---
title: Claude Fable 5.2
url: https://platform.claude.com/docs/pt-BR/models/fable-5-2/overview
description: "Uma visão geral do Claude Fable 5.2: para que serve, IDs de modelo em cada plataforma, janela de contexto, limites de saída, preços, disponibilidade e recursos para desenvolver com ele."
---
**Latest.** Released November 9, 2026.
For demanding reasoning and long-horizon agentic work
Model ID: `claude-fable-5-2`
Context window: 1M tokens · Max output: 128K tokens · Input pricing: $8 / MTok · Output pricing: $40 / MTok
[Announcement](https://www.anthropic.com/claude-fable-and-mythos-5-2) · [What’s new](https://platform.claude.com/docs/pt-BR/models/fable-5-2/whats-new-fable-5-2) · [Migration guide](https://platform.claude.com/docs/pt-BR/models/fable-5-2/migration-guide)
## Visão geral
Claude Fable 5.2 foi desenvolvido para raciocínio exigente e trabalho agêntico de longo horizonte. Os usos típicos incluem sessões de agentes que duram horas, pesquisas aprofundadas em várias etapas e análises levadas até um documento, uma planilha ou uma apresentação finalizados.
## Claude Fable 5.2 e Claude Mythos 5.2
O [Claude Mythos 5.2](https://platform.claude.com/docs/pt-BR/models/mythos-5-2/overview) oferece os mesmos recursos apenas para organizações verificadas por meio dos programas de verificação da Anthropic, como o [Cyber Verification Program](https://support.claude.com/en/articles/14604842). Ele compartilha as especificações e os preços do Claude Fable 5.2. Para solicitar acesso, inscreva-se no programa que abrange o seu caso de uso ou entre em contato com a sua equipe de conta.
## Como ele se compara
| Model | Context | Max output | Price / MTok | Latency | Thinking | Default effort | Knowledge cutoff |
| :------------------------------------------------------------------------------------- | :------ | :--------- | :----------------- | :------- | :------------------- | :------------- | :--------------- |
| **Claude Fable 5.2** (this model) | 1M | 128K | $8 / $40 | Moderate | 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](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 5.2, Claude Mythos 5.2, 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-fable-5-2` |
| [Amazon Bedrock](https://platform.claude.com/docs/pt-BR/build-with-claude/claude-in-amazon-bedrock) | `anthropic.claude-fable-5-2` |
| [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/pt-BR/build-with-claude/claude-models-on-google-cloud/google-managed) | `claude-fable-5-2` |
| [Microsoft Foundry](https://platform.claude.com/docs/pt-BR/build-with-claude/claude-in-microsoft-foundry) | `claude-fable-5-2` |
| [Claude Platform on AWS](https://platform.claude.com/docs/pt-BR/build-with-claude/claude-platform-on-aws) | `claude-fable-5-2` |
| [Claude Models on Google Cloud (Anthropic managed)](https://platform.claude.com/docs/pt-BR/build-with-claude/claude-models-on-google-cloud/anthropic-managed) | `claude-fable-5-2` |
### Pricing
| Feature | Value |
| :---------------------------------------------------------------------------------------- | :------------------------------- |
| Input | $8 / MTok |
| Output | $40 / MTok |
| [5m cache write](https://platform.claude.com/docs/pt-BR/build-with-claude/prompt-caching) | $10 / MTok |
| [1h cache write](https://platform.claude.com/docs/pt-BR/build-with-claude/prompt-caching) | $16 / MTok |
| [Cache read](https://platform.claude.com/docs/pt-BR/build-with-claude/prompt-caching) | $0.20 / 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 |
| [Thinking](https://platform.claude.com/docs/pt-BR/build-with-claude/thinking) | Adaptive (always on) |
| [Default effort](https://platform.claude.com/docs/pt-BR/build-with-claude/effort) | `high` |
| Comparative latency | Moderate |
| 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 | November 9, 2026 |
| Retirement | Not sooner than November 9, 2027 |
| Platforms | Claude API, [Amazon Bedrock](https://platform.claude.com/docs/pt-BR/build-with-claude/claude-in-amazon-bedrock), [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/pt-BR/build-with-claude/claude-models-on-google-cloud/google-managed), [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), [Claude Models on Google Cloud (Anthropic managed)](https://platform.claude.com/docs/pt-BR/build-with-claude/claude-models-on-google-cloud/anthropic-managed) |
## Bom saber
* O “adaptive thinking” (pensamento adaptativo) está sempre ativado e não pode ser desativado. Controle a profundidade do pensamento com o [parâmetro effort](https://platform.claude.com/docs/pt-BR/build-with-claude/effort).
* O “forced tool use” (uso forçado de ferramentas) (tipos de `tool_choice` `any` e `tool`) retorna um erro 400. Consulte [Pensamento e escolha de ferramenta](https://platform.claude.com/docs/pt-BR/models/fable-5-2/whats-new-fable-5-2#thinking-and-tool-choice).
* Omita `temperature`, `top_p` e `top_k`. Consulte [Parâmetros de amostragem](https://platform.claude.com/docs/pt-BR/build-with-claude/thinking#sampling-parameters) para ver os valores que retornam um erro 400.
* O Claude Fable 5.2 exige retenção de dados de 30 dias e não está disponível sob “zero data retention” (retenção zero de dados), a menos que seja expressamente autorizado pela Anthropic. Consulte [Requisitos de retenção de dados específicos do modelo](https://platform.claude.com/docs/pt-BR/manage-claude/api-and-data-retention#model-specific-data-retention-requirements).
* 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 Fable 5.2.
O que muda quando você migra do Claude Fable 5.1 ou de um modelo Claude Opus.
Editar turnos anteriores invalida os blocos de pensamento, para todas as contas.
Como o pensamento adaptativo funciona. É o único modo de pensamento no Claude Fable 5.2.
O controle da profundidade do pensamento, da latência e do custo. Escolha um nível para cada carga de trabalho.
Lide com recusas do classificador e tente novamente em outro modelo Claude.
Saída mais rápida do Claude Fable 5.2 em solicitações da Messages API, com preços premium.
## Referência
O prompt do sistema que o Claude Fable 5.2 usa no claude.ai e nos aplicativos Claude.
Avaliações de segurança e decisões de implantação para o Claude Fable 5.2 e o Claude Mythos 5.2.
Lista de preços completa, incluindo descontos em lote e tarifas de cache de prompt.
Como funcionam os IDs de modelo, os aliases e os snapshots fixados.
Status do ciclo de vida e compromissos de desativação para cada modelo Claude.