation configuration for the document - `enabled: boolean` - `source: BetaBase64PDFSource or BetaPlainTextSource` - `beta_base64_pdf_source: object` - `type: "base64"` - `data: string` format: byte - `media_type: "application/pdf"` - `beta_plain_text_source: object` - `type: "text"` - `data: string` - `media_type: "text/plain"` - `title: string` The title of the document - `retrieved_at: string` ISO 8601 timestamp when the content was retrieved - `url: string` Fetched content URL - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` - `beta_direct_caller: object` Tool invocation directly from the model. - `beta_server_tool_caller: object` Tool invocation generated by a server-side tool. - `beta_server_tool_caller_20260120: object` - `beta_advisor_tool_result_block: object` - `type: "advisor_tool_result"` - `content: BetaAdvisorToolResultError or BetaAdvisorResultBlock or BetaAdvisorRedactedResultBlock` - `beta_advisor_tool_result_error: object` - `type: "advisor_tool_result_error"` - `error_code: "max_uses_exceeded" or "prompt_too_long" or "too_many_requests" or 4 more` - `"max_uses_exceeded"` - `"prompt_too_long"` - `"too_many_requests"` - `"overloaded"` - `"unavailable"` - `"execution_time_exceeded"` - `"model_not_found"` - `beta_advisor_result_block: object` - `type: "advisor_result"` - `stop_reason: string` The advisor sub-inference's stop reason (same values as the top-level message `stop_reason`). `max_tokens` indicates the advisor's output was truncated at the tool's `max_tokens` value or the advisor model's policy cap. - `text: string` - `beta_advisor_redacted_result_block: object` - `type: "advisor_redacted_result"` - `encrypted_content: string` Opaque blob containing the advisor's output. Round-trip verbatim; do not inspect or modify. - `stop_reason: string` The advisor sub-inference's stop reason (same values as the top-level message `stop_reason`). - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `beta_code_execution_tool_result_block: object` - `type: "code_execution_tool_result"` - `content: BetaCodeExecutionToolResultError or BetaCodeExecutionResultBlock or BetaEncryptedCodeExecutionResultBlock` - `beta_code_execution_tool_result_error: object` - `type: "code_execution_tool_result_error"` - `error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or "execution_time_exceeded"` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `beta_code_execution_result_block: object` - `type: "code_execution_result"` - `content: array of BetaCodeExecutionOutputBlock` - `type: "code_execution_output"` - `file_id: string` - `return_code: number` - `stderr: string` - `stdout: string` - `beta_encrypted_code_execution_result_block: object` Code execution result with encrypted stdout for PFC + web_search results. - `type: "encrypted_code_execution_result"` - `content: array of BetaCodeExecutionOutputBlock` - `type: "code_execution_output"` - `file_id: string` - `encrypted_stdout: string` - `return_code: number` - `stderr: string` - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `beta_bash_code_execution_tool_result_block: object` - `type: "bash_code_execution_tool_result"` - `content: BetaBashCodeExecutionToolResultError or BetaBashCodeExecutionResultBlock` - `beta_bash_code_execution_tool_result_error: object` - `type: "bash_code_execution_tool_result_error"` - `error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or 2 more` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `"output_file_too_large"` - `beta_bash_code_execution_result_block: object` - `type: "bash_code_execution_result"` - `content: array of BetaBashCodeExecutionOutputBlock` - `type: "bash_code_execution_output"` - `file_id: string` - `return_code: number` - `stderr: string` - `stdout: string` - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `beta_text_editor_code_execution_tool_result_block: object` - `type: "text_editor_code_execution_tool_result"` - `content: BetaTextEditorCodeExecutionToolResultError or BetaTextEditorCodeExecutionViewResultBlock or BetaTextEditorCodeExecutionCreateResultBlock or BetaTextEditorCodeExecutionStrReplaceResultBlock` - `beta_text_editor_code_execution_tool_result_error: object` - `type: "text_editor_code_execution_tool_result_error"` - `error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or 2 more` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `"file_not_found"` - `error_message: string` - `beta_text_editor_code_execution_view_result_block: object` - `type: "text_editor_code_execution_view_result"` - `content: string` - `file_type: "text" or "image" or "pdf"` - `"text"` - `"image"` - `"pdf"` - `num_lines: number` - `start_line: number` - `total_lines: number` - `beta_text_editor_code_execution_create_result_block: object` - `type: "text_editor_code_execution_create_result"` - `is_file_update: boolean` - `beta_text_editor_code_execution_str_replace_result_block: object` - `type: "text_editor_code_execution_str_replace_result"` - `lines: array of string` - `new_lines: number` - `new_start: number` - `old_lines: number` - `old_start: number` - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `beta_tool_search_tool_result_block: object` - `type: "tool_search_tool_result"` - `content: BetaToolSearchToolResultError or BetaToolSearchToolSearchResultBlock` - `beta_tool_search_tool_result_error: object` - `type: "tool_search_tool_result_error"` - `error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or "execution_time_exceeded"` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `error_message: string` - `beta_tool_search_tool_search_result_block: object` - `type: "tool_search_tool_search_result"` - `tool_references: array of BetaToolReferenceBlock` - `type: "tool_reference"` - `tool_name: string` minLength: 1, maxLength: 256, pattern: ^[a-zA-Z0-9_-]{1,256}$ - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `beta_mcp_tool_use_block: object` - `type: "mcp_tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: map[unknown]` - `name: string` The name of the MCP tool - `server_name: string` The name of the MCP server - `beta_mcp_tool_result_block: object` - `type: "mcp_tool_result"` - `content: string or array of BetaTextBlock` - `union_member_0: string` - `beta_mcp_tool_result_block_content: array of BetaTextBlock` - `type: "text"` - `citations: array of BetaTextCitation` Citations supporting the text block. The type of citation returned will depend on the type of document being cited. Citing a PDF results in `page_location`, plain text results in `char_location`, and content document results in `content_block_location`. - `text: string` - `is_error: boolean` - `tool_use_id: string` pattern: ^[a-zA-Z0-9_-]+$ - `beta_container_upload_block: object` Response model for a file uploaded to the container. - `type: "container_upload"` - `file_id: string` - `beta_compaction_block: object` A compaction block returned when autocompact is triggered. When content is None, it indicates the compaction failed to produce a valid summary (e.g., malformed output from the model). Clients may round-trip compaction blocks with null content; the server treats them as no-ops. - `type: "compaction"` - `content: string` Summary of compacted content, or null if compaction failed - `encrypted_content: string` Opaque metadata from prior compaction, to be round-tripped verbatim - `signature: optional string` Signature over the summary, to be sent back with the block verbatim - `tool_changes: optional array of BetaResponseToolAdditionBlock or BetaResponseToolRemovalBlock` The tool changes of the compacted range: the `tool_addition` and `tool_removal` blocks that take the request's `tools` to the tool set in effect at the end of the range, or `[]` when the range changed no tool. Absent when the server did not compute them. Send the block back unchanged. - `beta_response_tool_addition_block: object` An entry of a `compaction` block's `tool_changes`: a tool the compacted range made available, as a reference to a `tools` entry or MCP toolset, or as the tool definition in effect at the end of the range, by value. Send it back unchanged. - `type: "tool_addition"` - `tool: BetaResponseToolChangeToolReference or BetaResponseToolChangeMCPToolReference or BetaResponseToolChangeMCPToolsetReference or BetaToolChangeToolDefinition` The tool made available: a reference to a `tools` entry or MCP toolset, or a `tool_definition` carrying the definition by value. - `beta_response_tool_change_tool_reference: object` Reference to a single tool, by the name the model uses to call it, as a `compaction` block's `tool_changes` entry reports it: a tool declared in `tools` or defined by an earlier `tool_addition` block. Send it back unchanged with the block. - `type: "tool_reference"` - `name: string` - `beta_response_tool_change_mcp_tool_reference: object` Reference to a single MCP tool, by its server and its name on that server, as a `compaction` block's `tool_changes` entry reports it. Send it back unchanged with the block. - `type: "mcp_tool_reference"` - `name: string` - `server_name: string` - `beta_response_tool_change_mcp_toolset_reference: object` Reference to every tool in the named MCP server's toolset, as a `compaction` block's `tool_changes` entry reports it. Send it back unchanged with the block. - `type: "mcp_toolset_reference"` - `server_name: string` - `beta_tool_change_tool_definition: object` A tool defined by value, as a `compaction` block's `tool_changes` entry reports it: `definition` is the tool's definition as it was sent, in the form of a `tools` entry, without `cache_control`. Send it back unchanged with the block. - `type: "tool_definition"` - `definition: BetaResponseTool or BetaToolBash20241022 or BetaToolBash20250124 or 25 more` - `beta_response_tool: object` A custom tool definition, as sent. - `type: optional "custom"` - `input_schema: object` [JSON schema](https://json-schema.org/draft/2020-12) for this tool's input. This defines the shape of the `input` that your tool accepts and that the model will produce. - `type: "object"` - `properties: optional map[unknown]` - `required: optional array of string` - `name: string` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. minLength: 1, maxLength: 128, pattern: ^[a-zA-Z0-9_-]{1,128}$ - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `description: optional string` Description of what this tool does. Tool descriptions should be as detailed as possible. The more information that the model has about what the tool is and how to use it, the better it will perform. You can use natural language descriptions to reinforce important aspects of the tool input JSON schema. - `eager_input_streaming: optional boolean` Enable eager input streaming for this tool. When true, tool input parameters will be streamed incrementally as they are generated, and types will be inferred on-the-fly rather than buffering the full JSON output. When false, streaming is disabled for this tool even if the fine-grained-tool-streaming beta is active. When null (default), uses the default behavior based on beta headers. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_bash_20241022: object` - `type: "bash_20241022"` - `name: "bash"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `"5m"` - `"1h"` - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_bash_20250124: object` - `type: "bash_20250124"` - `name: "bash"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_code_execution_tool_20250522: object` - `type: "code_execution_20250522"` - `name: "code_execution"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_code_execution_tool_20250825: object` - `type: "code_execution_20250825"` - `name: "code_execution"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_code_execution_tool_20260120: object` Code execution tool with REPL state persistence (daemon mode + gVisor checkpoint). - `type: "code_execution_20260120"` - `name: "code_execution"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_code_execution_tool_20260521: object` Code execution tool with REPL state persistence. - `type: "code_execution_20260521"` - `name: "code_execution"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_browser_toolset_20260801: object` The browser toolset: a single `tools[]` entry (carrying no `name`) that declares the browser tool family. The model is served the family's tool with any members disabled via `configs` removed from its schema. - `type: "browser_toolset_20260801"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `configs: optional object` Sparse per-member overrides, keyed by member name. Absent, null, and {} are equivalent; a member's defaults apply wherever its key is absent. - `type: optional object` `type`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `close_tab: optional object` `close_tab`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `double_click: optional object` `double_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `file_upload: optional object` `file_upload`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `find: optional object` `find`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `form_input: optional object` `form_input`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `get_page_text: optional object` `get_page_text`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `hold_key: optional object` `hold_key`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `hover: optional object` `hover`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `javascript_exec: optional object` `javascript_exec`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `key: optional object` `key`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_click: optional object` `left_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_click_drag: optional object` `left_click_drag`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_mouse_down: optional object` `left_mouse_down`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_mouse_up: optional object` `left_mouse_up`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `list_tabs: optional object` `list_tabs`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `middle_click: optional object` `middle_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `mouse_move: optional object` `mouse_move`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `navigate: optional object` `navigate`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `new_tab: optional object` `new_tab`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `read_console: optional object` `read_console`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `read_network: optional object` `read_network`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `read_page: optional object` `read_page`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `right_click: optional object` `right_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `screenshot: optional object` `screenshot`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `scroll: optional object` `scroll`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `scroll_to: optional object` `scroll_to`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `switch_tab: optional object` `switch_tab`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `triple_click: optional object` `triple_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `wait: optional object` `wait`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `zoom: optional object` `zoom`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `beta_tool_computer_use_20241022: object` - `type: "computer_20241022"` - `display_height_px: number` The height of the display in pixels. minimum: 1 - `display_width_px: number` The width of the display in pixels. minimum: 1 - `name: "computer"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `display_number: optional number` The X11 display number (e.g. 0, 1) for the display. minimum: 0 - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_memory_tool_20250818: object` - `type: "memory_20250818"` - `name: "memory"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_computer_use_20250124: object` - `type: "computer_20250124"` - `display_height_px: number` The height of the display in pixels. minimum: 1 - `display_width_px: number` The width of the display in pixels. minimum: 1 - `name: "computer"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `display_number: optional number` The X11 display number (e.g. 0, 1) for the display. minimum: 0 - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_text_editor_20241022: object` - `type: "text_editor_20241022"` - `name: "str_replace_editor"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_computer_use_20251124: object` - `type: "computer_20251124"` - `display_height_px: number` The height of the display in pixels. minimum: 1 - `display_width_px: number` The width of the display in pixels. minimum: 1 - `name: "computer"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `display_number: optional number` The X11 display number (e.g. 0, 1) for the display. minimum: 0 - `enable_zoom: optional boolean` Whether to enable an action to take a zoomed-in screenshot of the screen. