---
title: Claude Haiku 5.5
url: https://platform.claude.com/docs/pt-BR/models/haiku-5-5/overview
description: "Claude Haiku 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 October 7, 2026.
For high-volume, latency-sensitive tasks such as classification, extraction, and routing
Model ID: `claude-haiku-5-5`
Context window: 1M tokens · Max output: 128K tokens · Input pricing: From $0.10 / MTok · Output pricing: From $0.50 / MTok
[Announcement](https://www.anthropic.com/claude-haiku-5-5) · [What’s new](https://platform.claude.com/docs/pt-BR/models/haiku-5-5/whats-new-haiku-5-5) · [Migration guide](https://platform.claude.com/docs/pt-BR/models/haiku-5-5/migration-guide)
## Visão geral
O Claude Haiku 5.5 foi criado para trabalhos de alto volume e sensíveis à latência, como classificação, roteamento, extração e tarefas de subagentes. Ele oferece suporte a "adaptive thinking" (pensamento adaptativo) com o parâmetro "effort" (esforço), uma "context window" (janela de contexto) de 1M tokens e até 128k tokens de saída. Ele usa o mesmo tokenizador mais recente do Claude 4.7 e modelos posteriores, portanto o mesmo texto conta como aproximadamente 30% mais tokens do que no Claude Haiku 4.5. Seus blocos de pensamento funcionam apenas na conta que os produziu ou em uma conta vinculada a ela.
Para alterações de código, consulte o [guia de migração](https://platform.claude.com/docs/pt-BR/models/haiku-5-5/migration-guide). Para IDs de modelo, preços e limites, consulte a [visão geral do Claude Haiku 5.5](https://platform.claude.com/docs/pt-BR/models/haiku-5-5/overview). Para orientações sobre prompts, consulte [Prompting do Claude Haiku 5.5](https://platform.claude.com/docs/pt-BR/build-with-claude/prompt-engineering/prompting-claude-haiku-5-5).
[Novidades do Claude Haiku 5.5](https://platform.claude.com/docs/pt-BR/models/haiku-5-5/whats-new-haiku-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](https://platform.claude.com/docs/pt-BR/models/sonnet-5-5/overview) | 1M | 128K | $2 / $10 | Fast | Adaptive | `high` | Jun 2026 |
| **Claude Haiku 5.5** (this model) | 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-haiku-5-5` |
| [Amazon Bedrock](https://platform.claude.com/docs/pt-BR/build-with-claude/claude-in-amazon-bedrock) | `anthropic.claude-haiku-5-5` |
| [Google Cloud](https://platform.claude.com/docs/pt-BR/build-with-claude/claude-on-vertex-ai) | `claude-haiku-5-5` |
| [Microsoft Foundry](https://platform.claude.com/docs/pt-BR/build-with-claude/claude-in-microsoft-foundry) | `claude-haiku-5-5` |
| [Claude Platform on AWS](https://platform.claude.com/docs/pt-BR/build-with-claude/claude-platform-on-aws) | `claude-haiku-5-5` |
### Pricing
| Feature | Value |
| :---------------------------------------------------------------------------------------- | :-------------------------------------------------------------------------------------------- |
| Input | $0.10 / MTok for prompts up to 100,000 tokens; $0.50 / MTok for prompts over 100,000 tokens |
| Output | $0.50 / MTok for prompts up to 100,000 tokens; $2.50 / MTok for prompts over 100,000 tokens |
| [5m cache write](https://platform.claude.com/docs/pt-BR/build-with-claude/prompt-caching) | $0.125 / MTok for prompts up to 100,000 tokens; $0.625 / MTok for prompts over 100,000 tokens |
| [1h cache write](https://platform.claude.com/docs/pt-BR/build-with-claude/prompt-caching) | $0.20 / MTok for prompts up to 100,000 tokens; $1 / MTok for prompts over 100,000 tokens |
| [Cache read](https://platform.claude.com/docs/pt-BR/build-with-claude/prompt-caching) | $0.01 / MTok for prompts up to 100,000 tokens; $0.05 / MTok for prompts over 100,000 tokens |
| [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) | `medium` |
| Comparative latency | Fastest |
| 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 | October 7, 2026 |
| Retirement | Not sooner than October 7, 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. Controle a profundidade do pensamento com o [parâmetro effort](https://platform.claude.com/docs/pt-BR/build-with-claude/effort).
* Omita `temperature`, `top_p` e `top_k`. Consulte [Remova os parâmetros de amostragem](https://platform.claude.com/docs/pt-BR/models/haiku-5-5/migration-guide#remove-sampling-parameters) para ver os valores que retornam um erro 400.
* Na [Message Batches API](https://platform.claude.com/docs/pt-BR/build-with-claude/batch-processing#extended-output-beta), o Claude Haiku 5.5 suporta até 300k tokens de saída com o cabeçalho beta `output-300k-2026-03-24`.
* O comprimento mínimo de prompt armazenável em cache é de 512 tokens. Consulte [Cache de prompt](https://platform.claude.com/docs/pt-BR/build-with-claude/prompt-caching#cache-limitations).
* Consulte limites e capacidades programaticamente com a [Models API](https://platform.claude.com/docs/pt-BR/api/models/list).
## Recursos
Diferenças de comportamento e padrões de prompting específicos do Claude Haiku 5.5.
Escolha um modelo e um nível de esforço, estruture prompts e faça streaming da saída para respostas mais rápidas.
O Claude Haiku 5.5 determina quando e quanto pensar. Direcione a profundidade com `effort`.
Como a janela de contexto é contabilizada e gerenciada.
## Referência
O prompt do sistema que o Claude Haiku 5.5 usa no claude.ai e nos aplicativos Claude.
Avaliações de segurança e decisões de implantação para o Claude Haiku 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.