---
title: Claude Fable 5.1
url: https://platform.claude.com/docs/zh-CN/models/fable-5-1/overview
description: Claude Fable 5.1 概览：它的用途、各平台上的模型 ID、上下文窗口、输出限制、定价、可用性，以及使用它进行构建的相关资源。
---
**Latest.** Released September 1, 2026.
For demanding reasoning and long-horizon agentic work
Model ID: `claude-fable-5-1`
Context window: 1M tokens · Max output: 128K tokens · Input pricing: $10 / MTok · Output pricing: $50 / MTok
[Announcement](https://www.anthropic.com/claude-fable-and-mythos-5-1) · [What’s new](https://platform.claude.com/docs/zh-CN/models/fable-5-1/whats-new-fable-5-1) · [Migration guide](https://platform.claude.com/docs/zh-CN/models/fable-5-1/migration-guide)
## 概述
Claude Fable 5.1 在 Claude Fable 5 的基础上进行了扩展，输入和输出价格保持不变，缓存读取成本降至四分之一，并在长时间运行的智能体编码、多步骤研究以及文档、电子表格和幻灯片工作方面表现更强。对于大多数工作负载，请从 Claude Opus 5.5 开始（请参阅[选择模型](https://platform.claude.com/docs/zh-CN/about-claude/models/choosing-a-model)）。对于要求较高的推理和长周期智能体工作，或者当您在更高 effort 下对 Claude Opus 5.5 的评估仍然不达标时，请使用 Claude Fable 5.1。Claude Mythos 5.1 提供相同的能力，但仅面向通过 Anthropic 验证计划（例如 [Cyber Verification Program](https://support.claude.com/en/articles/14604842)）验证的组织。
如果您已经在调用 Claude Fable 5，有三项变更属于破坏性变更：[强制工具使用会返回错误](https://platform.claude.com/docs/zh-CN/models/fable-5-1/whats-new-fable-5-1#forced-tool-use-is-not-supported)、[只有 Claude Fable 5.1 和 Claude Mythos 5.1 可以读取 Claude Fable 5.1 的思考块](https://platform.claude.com/docs/zh-CN/models/fable-5-1/whats-new-fable-5-1#thinking-blocks-are-tied-to-the-model-that-produced-them)，以及[编辑早期轮次会使思考块失效](https://platform.claude.com/docs/zh-CN/models/fable-5-1/whats-new-fable-5-1#editing-earlier-turns-invalidates-thinking-blocks)。另有五项为新增功能：[按消息设置 effort](https://platform.claude.com/docs/zh-CN/models/fable-5-1/whats-new-fable-5-1#change-effort-mid-conversation-beta)（测试版）、[轮次作用域的系统消息](https://platform.claude.com/docs/zh-CN/models/fable-5-1/whats-new-fable-5-1#turn-scoped-system-messages-beta)（测试版）、[工具调用之间可读的进度更新](https://platform.claude.com/docs/zh-CN/models/fable-5-1/whats-new-fable-5-1#progress-updates-between-tool-calls-beta)（`display: "updates"`，测试版）、[更低的缓存读取价格](https://platform.claude.com/docs/zh-CN/models/fable-5-1/whats-new-fable-5-1#pricing)，以及[内容溯源](https://platform.claude.com/docs/zh-CN/models/fable-5-1/whats-new-fable-5-1#content-provenance)。
[Claude Fable 5.1 的新特性](https://platform.claude.com/docs/zh-CN/models/fable-5-1/whats-new-fable-5-1)
## Claude Fable 5.1 与 Claude Mythos 5.1
[Claude Mythos 5.1](https://platform.claude.com/docs/zh-CN/models/mythos-5-1/overview) 提供相同的能力，但仅面向通过 Anthropic 验证计划（例如 [Cyber Verification Program](https://support.claude.com/en/articles/14604842)）验证的组织。它与 Claude Fable 5.1 共享相同的规格和定价。如需申请访问权限，请申请涵盖您用例的计划，或联系您的 Anthropic、AWS 或 Google Cloud 客户团队。
## 对比情况
| Model | Context | Max output | Price / MTok | Latency | Thinking | Default effort | Knowledge cutoff |
| :------------------------------------------------------------------------------------- | :------ | :--------- | :----------------- | :------- | :------------------- | :------------- | :--------------- |
| **Claude Fable 5.1** (this model) | 1M | 128K | $10 / $50 | Slower | Adaptive (always on) | `high` | Jun 2026 |
| [Claude Opus 5.5](https://platform.claude.com/docs/zh-CN/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/zh-CN/models/sonnet-5-5/overview) | 1M | 128K | $2 / $10 | Fast | Adaptive | `high` | Jun 2026 |
| [Claude Haiku 5.5](https://platform.claude.com/docs/zh-CN/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.