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_computer_toolset_20260801: object` The computer toolset: a single `tools[]` entry (carrying no `name`) that declares the computer tool family. The model is served the family's tool with any members disabled via `configs` removed from its schema. Every member is enabled by default, zoom included. The single-tool options `display_number` and `enable_zoom` are not fields of a toolset entry — it carries only `type`, `configs`, and `cache_control`; zoom is controlled via `configs.zoom.enabled`. - `type: "computer_toolset_20260801"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `configs: optional object` Sparse per-member overrides, keyed by member name. Absent, null, and {} are equivalent; a member's defaults apply wherever its key is absent. - `type: optional object` `type`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `cursor_position: optional object` `cursor_position`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `double_click: optional object` `double_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `hold_key: optional object` `hold_key`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `key: optional object` `key`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_click: optional object` `left_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_click_drag: optional object` `left_click_drag`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_mouse_down: optional object` `left_mouse_down`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_mouse_up: optional object` `left_mouse_up`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `middle_click: optional object` `middle_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `mouse_move: optional object` `mouse_move`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `right_click: optional object` `right_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `screenshot: optional object` `screenshot`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `scroll: optional object` `scroll`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `triple_click: optional object` `triple_click`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `wait: optional object` `wait`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `zoom: optional object` `zoom`'s config overrides. - `defer_loading: optional boolean` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `beta_tool_text_editor_20250124: object` - `type: "text_editor_20250124"` - `name: "str_replace_editor"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_text_editor_20250429: object` - `type: "text_editor_20250429"` - `name: "str_replace_based_edit_tool"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_text_editor_20250728: object` - `type: "text_editor_20250728"` - `name: "str_replace_based_edit_tool"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: optional array of map[unknown]` - `max_characters: optional number` Maximum number of characters to display when viewing a file. If not specified, defaults to displaying the full file. minimum: 1 - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_web_search_tool_20250305: object` - `type: "web_search_20250305"` - `name: "web_search"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: optional array of string` If provided, only these domains will be included in results. Cannot be used alongside `blocked_domains`. - `blocked_domains: optional array of string` If provided, these domains will never appear in results. Cannot be used alongside `allowed_domains`. - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `user_location: optional object` Parameters for the user's location. Used to provide more relevant search results. - `type: "approximate"` - `city: optional string` The city of the user. minLength: 1, maxLength: 255 - `country: optional string` The two letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1_alpha-2) of the user. minLength: 2, maxLength: 2 - `region: optional string` The region of the user. minLength: 1, maxLength: 255 - `timezone: optional string` The [IANA timezone](https://nodatime.org/TimeZones) of the user. minLength: 1, maxLength: 255 - `beta_web_fetch_tool_20250910: object` - `type: "web_fetch_20250910"` - `name: "web_fetch"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: optional array of string` List of domains to allow fetching from - `blocked_domains: optional array of string` List of domains to block fetching from - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `citations: optional object` Citations configuration for fetched documents. Citations are disabled by default. - `enabled: optional boolean` - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_content_tokens: optional number` Maximum number of tokens used by including web page text content in the context. The limit is approximate and does not apply to binary content such as PDFs. minimum: 1 - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `url_sources: optional object` Which sources contribute to the set of URLs the tool may fetch. Omitted means every source. - `client_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which client tools' results contribute fetchable URLs: "all", "none", or an only or except list of client tool names from tools[]. - `beta_web_fetch_url_source_all: object` The `url_sources` variant under which a source contributes in full: every result of the tool filter's source, or all user input. - `type: "all"` - `beta_web_fetch_url_source_none: object` The `url_sources` variant under which a source contributes nothing: no result of the tool filter's source, or no user input. - `type: "none"` - `beta_web_fetch_url_source_only: object` The tool filter variant under which only the named tools' results contribute. - `type: "only"` - `tools: array of BetaWebFetchURLSourceToolReference` - `type: "tool_reference"` - `name: string` - `beta_web_fetch_url_source_except: object` The tool filter variant under which every result but the named tools' contributes. - `type: "except"` - `tools: array of BetaWebFetchURLSourceToolReference` - `type: "tool_reference"` - `name: string` - `server_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which server tools' results contribute fetchable URLs: "all", "none", or an only or except list of server tool names from tools[]; only web_search and web_fetch results ever contribute. - `beta_web_fetch_url_source_all: object` The `url_sources` variant under which a source contributes in full: every result of the tool filter's source, or all user input. - `beta_web_fetch_url_source_none: object` The `url_sources` variant under which a source contributes nothing: no result of the tool filter's source, or no user input. - `beta_web_fetch_url_source_only: object` The tool filter variant under which only the named tools' results contribute. - `beta_web_fetch_url_source_except: object` The tool filter variant under which every result but the named tools' contributes. - `user_input: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone` Whether URLs in user messages are fetchable: "all" or "none". - `beta_web_fetch_url_source_all: object` The `url_sources` variant under which a source contributes in full: every result of the tool filter's source, or all user input. - `beta_web_fetch_url_source_none: object` The `url_sources` variant under which a source contributes nothing: no result of the tool filter's source, or no user input. - `beta_web_search_tool_20260209: object` - `type: "web_search_20260209"` - `name: "web_search"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: optional array of string` If provided, only these domains will be included in results. Cannot be used alongside `blocked_domains`. - `blocked_domains: optional array of string` If provided, these domains will never appear in results. Cannot be used alongside `allowed_domains`. - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `user_location: optional object` Parameters for the user's location. Used to provide more relevant search results. - `type: "approximate"` - `city: optional string` The city of the user. minLength: 1, maxLength: 255 - `country: optional string` The two letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1_alpha-2) of the user. minLength: 2, maxLength: 2 - `region: optional string` The region of the user. minLength: 1, maxLength: 255 - `timezone: optional string` The [IANA timezone](https://nodatime.org/TimeZones) of the user. minLength: 1, maxLength: 255 - `beta_web_fetch_tool_20260209: object` - `type: "web_fetch_20260209"` - `name: "web_fetch"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: optional array of string` List of domains to allow fetching from - `blocked_domains: optional array of string` List of domains to block fetching from - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `citations: optional object` Citations configuration for fetched documents. Citations are disabled by default. - `enabled: optional boolean` - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_content_tokens: optional number` Maximum number of tokens used by including web page text content in the context. The limit is approximate and does not apply to binary content such as PDFs. minimum: 1 - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `url_sources: optional object` Which sources contribute to the set of URLs the tool may fetch. Omitted means every source. - `client_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which client tools' results contribute fetchable URLs: "all", "none", or an only or except list of client tool names from tools[]. - `server_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which server tools' results contribute fetchable URLs: "all", "none", or an only or except list of server tool names from tools[]; only web_search and web_fetch results ever contribute. - `user_input: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone` Whether URLs in user messages are fetchable: "all" or "none". - `beta_web_fetch_tool_20260309: object` Web fetch tool with use_cache parameter for bypassing cached content. - `type: "web_fetch_20260309"` - `name: "web_fetch"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: optional array of string` List of domains to allow fetching from - `blocked_domains: optional array of string` List of domains