Claude Fable/Mythos 5.2 发布:弃用旧 toolset
Claude Platform release notes — November 9, 2026
推荐理由
开发者必须立即检查代码中的 system prompt 编辑逻辑与 toolset 版本,避免升级后遭遇 400 报错中断服务。
- We’ve launched Claude Fable 5.2 (claude-fable-5-2), built for demanding reasoning and long-horizon agentic work. Claude Mythos 5.2 (claude-mythos-5-2) offers the same capabilities only to organizations verified through Anthropic’s verification programs, such as the Cyber Verification Program. Both models have a 1M token context window, 128k max output tokens, and always-on adaptive thinking. They cost $8 USD per MTok of input and $40 USD per MTok of output (Claude Fable 5.1 and Claude Mythos 5.1 cost $10 USD per MTok of input and $50 USD per MTok of output). Claude Fable 5.2 is available on the Claude API, Claude Platform on AWS, and Claude Models on Google Cloud (Anthropic managed). It’s also available on Claude in Amazon Bedrock. It’s also available on Claude Models on Google Cloud (Google managed). It’s also available on Claude in Microsoft Foundry. See What’s new in Claude Fable 5.2 for API changes and migration guidance. For model-specific prompting patterns, see Prompting Claude Fable 5.2.
- Claude Fable 5.2 and Claude Mythos 5.2 enforce the prefix check for every account, whatever its age. Claude Fable 5.1 returns the error by default on accounts created on or after August 31, 2026 (see When prefix_mismatch_behavior is unset). If your code edits the system prompt, tools, or an earlier message and then sends back a Claude Fable 5.2 or Claude Mythos 5.2 thinking block from a later turn, the request returns a 400 error. Before you switch, check whether your code edits the prefix.
- On the Claude API and Claude Models on Google Cloud (Google managed), a conversation that moves onto Claude Fable 5.2 or Claude Mythos 5.2 keeps the reasoning from other models, including Claude Opus 5.5, Claude Sonnet 5.5, and Claude Haiku 5.5. When the conversation moves the other way, to any other model, including Claude Opus 5.5 and Claude Fable 5.1, the API drops the thinking blocks that Claude Fable 5.2 or Claude Mythos 5.2 produced, and the request still succeeds. See Switching models mid-conversation.
- Claude Fable 5.2 and Claude Mythos 5.2 support computer use through the computer_toolset_20260801 toolset. A request that declares the earlier computer_20251124 tool returns a 400 error on every platform except Amazon Bedrock, where the earlier tool still works. See Migrate from computer_20251124.
- With the advisor tool, which is in beta, a Claude Fable 5.2 or Claude Mythos 5.2 executor accepts only Claude Fable 5.2 or Claude Mythos 5.2 as its advisor. Any other advisor returns a 400 error, so set the advisor’s model to one of these two models when you move an executor to them. Every executor model accepts Claude Fable 5.2 as its advisor. See Model compatibility.
- Both models require 30-day data retention, like Claude Fable 5.1 and Claude Mythos 5.1. They aren’t available under zero data retention unless expressly authorized by Anthropic. See Model-specific data retention requirements.
- Thinking blocks that Claude Fable 5.2 and Claude Mythos 5.2 produce work only in the account that produced them, or in an account linked to it. See Preserved thinking.
- 我们已推出 Claude Fable 5.2(claude-fable-5-2),专为高难度推理和长周期智能体工作而构建。Claude Mythos 5.2(claude-mythos-5-2)提供相同的能力,但仅限通过 Anthropic 验证计划(如网络验证计划)验证的组织使用。这两个模型均具备 1M token 的上下文窗口、128k 的最大输出 token 数以及始终开启的自适应思考功能。输入价格为每百万 token 8 美元,输出价格为每百万 token 40 美元(Claude Fable 5.1 和 Claude Mythos 5.1 的输入价格为每百万 token 10 美元,输出价格为每百万 token 50 美元)。Claude Fable 5.2 可在 Claude API、AWS 上的 Claude Platform 以及 Google Cloud 上的 Claude Models(Anthropic 管理)上使用。它也在 Amazon Bedrock 上的 Claude 中可用。它也在 Google Cloud 上的 Claude Models(Google 管理)中可用。它也在 Microsoft Foundry 中的 Claude 中可用。有关 API 变更和迁移指南,请参阅《Claude Fable 5.2 的新增内容》。有关特定模型的提示模式,请参阅《提示 Claude Fable 5.2》。
- 无论账户创建时间长短,Claude Fable 5.2 和 Claude Mythos 5.2 都会对每个账户强制执行前缀检查。对于在 2026 年 8 月 31 日或之后创建的账户,Claude Fable 5.1 默认返回错误(参见“当 prefix_mismatch_behavior 未设置时”)。如果您的代码编辑了系统提示、工具或更早的消息,然后从后续轮次发回一个 Claude Fable 5.2 或 Claude Mythos 5.2 的思考块,请求将返回 400 错误。在切换之前,请检查您的代码是否编辑了前缀。
- 在 Claude API 和 Google Cloud 上的 Claude Models(Google 管理)上,当对话切换到 Claude Fable 5.2 或 Claude Mythos 5.2 时,会保留来自其他模型(包括 Claude Opus 5.5、Claude Sonnet 5.5 和 Claude Haiku 5.5)的推理内容。当对话反向切换至任何其他模型(包括 Claude Opus 5.5 和 Claude Fable 5.1)时,API 会丢弃由 Claude Fable 5.2 或 Claude Mythos 5.2 生成的思考块,但请求仍会成功。参见“对话中途切换模型”。
- Claude Fable 5.2 和 Claude Mythos 5.2 支持通过 computer_toolset_20260801 工具集进行计算机操作。声明使用较早的 computer_20251124 工具集的请求在所有平台上均会返回 400 错误,Amazon Bedrock 除外,在该平台上较早的工具仍可正常工作。参见“从 computer_20251124 迁移”。
- 在使用中的顾问工具(处于测试阶段),Claude Fable 5.2 或 Claude Mythos 5.2 执行器仅接受 Claude Fable 5.2 或 Claude Mythos 5.2 作为其顾问。任何其他顾问都会返回 400 错误,因此当将执行器迁移至这两个模型时,需将顾问的模型设置为其中之一。所有执行器模型均接受 Claude Fable 5.2 作为其顾问。请参阅模型兼容性。
- 这两个模型都需要 30 天的数据保留期,与 Claude Fable 5.1 和 Claude Mythos 5.1 相同。除非获得 Anthropic 明确授权,否则它们不支持零数据保留模式。请参阅特定模型的数据保留要求。
- Claude Fable 5.2 和 Claude Mythos 5.2 生成的思维块仅能在生成它们的账户中使用,或在与其关联的账户中使用。请参阅保留的思维。
更进一步:量化金融体系
看懂新闻只是起点——沿量化金融路径,把它变成能交付的工程能力