--- title: Claude Sonnet 5.5 url: https://platform.claude.com/docs/pt-BR/models/sonnet-5-5/overview description: "Claude Sonnet 5.5 em resumo: para que serve, IDs de modelo em todas as plataformas, janela de contexto, limites de saída, preços, disponibilidade e os guias e recursos para construir com ele." --- **Latest.** Released September 28, 2026. The best combination of speed and intelligence Model ID: `claude-sonnet-5-5` Context window: 1M tokens · Max output: 128K tokens · Input pricing: $2 / MTok · Output pricing: $10 / MTok [Announcement](https://www.anthropic.com/claude-sonnet-5-5) · [What’s new](https://platform.claude.com/docs/pt-BR/models/sonnet-5-5/whats-new-sonnet-5-5) · [Migration guide](https://platform.claude.com/docs/pt-BR/models/sonnet-5-5/migration-guide) ## Visão geral O Claude Sonnet 5.5 oferece a melhor combinação de velocidade e inteligência. Cinco "breaking changes" (mudanças incompatíveis) afetam código que já roda no Claude Sonnet 5: * [Desative o pensamento antecipado com `between_tools`](https://platform.claude.com/docs/pt-BR/models/sonnet-5-5/whats-new-sonnet-5-5#turn-off-up-front-thinking). * [O uso forçado de ferramentas retorna um erro](https://platform.claude.com/docs/pt-BR/models/sonnet-5-5/whats-new-sonnet-5-5#forced-tool-use-is-not-supported). * [Os blocos de pensamento estão vinculados ao modelo e à conversa](https://platform.claude.com/docs/pt-BR/models/sonnet-5-5/whats-new-sonnet-5-5#thinking-blocks-are-tied-to-the-model-that-produced-them). * [Na Claude API e no Google Cloud, a ferramenta de uso do computador anterior `computer_20251124` não é aceita](https://platform.claude.com/docs/pt-BR/models/sonnet-5-5/whats-new-sonnet-5-5#computer-20251124-is-not-supported). * [A ferramenta advisor rejeita Claude Opus 4.8, Claude Opus 4.7, Claude Sonnet 5 e Claude Haiku 5.5 como advisors](https://platform.claude.com/docs/pt-BR/models/sonnet-5-5/whats-new-sonnet-5-5#advisor-tool-pairings). Mais uma mudança altera o formato da resposta sem fazer nenhuma requisição falhar: [o texto entre chamadas de ferramentas volta em blocos `thinking`](https://platform.claude.com/docs/pt-BR/models/sonnet-5-5/whats-new-sonnet-5-5#text-between-tool-calls). Uma aplicação que faz streaming desse texto para seus usuários fica em silêncio entre as chamadas de ferramentas até definir um valor de `display` que retorne o texto, ou até desativar o pensamento antecipado com `between_tools`. [Novidades do Claude Sonnet 5.5](https://platform.claude.com/docs/pt-BR/models/sonnet-5-5/whats-new-sonnet-5-5) ## Como ele se compara | Model | Context | Max output | Price / MTok | Latency | Thinking | Default effort | Knowledge cutoff | | :----------------------------------------------------------------------------------- | :------ | :--------- | :----------------- | :------- | :------------------- | :------------- | :--------------- | | [Claude Fable 5.1](https://platform.claude.com/docs/pt-BR/models/fable-5-1/overview) | 1M | 128K | $10 / $50 | Slower | Adaptive (always on) | `high` | Jun 2026 | | [Claude Opus 5.5](https://platform.claude.com/docs/pt-BR/models/opus-5-5/overview) | 1M | 128K | $4 / $20 | Moderate | Adaptive (always on) | `medium` | Jun 2026 | | **Claude Sonnet 5.5** (this model) | 1M | 128K | $2 / $10 | Fast | Adaptive | `high` | Jun 2026 | | [Claude Haiku 5.5](https://platform.claude.com/docs/pt-BR/models/haiku-5-5/overview) | 1M | 128K | From $0.10 / $0.50 | Fastest | Adaptive | `medium` | Jun 2026 | * **Context:** 1M tokens is roughly 555k words or 2.5M Unicode characters on the current tokenizer (introduced with Claude Opus 4.7); models before it fit about 750k words in 1M tokens. 200k tokens is roughly 150k words. * **Max output:** Synchronous Messages API limit. On the Message Batches API, Claude Opus 5.5, Claude Opus 5, Claude Sonnet 5.5, Claude Sonnet 5, Claude Haiku 5.5, Claude Opus 4.8, Claude Opus 4.7, Claude Opus 4.6, and Claude Sonnet 4.6 support up to 300k output tokens with the output-300k-2026-03-24 beta header. * **Price / MTok:** Input / output, base price per million tokens. Batch API requests are 50% off; prompt caching reads cost 10% of the base input price (2.5% on Claude Fable 5.1 and Claude Mythos 5.1, 5% on Claude Opus 5.5 and Claude Sonnet 5.5). See Pricing for the full list. * **Latency:** Comparative latency, relative to the current lineup, as published in the models overview. Actual latency depends on prompt length, output length, and thinking effort. * **Thinking:** Adaptive thinking lets the model decide how much to think, steered by effort. Extended thinking is the manual budget\_tokens mode on earlier models. * **Default effort:** The effort parameter’s default on the Claude API. Models without a value don’t support the parameter. * **Knowledge cutoff:** Reliable knowledge cutoff: the date through which the model’s knowledge is most extensive and reliable. ## Especificações ### Model IDs | Platform | Model ID | | :-------------------------------------------------------------------------------------------------------- | :---------------------------- | | Claude API | `claude-sonnet-5-5` | | [Amazon Bedrock](https://platform.claude.com/docs/pt-BR/build-with-claude/claude-in-amazon-bedrock) | `anthropic.claude-sonnet-5-5` | | [Google Cloud](https://platform.claude.com/docs/pt-BR/build-with-claude/claude-on-vertex-ai) | `claude-sonnet-5-5` | | [Microsoft Foundry](https://platform.claude.com/docs/pt-BR/build-with-claude/claude-in-microsoft-foundry) | `claude-sonnet-5-5` | | [Claude Platform on AWS](https://platform.claude.com/docs/pt-BR/build-with-claude/claude-platform-on-aws) | `claude-sonnet-5-5` | ### Pricing | Feature | Value | | :---------------------------------------------------------------------------------------- | :------------------------------- | | Input | $2 / MTok | | Output | $10 / MTok | | [5m cache write](https://platform.claude.com/docs/pt-BR/build-with-claude/prompt-caching) | $2.50 / MTok | | [1h cache write](https://platform.claude.com/docs/pt-BR/build-with-claude/prompt-caching) | $4 / MTok | | [Cache read](https://platform.claude.com/docs/pt-BR/build-with-claude/prompt-caching) | $0.10 / MTok | | [Batch API](https://platform.claude.com/docs/pt-BR/build-with-claude/batch-processing) | 50% discount on input and output | [Full price list](https://platform.claude.com/docs/pt-BR/about-claude/pricing) ### Capabilities | Feature | Value | | :----------------------------------------------------------------------------------------------------------------------------- | :--------------------- | | [Context window](https://platform.claude.com/docs/pt-BR/build-with-claude/context-windows) | 1M tokens | | Max output | 128K tokens | | [Max output (Batch API, beta)](https://platform.claude.com/docs/pt-BR/build-with-claude/batch-processing#extended-output-beta) | 300K tokens | | [Thinking](https://platform.claude.com/docs/pt-BR/build-with-claude/thinking) | Adaptive | | [Default effort](https://platform.claude.com/docs/pt-BR/build-with-claude/effort) | `high` | | Comparative latency | Fast | | Input → output | Text and images → text | | Reliable knowledge cutoff | Jun 2026 | | Training data cutoff | Jun 2026 | ### Availability | Feature | Value | | :------------------------------------------------------------------------------- | :---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | [Status](https://platform.claude.com/docs/pt-BR/about-claude/model-deprecations) | Active (latest) | | Released | September 28, 2026 | | Retirement | Not sooner than September 28, 2027 | | Platforms | Claude API, [Amazon Bedrock](https://platform.claude.com/docs/pt-BR/build-with-claude/claude-in-amazon-bedrock), [Google Cloud](https://platform.claude.com/docs/pt-BR/build-with-claude/claude-on-vertex-ai), [Microsoft Foundry](https://platform.claude.com/docs/pt-BR/build-with-claude/claude-in-microsoft-foundry), [Claude Platform on AWS](https://platform.claude.com/docs/pt-BR/build-with-claude/claude-platform-on-aws) | ## Bom saber * O "adaptive thinking" (pensamento adaptativo) está ativado por padrão. A configuração de pensamento mais baixa é `between_tools`, que desativa o pensamento antecipado. Ela funciona com "effort" (esforço) `high` ou inferior. Consulte [Novidades no Claude Sonnet 5.5](https://platform.claude.com/docs/pt-BR/models/sonnet-5-5/whats-new-sonnet-5-5#turn-off-up-front-thinking). * Definir `temperature`, `top_p` ou `top_k` com um valor diferente do padrão retorna um erro 400. * O comprimento mínimo de prompt para "prompt caching" (cache de prompt) é de 512 tokens. Consulte [Cache de prompt](https://platform.claude.com/docs/pt-BR/build-with-claude/prompt-caching#cache-limitations). * Na [Message Batches API](https://platform.claude.com/docs/pt-BR/build-with-claude/batch-processing#extended-output-beta), o Claude Sonnet 5.5 suporta até 300k tokens de saída com o cabeçalho beta `output-300k-2026-03-24`. * Consulte limites e recursos programaticamente com a [Models API](https://platform.claude.com/docs/pt-BR/api/models/list). ## Recursos Diferenças de comportamento e padrões de prompt específicos do Claude Sonnet 5.5. O controle para profundidade de pensamento, "latency" (latência) e custo. Escolha um nível para cada carga de trabalho. Como o pensamento adaptativo funciona, quais configurações de pensamento cada modelo aceita e como os blocos de pensamento são preservados. ## Referência O prompt do sistema que o Claude Sonnet 5.5 usa no claude.ai e nos aplicativos Claude. Avaliações de segurança e decisões de implantação para o Claude Sonnet 5.5. Lista completa de preços, incluindo descontos em lote e tarifas de cache de prompt. Como funcionam os IDs de modelo, aliases e snapshots fixados. Status do ciclo de vida e compromissos de desativação para cada modelo Claude.