to block fetching from - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `citations: optional object` Citations configuration for fetched documents. Citations are disabled by default. - `enabled: optional boolean` - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_content_tokens: optional number` Maximum number of tokens used by including web page text content in the context. The limit is approximate and does not apply to binary content such as PDFs. minimum: 1 - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `url_sources: optional object` Which sources contribute to the set of URLs the tool may fetch. Omitted means every source. - `client_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which client tools' results contribute fetchable URLs: "all", "none", or an only or except list of client tool names from tools[]. - `server_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which server tools' results contribute fetchable URLs: "all", "none", or an only or except list of server tool names from tools[]; only web_search and web_fetch results ever contribute. - `user_input: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone` Whether URLs in user messages are fetchable: "all" or "none". - `use_cache: optional boolean` Whether to use cached content. Set to false to bypass the cache and fetch fresh content. Only set to false when the user explicitly requests fresh content or when fetching rapidly-changing sources. - `beta_web_search_tool_20260318: object` - `type: "web_search_20260318"` - `name: "web_search"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: optional array of string` If provided, only these domains will be included in results. Cannot be used alongside `blocked_domains`. - `blocked_domains: optional array of string` If provided, these domains will never appear in results. Cannot be used alongside `allowed_domains`. - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `response_inclusion: optional "full" or "excluded"` How this tool's result blocks appear in the API response when the result was consumed by a completed code_execution call in the same turn. 'full' returns the complete content (default). 'excluded' drops the nested server_tool_use and result block pair entirely. Results from direct calls, or from code_execution calls that paused before completing, are always returned in full so they can be sent back on the next turn. - `"full"` - `"excluded"` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `user_location: optional object` Parameters for the user's location. Used to provide more relevant search results. - `type: "approximate"` - `city: optional string` The city of the user. minLength: 1, maxLength: 255 - `country: optional string` The two letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1_alpha-2) of the user. minLength: 2, maxLength: 2 - `region: optional string` The region of the user. minLength: 1, maxLength: 255 - `timezone: optional string` The [IANA timezone](https://nodatime.org/TimeZones) of the user. minLength: 1, maxLength: 255 - `beta_web_fetch_tool_20260318: object` - `type: "web_fetch_20260318"` - `name: "web_fetch"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: optional array of string` List of domains to allow fetching from - `blocked_domains: optional array of string` List of domains to block fetching from - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `citations: optional object` Citations configuration for fetched documents. Citations are disabled by default. - `enabled: optional boolean` - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_content_tokens: optional number` Maximum number of tokens used by including web page text content in the context. The limit is approximate and does not apply to binary content such as PDFs. minimum: 1 - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `response_inclusion: optional "full" or "excluded"` How this tool's result blocks appear in the API response when the result was consumed by a completed code_execution call in the same turn. 'full' returns the complete content (default). 'excluded' drops the nested server_tool_use and result block pair entirely. Results from direct calls, or from code_execution calls that paused before completing, are always returned in full so they can be sent back on the next turn. - `"full"` - `"excluded"` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `url_sources: optional object` Which sources contribute to the set of URLs the tool may fetch. Omitted means every source. - `client_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which client tools' results contribute fetchable URLs: "all", "none", or an only or except list of client tool names from tools[]. - `server_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept` Which server tools' results contribute fetchable URLs: "all", "none", or an only or except list of server tool names from tools[]; only web_search and web_fetch results ever contribute. - `user_input: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone` Whether URLs in user messages are fetchable: "all" or "none". - `use_cache: optional boolean` Whether to use cached content. Set to false to bypass the cache and fetch fresh content. Only set to false when the user explicitly requests fresh content or when fetching rapidly-changing sources. - `beta_advisor_tool_20260301: object` - `type: "advisor_20260301"` - `model: "claude-haiku-5-5" or "claude-sonnet-5-5" or "claude-fable-5-1" or 17 more or string` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-haiku-5-5"` Fastest model for high-volume, real-time tasks - `"claude-sonnet-5-5"` Efficient model for coding and agents - `"claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows - `"claude-opus-5-5"` Powerful intelligence for coding, knowledge work, and long-running agents - `"claude-mythos-5-1"` Our most capable model for cybersecurity and biology research, available through trusted access programs - `"claude-sonnet-5"` Efficient model for coding and agents - `"claude-fable-5"` Next generation of intelligence for the hardest knowledge work and coding problems - `"claude-mythos-5"` Most capable model for cybersecurity and biology research - `"claude-opus-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-8"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-7"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-6"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-6"` Best combination of speed and intelligence - `"claude-haiku-4-5"` - `"claude-haiku-4-5-20251001"` - `"claude-opus-4-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-5-20251101"` Powerful intelligence for long-running agents and coding - `"claude-mythos-preview"` **Deprecated**: Will reach end-of-life on June 30, 2026. Please migrate to claude-mythos-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. New class of intelligence, strongest in coding and cybersecurity - `"claude-sonnet-4-5"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `"claude-sonnet-4-5-20250929"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `name: "advisor"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `caching: optional object` Caching for the advisor's own prompt. When set, each advisor call writes a cache entry at the given TTL so subsequent calls in the same conversation read the stable prefix. When omitted, the advisor prompt is not cached. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_tokens: optional number` Bounds the advisor's total output (thinking + text) per call. When the advisor hits this cap, the returned advisor_result or advisor_redacted_result block carries stop_reason='max_tokens', and a truncation note is appended to the advice text the worker model sees (inside the encrypted blob in redacted mode). When set, the server also emits a remaining-tokens budget block in the advisor's prompt so the advisor self-shapes toward the cap. When omitted, the advisor model's default output cap applies and no budget block is emitted. minimum: 1024 - `max_uses: optional number` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_search_tool_bm25_20251119: object` - `type: "tool_search_tool_bm25_20251119" or "tool_search_tool_bm25"` - `"tool_search_tool_bm25_20251119"` - `"tool_search_tool_bm25"` - `name: "tool_search_tool_bm25"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_tool_search_tool_regex_20251119: object` - `type: "tool_search_tool_regex_20251119" or "tool_search_tool_regex"` - `"tool_search_tool_regex_20251119"` - `"tool_search_tool_regex"` - `name: "tool_search_tool_regex"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `beta_mcp_toolset: object` Configuration for a group of tools from an MCP server. Allows configuring enabled status and defer_loading for all tools from an MCP server, with optional per-tool overrides. - `type: "mcp_toolset"` - `mcp_server_name: string` Name of the MCP server to configure tools for minLength: 1, maxLength: 255 - `cache_control: optional object` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=cli) for details. - `configs: optional map[BetaMCPToolConfig]` Configuration overrides for specific tools, keyed by tool