## 规格
### Model IDs
| Platform | Model ID |
| :-------------------------------------------------------------------------------------------------------- | :--------------------------- |
| Claude API | `claude-fable-5-1` |
| [Amazon Bedrock](https://platform.claude.com/docs/zh-CN/build-with-claude/claude-in-amazon-bedrock) | `anthropic.claude-fable-5-1` |
| [Google Cloud](https://platform.claude.com/docs/zh-CN/build-with-claude/claude-on-vertex-ai) | `claude-fable-5-1` |
| [Microsoft Foundry](https://platform.claude.com/docs/zh-CN/build-with-claude/claude-in-microsoft-foundry) | `claude-fable-5-1` |
| [Claude Platform on AWS](https://platform.claude.com/docs/zh-CN/build-with-claude/claude-platform-on-aws) | `claude-fable-5-1` |
### Pricing
| Feature | Value |
| :---------------------------------------------------------------------------------------- | :------------------------------- |
| Input | $10 / MTok |
| Output | $50 / MTok |
| [5m cache write](https://platform.claude.com/docs/zh-CN/build-with-claude/prompt-caching) | $12.50 / MTok |
| [1h cache write](https://platform.claude.com/docs/zh-CN/build-with-claude/prompt-caching) | $20 / MTok |
| [Cache read](https://platform.claude.com/docs/zh-CN/build-with-claude/prompt-caching) | $0.25 / MTok |
| [Batch API](https://platform.claude.com/docs/zh-CN/build-with-claude/batch-processing) | 50% discount on input and output |
[Full price list](https://platform.claude.com/docs/zh-CN/about-claude/pricing)
### Capabilities
| Feature | Value |
| :----------------------------------------------------------------------------------------- | :--------------------- |
| [Context window](https://platform.claude.com/docs/zh-CN/build-with-claude/context-windows) | 1M tokens |
| Max output | 128K tokens |
| [Thinking](https://platform.claude.com/docs/zh-CN/build-with-claude/thinking) | Adaptive (always on) |
| [Default effort](https://platform.claude.com/docs/zh-CN/build-with-claude/effort) | `high` |
| Comparative latency | Slower |
| 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/zh-CN/about-claude/model-deprecations) | Active (latest) |
| Released | September 1, 2026 |
| Retirement | Not sooner than September 1, 2027 |
| Platforms | Claude API, [Amazon Bedrock](https://platform.claude.com/docs/zh-CN/build-with-claude/claude-in-amazon-bedrock), [Google Cloud](https://platform.claude.com/docs/zh-CN/build-with-claude/claude-on-vertex-ai), [Microsoft Foundry](https://platform.claude.com/docs/zh-CN/build-with-claude/claude-in-microsoft-foundry), [Claude Platform on AWS](https://platform.claude.com/docs/zh-CN/build-with-claude/claude-platform-on-aws) |
## 资源
针对长周期和智能体工作的模型专属提示指南。
从 Claude Fable 5、Claude Opus 5 或 Claude Opus 4.8 迁移时会发生哪些变化。
此模型的思考块何时保持可用：跨模型切换以及跨对话变更。
在对话中途更改 effort 级别，而不会使 "prompt cache"（提示缓存）失效。
处理分类器拒绝，并在另一个 Claude 模型上重试。
Claude Fable 5.1 上唯一的思考模式。使用 `effort` 控制思考深度。
## 参考
Claude Fable 5.1 在 claude.ai 和 Claude 应用中使用的系统提示。
Claude Fable 5.1 和 Claude Mythos 5.1 的安全评估与部署决策。
完整价格列表，包括批量折扣和提示缓存费率。
模型 ID、别名和固定快照的工作方式。
每个 Claude 模型的生命周期状态和退役承诺。