name - `defer_loading: optional boolean` - `enabled: optional boolean` - `default_config: optional object` Default configuration applied to all tools from this server - `defer_loading: optional boolean` - `enabled: optional boolean` - `tools: optional array of BetaMCPToolParam` The server's tool listing, pinned: when present, the server is not asked for its tools before sampling and exactly these entries, with `default_config` and `configs` applied, are the toolset's tools. Copy it from the `mcp_tool_listing` block of an earlier response. - `input_schema: map[unknown]` The tool's input schema as the MCP server lists it, verbatim. - `name: string` The tool's name as the MCP server lists it (not prefixed with the server name). minLength: 1 - `description: optional string` The tool's description as the MCP server lists it. - `beta_response_tool_removal_block: object` An entry of a `compaction` block's `tool_changes`: a tool of the request's `tools` (or an MCP tool or toolset) that the compacted range withdrew. Send it back unchanged. - `type: "tool_removal"` - `tool: BetaResponseToolChangeToolReference or BetaResponseToolChangeMCPToolReference or BetaResponseToolChangeMCPToolsetReference` A reference to the withdrawn `tools` entry, MCP tool or MCP toolset. - `beta_response_tool_change_tool_reference: object` Reference to a single tool, by the name the model uses to call it, as a `compaction` block's `tool_changes` entry reports it: a tool declared in `tools` or defined by an earlier `tool_addition` block. Send it back unchanged with the block. - `beta_response_tool_change_mcp_tool_reference: object` Reference to a single MCP tool, by its server and its name on that server, as a `compaction` block's `tool_changes` entry reports it. Send it back unchanged with the block. - `beta_response_tool_change_mcp_toolset_reference: object` Reference to every tool in the named MCP server's toolset, as a `compaction` block's `tool_changes` entry reports it. Send it back unchanged with the block. - `beta_fallback_block: object` Marks the point in `content` where one model's output gives way to the next. One block appears per hop where a preceding model actually ran this turn and declined. A turn where no preceding model ran and declined has no such boundary and carries no block — the signal for whether a fallback model served the response is the presence of a `fallback_message` entry in `usage.iterations`, not this block. The block is treated like a server-tool content block for streaming: it arrives via the standard `content_block_start` / `content_block_stop` pair and carries no deltas. - `type: "fallback"` - `from: object` The model whose output ends at this point — the model that declined at this hop. When the declining hop is the requested model, its `model` echoes the top-level `model` string the caller sent (alias or canonical); when the declining hop is a fallback model, its `model` is that model's canonical id. - `model: "claude-haiku-5-5" or "claude-sonnet-5-5" or "claude-fable-5-1" or 17 more or string` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-haiku-5-5"` Fastest model for high-volume, real-time tasks - `"claude-sonnet-5-5"` Efficient model for coding and agents - `"claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows - `"claude-opus-5-5"` Powerful intelligence for coding, knowledge work, and long-running agents - `"claude-mythos-5-1"` Our most capable model for cybersecurity and biology research, available through trusted access programs - `"claude-sonnet-5"` Efficient model for coding and agents - `"claude-fable-5"` Next generation of intelligence for the hardest knowledge work and coding problems - `"claude-mythos-5"` Most capable model for cybersecurity and biology research - `"claude-opus-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-8"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-7"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-6"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-6"` Best combination of speed and intelligence - `"claude-haiku-4-5"` - `"claude-haiku-4-5-20251001"` - `"claude-opus-4-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-5-20251101"` Powerful intelligence for long-running agents and coding - `"claude-mythos-preview"` **Deprecated**: Will reach end-of-life on June 30, 2026. Please migrate to claude-mythos-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. New class of intelligence, strongest in coding and cybersecurity - `"claude-sonnet-4-5"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `"claude-sonnet-4-5-20250929"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `to: object` The fallback model producing the content that follows this block. Its `model` is always the canonical id. - `model: "claude-haiku-5-5" or "claude-sonnet-5-5" or "claude-fable-5-1" or 17 more or string` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `trigger: object` What caused the `from` model to hand over at this hop. - `type: "refusal"` - `category: "cyber" or "bio" or "frontier_llm" or 2 more` The policy category that triggered the `from` model's refusal at this hop. `null` when the refusal doesn't map to a named category. Same vocabulary as `stop_details.category`. - `"cyber"` The request could enable cyber harm, such as malware or exploit development. Benign cybersecurity work can also trigger this category. - `"bio"` The request could enable biological harm, such as dangerous lab methods. Beneficial life sciences work can also trigger this category. - `"frontier_llm"` The request could assist the development of competing AI models, which is restricted under [Anthropic's commercial terms](https://www.anthropic.com/legal/commercial-terms). Benign machine learning work can also trigger this category. - `"reasoning_extraction"` The request asks the model to reproduce its internal reasoning in the response text. To get reasoning in a structured form instead, use [adaptive thinking](https://platform.claude.com/docs/en/build-with-claude/adaptive-thinking?sdk_languages=cli). - `"general_harms"` The request could be related to an area that was determined as harmful. Benign work might sometimes trigger this category. - `beta_mcp_tool_listing_block: object` The tool listing the server fetched from an MCP server while producing this response. Send the assistant message back unchanged, this block included, so later requests use this listing instead of asking the MCP server again. - `type: "mcp_tool_listing"` - `mcp_server_name: string` - `tools: array of BetaMCPTool` - `input_schema: map[unknown]` - `name: string` - `description: optional string` - `context_management: object` Context management response. Information about context management strategies applied during the request. - `applied_edits: array of BetaClearToolUses20250919EditResponse or BetaClearThinking20251015EditResponse` List of context management edits that were applied. - `beta_clear_tool_uses_20250919_edit_response: object` - `type: "clear_tool_uses_20250919"` The type of context management edit applied. - `cleared_input_tokens: number` Number of input tokens cleared by this edit. minimum: 0 - `cleared_tool_uses: number` Number of tool uses that were cleared. minimum: 0 - `beta_clear_thinking_20251015_edit_response: object` - `type: "clear_thinking_20251015"` The type of context management edit applied. - `cleared_input_tokens: number` Number of input tokens cleared by this edit. minimum: 0 - `cleared_thinking_turns: number` Number of thinking turns that were cleared. minimum: 0 - `diagnostics: object` Request-level diagnostics. `null` when the request did not supply `diagnostics`, or when it did and no prompt-cache divergence was detected. - `cache_miss_reason: BetaCacheMissModelChanged or BetaCacheMissSystemChanged or BetaCacheMissToolsChanged or 3 more` Explains why the prompt cache could not fully reuse the prefix from the request identified by `diagnostics.previous_message_id`. `null` means diagnosis is still pending — the response was serialized before the background comparison completed. - `beta_cache_miss_model_changed: object` - `type: "model_changed"` - `cache_missed_input_tokens: number` Approximate number of input tokens that would have been read from cache had the prefix matched the previous request. - `beta_cache_miss_system_changed: object` - `type: "system_changed"` - `cache_missed_input_tokens: number` Approximate number of input tokens that would have been read from cache had the prefix matched the previous request. - `beta_cache_miss_tools_changed: object` - `type: "tools_changed"` - `cache_missed_input_tokens: number` Approximate number of input tokens that would have been read from cache had the prefix matched the previous request. - `beta_cache_miss_messages_changed: object` - `type: "messages_changed"` - `cache_missed_input_tokens: number` Approximate number of input tokens that would have been read from cache had the prefix matched the previous request. - `beta_cache_miss_previous_message_not_found: object` - `type: "previous_message_not_found"` - `beta_cache_miss_unavailable: object` - `type: "unavailable"` - `model: "claude-haiku-5-5" or "claude-sonnet-5-5" or "claude-fable-5-1" or 17 more or string` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-haiku-5-5"` Fastest model for high-volume, real-time tasks - `"claude-sonnet-5-5"` Efficient model for coding and agents - `"claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows - `"claude-opus-5-5"` Powerful intelligence for coding, knowledge work, and long-running agents - `"claude-mythos-5-1"` Our most capable model for cybersecurity and biology research, available through trusted access programs - `"claude-sonnet-5"` Efficient model for coding and agents - `"claude-fable-5"` Next generation of intelligence for the hardest knowledge work and coding problems - `"claude-mythos-5"` Most capable model for cybersecurity and biology research - `"claude-opus-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-8"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-7"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-6"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-6"` Best combination of speed and intelligence - `"claude-haiku-4-5"` - `"claude-haiku-4-5-20251001"` - `"claude-opus-4-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-5-20251101"` Powerful intelligence for long-running agents and coding - `"claude-mythos-preview"` **Deprecated**: Will reach end-of-life on June 30, 2026. Please migrate to claude-mythos-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. New class of intelligence, strongest in coding and cybersecurity - `"claude-sonnet-4-5"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `"claude-sonnet-4-5-20250929"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `role: "assistant"` Conversational role of the generated message. This will always be `"assistant"`. - `stop_details: object` Structured information about why model output stopped. This is `null` when the `stop_reason` has no additional detail to report. - `type: "refusal"` - `category: "cyber" or "bio" or "frontier_llm" or 2 more` The policy category that triggered the refusal. `null` when the refusal doesn't map to a named category. - `"cyber"` The request could enable cyber harm, such as malware or exploit development. Benign cybersecurity work can also trigger this category. - `"bio"` The request could enable biological harm, such as dangerous lab methods. Beneficial life sciences work can also trigger this category. - `"frontier_llm"` The request could assist the development of competing AI models, which is restricted under [Anthropic's commercial terms](https://www.anthropic.com/legal/commercial-terms). Benign machine learning work can also trigger this category. - `"reasoning_extraction"` The request asks the model to reproduce its internal reasoning in the response text. To get reasoning in a structured form instead, use [adaptive thinking](https://platform.claude.com/docs/en/build-with-claude/adaptive-thinking?sdk_languages=cli). - `"general_harms"` The request could be related to an area that was determined as harmful. Benign work might sometimes trigger this category. - `explanation: string` Human-readable explanation of the refusal. This text is not guaranteed to be stable. `null` when no explanation is available for the category. - `fallback_credit_token: string` Opaque code that refunds the cache-miss cost when retrying this refused request on the fallback model. Pass it as `fallback_credit_token` on the retry request. Expires 5 minutes after the refusal. The retry is sent either with the same request body (`system`, `messages`, `tools`, and other render-shaping fields), or with the same body plus one appended `assistant` message whose content is the partial text (with any trailing whitespace stripped from the final text block) and paired server-tool blocks from this refusal — which also authorizes that appended turn as an assistant-prefill continuation on models that otherwise disallow prefill. A token minted mid-server-tool-loop whose partial content was continuable may only be redeemed the second way — if a same-body retry is rejected with a 400 saying the token must be redeemed by continuing the partial response, retry the second way instead. Either way: same workspace, same platform; a mismatch is a 400. Resending a token for an already-warm prefix is permitted but yields no additional credit. `null` when the refused model isn't eligible for a fallback credit. - `fallback_has_prefill_claim: boolean` Whether the accompanying `fallback_credit_token` may be redeemed with the appended-assistant retry form. Only set when `fallback_credit_token` is present. `true`: retry by resending the same request body plus one appended `assistant` message whose content is this response's `content` with any trailing whitespace stripped from the final text block and unpaired `tool_use` blocks omitted (the same appended-turn shape described on `fallback_credit_token`), with the token attached. `false`: retry by resending the original request body unchanged, with the token attached — the appended-assistant form is not available for this refusal (no continuable partial content, or the request uses `output_format` or a `tool_choice` that forces tool use). One exception: when the request used `output_format` or a forced `tool_choice` and the refusal arrived after server tools (including MCP connector tools) had already executed, the token may not be redeemable by either retry form; if the exact-body retry is then rejected with a 400 saying the token must be redeemed by continuing the partial response, discard the token and retry without it. Advisory: if an appended-assistant retry is rejected with a 400 despite `true`, fall back to resending the original request body with the token. - `recommended_model: string` The server's suggested retry target for this refusal. Populated when a fallback attempt could not be made (the fallback model's rate limit was exhausted, or it was overloaded); names the fallback model the caller can retry directly. Null otherwise. - `stop_reason: "end_turn" or "max_tokens" or "stop_sequence" or 5 more` The reason that we stopped. This may be one the following values: * `"end_turn"`: the model reached a natural stopping point * `"max_tokens"`: we exceeded the requested `max_tokens` or the model's maximum * `"stop_sequence"`: one of your provided custom `stop_sequences` was generated * `"tool_use"`: the model invoked one or more tools * `"pause_turn"`: we paused a long-running turn. You may provide the response back as-is in a subsequent request to let the model continue. * `"refusal"`: when streaming classifiers intervene to handle potential policy violations * `"model_context_window_exceeded"`: we exceeded the model's context window In non-streaming mode this value is always non-null. In streaming mode, it is null in the `message_start` event and non-null otherwise. - `"end_turn"` - `"max_tokens"` - `"stop_sequence"` - `"tool_use"` - `"pause_turn"` - `"compaction"` - `"refusal"` - `"model_context_window_exceeded"` - `stop_sequence: string` Which custom stop sequence was generated, if any. This value will be a non-null string if one of your custom stop sequences was generated. - `usage: object` Billing and rate-limit usage. Anthropic's API bills and rate-limits by token counts, as tokens represent the underlying cost to our systems. Under the hood, the API transforms requests into a format suitable for the model. The model's output then goes through a parsing stage before becoming an API response. As a result, the token counts in `usage` will not match one-to-one with the exact visible content of an API request or response. For example, `output_tokens` will be non-zero, even for an empty string response from Claude. Total input tokens in a request is the summation of `input_tokens`, `cache_creation_input_tokens`, and `cache_read_input_tokens`. - `cache_creation: object` Breakdown of cached tokens by TTL - `ephemeral_1h_input_tokens: number` The number of input tokens used to create the 1 hour cache entry. minimum: 0 - `ephemeral_5m_input_tokens: number` The number of input tokens used to create the 5 minute cache entry. minimum: 0 - `cache_creation_input_tokens: number` The number of input tokens used to create the cache entry. minimum: 0 - `cache_read_input_tokens: number` The number of input tokens read from the cache. minimum: 0 - `fallback_credit: object` Outcome of the `fallback_credit_token` presented on this request. Present on every response to a non-batch request that carried a `fallback_credit_token`, in either redemption mode; absent otherwise (batch items accept and ignore the token and carry no outcome object). - `status: BetaFallbackCreditRedeemed or BetaFallbackCreditNotApplied` Whether the fallback-credit reprice was applied to this response's billing. A union discriminated on `type`. `redeemed`: the retry is billed as if the conversation had been on the retry model all along — including when the resulting shift is zero because there was nothing to move. `not_applied`: no reprice was applied; the arm's `reason` says why. - `beta_fallback_credit_redeemed: object` The reprice was applied: the retry is billed as if the conversation had been on the retry model all along. - `type: "redeemed"` - `beta_fallback_credit_not_applied: object` No reprice was applied; `reason` says why. - `type: "not_applied"` - `reason: "body_mismatch" or "continuation_excluded" or "continuation_only" or 9 more` Why the reprice was not applied. A closed enum; additions to the redemption-check vocabulary arrive as deliberate schema updates. - `"body_mismatch"` - `"continuation_excluded"` - `"continuation_only"` - `"expired"` - `"invalid_target_model"` - `"not_enabled"` - `"reprice_unavailable"` - `"temporarily_unavailable"` - `"variant_fields_present"` - `"wrong_organization"` - `"wrong_platform"` - `"wrong_workspace"` - `remove_to_redeem: optional array of string` Request fields to remove before retrying, so the retry can redeem this token. Present exactly when `reason` is `variant_fields_present` — never null, never an empty array; absent otherwise. Fields are named only from your own request, and only after the sealed variant hash matched. A served best-effort retry has already been billed at normal price; nothing redeems retroactively, but a corrected re-send inside the token's five-minute window can still redeem. - `inference_geo: string` The geographic region where inference was performed for this request. - `input_tokens: number` The number of input tokens which were used. minimum: 0 - `iterations: array of BetaMessageIterationUsage or BetaCompactionIterationUsage or BetaAdvisorMessageIterationUsage or BetaFallbackMessageIterationUsage` Per-iteration token usage breakdown. Each entry represents one sampling iteration, with its own input/output token counts and cache statistics, discriminated by `type`. For `message` entries (model sampling iterations, such as the turns of a server-side tool use loop), this allows you to: - Calculate the context window size from the last `message` entry - Understand token accumulation across server-side tool use loops A `compaction` entry reports the token usage of the compaction operation itself — the server-side request that summarizes the context being closed — NOT the size of the context that was compacted away, and its token counts can be much smaller than that closed context (for example, a compaction that closes a ~200k-token context can report only a few thousand tokens). Do not derive the context window size from a `compaction` entry, even when it is the last entry. A `compaction` entry's tokens are not included in the top-level `usage` fields. When an input-token trigger is in effect (the default — 150,000 tokens unless configured otherwise), each `compaction` entry closes a context that had reached at least that threshold, though the context can exceed it by the final iteration's output and tool results. - `beta_message_iteration_usage: object` Token usage for a sampling iteration. - `type: "message"` Usage for a sampling iteration - `cache_creation: object` Breakdown of cached tokens by TTL - `ephemeral_1h_input_tokens: number` The number of input tokens used to create the 1 hour cache entry. minimum: 0 - `ephemeral_5m_input_tokens: number` The number of input tokens used to create the 5 minute cache entry. minimum: 0 - `cache_creation_input_tokens: number` The number of input tokens used to create the cache entry. minimum: 0 - `cache_read_input_tokens: number` The number of input tokens read from the cache. minimum: 0 - `input_tokens: number` The number of input tokens which were used. minimum: 0 - `model: "claude-haiku-5-5" or "claude-sonnet-5-5" or "claude-fable-5-1" or 17 more or string` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-haiku-5-5"` Fastest model for high-volume, real-time tasks - `"claude-sonnet-5-5"` Efficient model for coding and agents - `"claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows - `"claude-opus-5-5"` Powerful intelligence for coding, knowledge work, and long-running agents - `"claude-mythos-5-1"` Our most capable model for cybersecurity and biology research, available through trusted access programs - `"claude-sonnet-5"` Efficient model for coding and agents - `"claude-fable-5"` Next generation of intelligence for the hardest knowledge work and coding problems - `"claude-mythos-5"` Most capable model for cybersecurity and biology research - `"claude-opus-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-8"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-7"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-6"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-6"` Best combination of speed and intelligence - `"claude-haiku-4-5"` - `"claude-haiku-4-5-20251001"` - `"claude-opus-4-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-5-20251101"` Powerful intelligence for long-running agents and coding - `"claude-mythos-preview"` **Deprecated**: Will reach end-of-life on June 30, 2026. Please migrate to claude-mythos-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. New class of intelligence, strongest in coding and cybersecurity - `"claude-sonnet-4-5"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `"claude-sonnet-4-5-20250929"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `output_tokens: number` The number of output tokens which were used. minimum: 0 - `beta_compaction_iteration_usage: object` Token usage for a compaction iteration. - `type: "compaction"` Usage for a compaction iteration - `cache_creation: object` Breakdown of cached tokens by TTL - `ephemeral_1h_input_tokens: number` The number of input tokens used to create the 1 hour cache entry. minimum: 0 - `ephemeral_5m_input_tokens: number` The number of input tokens used to create the 5 minute cache entry. minimum: 0 - `cache_creation_input_tokens: number` The number of input tokens used to create the cache entry. minimum: 0 - `cache_read_input_tokens: number` The number of input tokens read from the cache. minimum: 0 - `input_tokens: number` The number of input tokens which were used. minimum: 0 - `output_tokens: number` The number of output tokens which were used. minimum: 0 - `beta_advisor_message_iteration_usage: object` Token usage for an advisor sub-inference iteration. - `type: "advisor_message"` Usage for an advisor sub-inference iteration - `cache_creation: object` Breakdown of cached tokens by TTL - `ephemeral_1h_input_tokens: number` The number of input tokens used to create the 1 hour cache entry. minimum: 0 - `ephemeral_5m_input_tokens: number` The number of input tokens used to create the 5 minute cache entry. minimum: 0 - `cache_creation_input_tokens: number` The number of input tokens used to create the cache entry. minimum: 0 - `cache_read_input_tokens: number` The number of input tokens read from the cache. minimum: 0 - `input_tokens: number` The number of input tokens which were used. minimum: 0 - `model: "claude-haiku-5-5" or "claude-sonnet-5-5" or "claude-fable-5-1" or 17 more or string` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-haiku-5-5"` Fastest model for high-volume, real-time tasks - `"claude-sonnet-5-5"` Efficient model for coding and agents - `"claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows - `"claude-opus-5-5"` Powerful intelligence for coding, knowledge work, and long-running agents - `"claude-mythos-5-1"` Our most capable model for cybersecurity and biology research, available through trusted access programs - `"claude-sonnet-5"` Efficient model for coding and agents - `"claude-fable-5"` Next generation of intelligence for the hardest knowledge work and coding problems - `"claude-mythos-5"` Most capable model for cybersecurity and biology research - `"claude-opus-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-8"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-7"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-6"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-6"` Best combination of speed and intelligence - `"claude-haiku-4-5"` - `"claude-haiku-4-5-20251001"` - `"claude-opus-4-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-5-20251101"` Powerful intelligence for long-running agents and coding - `"claude-mythos-preview"` **Deprecated**: Will reach end-of-life on June 30, 2026. Please migrate to claude-mythos-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. New class of intelligence, strongest in coding and cybersecurity - `"claude-sonnet-4-5"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `"claude-sonnet-4-5-20250929"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `output_tokens: number` The number of output tokens which were used. minimum: 0 - `beta_fallback_message_iteration_usage: object` Token usage for the fallback-model attempt of a server-side fallback request. The terminal entry of a fallback-served turn: when a fallback hop's output is the returned message, the entry for the iteration that completed it carries this type in place of `message`. A declined hop and the serving hop's earlier tool-loop iterations produce `message` entries. Whether a fallback model served the response is signalled by the presence of this entry in `usage.iterations`. - `type: "fallback_message"` Usage for the fallback-model attempt that served the response - `cache_creation: object` Breakdown of cached tokens by TTL - `ephemeral_1h_input_tokens: number` The number of input tokens used to create the 1 hour cache entry. minimum: 0 - `ephemeral_5m_input_tokens: number` The number of input tokens used to create the 5 minute cache entry. minimum: 0 - `cache_creation_input_tokens: number` The number of input tokens used to create the cache entry. minimum: 0 - `cache_read_input_tokens: number` The number of input tokens read from the cache. minimum: 0 - `input_tokens: number` The number of input tokens which were used. minimum: 0 - `model: "claude-haiku-5-5" or "claude-sonnet-5-5" or "claude-fable-5-1" or 17 more or string` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-haiku-5-5"` Fastest model for high-volume, real-time tasks - `"claude-sonnet-5-5"` Efficient model for coding and agents - `"claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows - `"claude-opus-5-5"` Powerful intelligence for coding, knowledge work, and long-running agents - `"claude-mythos-5-1"` Our most capable model for cybersecurity and biology research, available through trusted access programs - `"claude-sonnet-5"` Efficient model for coding and agents - `"claude-fable-5"` Next generation of intelligence for the hardest knowledge work and coding problems - `"claude-mythos-5"` Most capable model for cybersecurity and biology research - `"claude-opus-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-8"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-7"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-6"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-6"` Best combination of speed and intelligence - `"claude-haiku-4-5"` - `"claude-haiku-4-5-20251001"` - `"claude-opus-4-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-5-20251101"` Powerful intelligence for long-running agents and coding - `"claude-mythos-preview"` **Deprecated**: Will reach end-of-life on June 30, 2026. Please migrate to claude-mythos-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. New class of intelligence, strongest in coding and cybersecurity - `"claude-sonnet-4-5"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `"claude-sonnet-4-5-20250929"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `output_tokens: number` The number of output tokens which were used. minimum: 0 - `output_tokens: number` The number of output tokens which were used. minimum: 0 - `output_tokens_details: object` Breakdown of output tokens by category. `output_tokens` remains the inclusive, authoritative total used for billing. This object provides a read-only decomposition for observability — for example, how many of the billed output tokens were spent on internal reasoning that may have been summarized before being returned to you. - `thinking_tokens: number` Number of output tokens the model generated as internal reasoning, including the thinking-block delimiter tokens. Reflects the raw reasoning the model produced, not the (possibly shorter) summarized thinking text returned in the response body. Computed by re-tokenizing the raw reasoning text, so it may differ from the model's exact generation count by a small number of tokens. Always ≤ `output_tokens`; `output_tokens - thinking_tokens` approximates the non-reasoning output. minimum: 0 - `server_tool_use: object` The number of server tool requests. - `web_fetch_requests: number` The number of web fetch tool requests. minimum: 0 - `web_search_requests: number` The number of web search tool requests. minimum: 0 - `service_tier: "standard" or "priority" or "batch"` If the request used the priority, standard, or batch tier. - `"standard"` - `"priority"` - `"batch"` - `speed: "standard" or "fast"` The inference speed mode used for this request. - `"standard"` - `"fast"` - `input_transformations: optional array of BetaInputTransformation` Changes the API made to the request's input before showing it to the model, and blocks that failed a binding check but were left unchanged: one entry per block, in request order. Two entry types today. `thinking_dropped` — a `thinking`, `redacted_thinking` or `connector_text` block from the request's `messages` that was removed from the prompt instead of being shown to the model because it failed a binding check. `thinking_mismatch_allowed` — a `thinking` or `redacted_thinking` block that failed the conversation check (the conversation before it differs from the one it was created in, or it carries no record of one on a model that requires it) and was shown to the model all the same, because that check is not enforced for this request. More entry types may be added over time; ignore types you do not recognize. Requires `anthropic-beta: thinking-binding-controls-2026-08-01`. Present on every such response from a model that supports extended thinking, as `[]` when there is no entry to report; without the beta, blocks are removed or left in place all the same but nothing is reported. Removed blocks contribute nothing to `usage.input_tokens`; blocks left in place count as sent. When streaming, the array is final in `message_start`; the final `message_delta` event carries it only when a server-side model fallback happened mid-stream, in which case it holds the serving model's entries and replaces the one in `message_start`. - `beta_thinking_dropped_input_transformation: object` - `type: "thinking_dropped"` Always `thinking_dropped` for this entry type. - `path: string` Where the removed block was in your request, as `messages.{i}.content.{j}`: `i` indexes the `messages` array you sent and `j` that message's `content` array — the same form error messages use. - `reason: "model_binding_mismatch" or "prefix_binding_mismatch" or "organization_binding_mismatch" or "end_user_binding_mismatch"` Which binding check removed the block: `model_binding_mismatch` — it was created by a model whose reasoning the requested model may not read; `prefix_binding_mismatch` — the conversation before it differs from the conversation it was created in (the rest of that turn's consecutive thinking blocks are removed with it, each with this reason); `organization_binding_mismatch` — it was created under a different organization (an Anthropic organization, AWS account or Google Cloud project) and this organization is not one of its additional organizations; `end_user_binding_mismatch` — it was created for a different end user, or was removed by the consumer-organization binding. A block that would fail several checks reports one reason, in this order of precedence: `organization_binding_mismatch`, `end_user_binding_mismatch`, `model_binding_mismatch`, `prefix_binding_mismatch`. - `"model_binding_mismatch"` - `"prefix_binding_mismatch"` - `"organization_binding_mismatch"` - `"end_user_binding_mismatch"` - `beta_thinking_mismatch_allowed_input_transformation: object` - `type: "thinking_mismatch_allowed"` Always `thinking_mismatch_allowed` for this entry type. - `path: string` Where the block is in your request, as `messages.{i}.content.{j}`: `i` indexes the `messages` array you sent and `j` that message's `content` array — the same form error messages use. - `reason: "model_binding_mismatch" or "prefix_binding_mismatch" or "organization_binding_mismatch" or "end_user_binding_mismatch"` Which binding check the block failed; the block was shown to the model all the same. Always `prefix_binding_mismatch` today — the conversation before the block differs from the conversation it was created in, or the block carries no record of one on a model that requires it. Were the check enforced for this request, the block would have been removed or the request rejected (`thinking.block_binding.prefix_mismatch_behavior`). A removal also takes the rest of that turn's consecutive thinking blocks, whereas here each block is checked on its own, so `thinking_mismatch_allowed` entries are a lower bound on what enforcement would remove. - `"model_binding_mismatch"` - `"prefix_binding_mismatch"` - `"organization_binding_mismatch"` - `"end_user_binding_mismatch"` - `beta_message_batch_errored_result: object` - `type: "errored"` - `error: object` - `type: "error"` - `error: BetaInvalidRequestError or BetaAuthenticationError or BetaBillingError or 6 more` - `beta_invalid_request_error: object` - `type: "invalid_request_error"` - `message: string` - `beta_authentication_error: object` - `type: "authentication_error"` - `message: string` - `beta_billing_error: object` - `type: "billing_error"` - `message: string` - `beta_permission_error: object` - `type: "permission_error"` - `message: string` - `beta_not_found_error: object` - `type: "not_found_error"` - `message: string` - `beta_rate_limit_error: object` - `type: "rate_limit_error"` - `message: string` - `beta_gateway_timeout_error: object` - `type: "timeout_error"` - `message: string` - `beta_api_error: object` - `type: "api_error"` - `message: string` - `beta_overloaded_error: object` - `type: "overloaded_error"` - `message: string` - `request_id: string` - `beta_message_batch_canceled_result: object` - `type: "canceled"` - `beta_message_batch_expired_result: object` - `type: "expired"` #### Example ```bash ant beta:messages:batches results \ --api-key my-anthropic-api-key \ --message-batch-id message_batch_id ```