我们推出了 Claude Fable 5.1（claude-fable-5-1），它是 Claude Fable 5 的继任者，面向长时间运行的智能体编程、知识工作和研究，同时推出了 Claude Mythos 5.1（clau

我们推出了 Claude Fable 5.1（claude-fable-5-1），它是 Claude Fable 5 的继任者，面向长时间运行的智能体编程、知识工作和研究，同时为 Project Glasswing 参与者推出了 Claude Mythos 5.1（claude-mythos-5-1）。两个模型默认支持 100 万 token 上下文窗口、128k 最大输出 token，并始终启用自适应思考，价格为每百万 token 10 美元 / 50 美元，与 Claude Fable 5 相同，缓存读取降至每百万 token 0.25 美元。Claude Fable 5.1 可在 Claude API、Amazon Bedrock 中的 Claude、AWS 上的 Claude Platform、Google Cloud 上的 Claude 以及 Microsoft Foundry 中的 Claude 上使用。有关功能、API 变更和迁移指南，请参阅 Claude Fable 5.1 的新增内容。Claude Fable 5.1 和 Claude Mythos 5.1 上的提示缓存读取费用为每百万 token 0.25 美元：为基础输入价格的 0.025 倍，而其他模型为 0.1 倍。缓存写入保持不变。请参阅提示缓存定价。在 Claude Fable 5.1 和 Claude Mythos 5.1 上，不支持 tool_choice 类型 any 和 tool，并会返回 400 错误。auto 和 none 保持不变。为保证工具输入符合 schema，请使用严格工具使用或结构化输出。Claude Fable 5.1 和 Claude Mythos 5.1 生成的思考块仅会为生成它们的模型或更新模型保留：更早的模型无法读取它们，API 会丢弃重放到更早模型的思考块。Claude Fable 5.1 接受来自 Claude Opus 5、Claude Fable 5、Claude Mythos 5 及更早 Claude 模型的思考块。在 Claude Fable 5.1 上，API 还会检查块之前的任何内容是否已更改：对于在 2026 年 8 月 31 日或之后创建的新账户，在系统提示、工具或更早消息更改后重放思考块会返回 400 错误。使用 thinking-binding-controls-2026-08-01 beta 标头时，被丢弃的块会在 input_transformations 响应字段中报告，而 thinking.block_binding.prefix_mismatch_behavior 可选择拒绝还是丢弃历史已更改的块。请参阅保留思考。按消息更改 effort 功能在 Claude API 上的 Claude Fable 5.1、Claude Mythos 5.1 和 Claude Opus 5 上处于 beta 阶段。在 messages 中添加带有 output_config.effort 的 role: "system" 消息，可在保留提示缓存的同时更改后续轮次的 effort。请在请求中包含 mid-conversation-output-config-2026-07-01 beta 标头。请参阅按消息 effort。轮次作用域系统消息处于 beta 阶段（mid-conversation-system-clear-at-2026-08-21 标头）。在对话中间的 role: "system" 消息上设置 clear_at: "next_user_message"，它仅会在当前轮次呈现，然后以零 token 成本保留在历史记录中。每轮提醒不会累积，也不会使提示缓存或后续思考块失效。thinking.display 在 beta 中接受第三个值 "updates"（thinking-display-updates-2026-08-18 标头）。推理会以空的 thinking 字段返回，如同在 "omitted" 下一样，而 Claude Fable 5.1、Claude Mythos 5.1 和 Claude Fable 5 在工具调用之间写入的简短进度更新会以文本形式返回，在工具调用前最多有一个思考块。请参阅工具调用之间的进度更新。Claude Fable 5.1 和 Claude Mythos 5.1 生成的文本带有 Anthropic 的文本水印，并且当你在 Claude API 上通过 Files API 检索 Claude 通过代码执行工具生成的支持的图像、视频和音频文件时，这些文件带有 C2PA 内容凭证。标记无需更改你的请求或响应处理。与 Claude Fable 5 一样，两个模型都要求 30 天数据保留，除非 Anthropic 明确授权，否则不可在零数据保留下使用。请参阅特定模型的数据保留要求。Admin API 的 Claude Enterprise 端点（用户管理和支出限制）、Claude Enterprise Analytics API 和 Compliance API 的指南现在显示 anthropic-version 标头；请像 Claude API 的其余部分一样，在每次请求这些端点时发送它。请参阅 API 版本。

We’ve launched Claude Fable 5.1 (claude-fable-5-1), the successor to Claude Fable 5 for long-running agentic coding, knowledge work, and research, alongside Claude Mythos 5.1 (claude-mythos-5-1) for Project Glasswing participants. Both models support a 1M token context window by default, 128k max output tokens, and always-on adaptive thinking, at $10 / $50 USD per MTok, the same as Claude Fable 5, with cache reads cut to $0.25 USD per MTok. Claude Fable 5.1 is available on the Claude API, Claude in Amazon Bedrock, Claude Platform on AWS, Claude on Google Cloud, and Claude in Microsoft Foundry. See What’s new in Claude Fable 5.1 for capabilities, API changes, and migration guidance. Prompt cache reads on Claude Fable 5.1 and Claude Mythos 5.1 cost $0.25 USD per million tokens: 0.025x the base input price, compared with 0.1x on other models. Cache writes are unchanged. See Prompt caching pricing. On Claude Fable 5.1 and Claude Mythos 5.1, tool_choice types any and tool aren’t supported and return a 400 error. auto and none are unchanged. To guarantee schema-conformant tool inputs, use strict tool use or structured outputs. Thinking blocks produced by Claude Fable 5.1 and Claude Mythos 5.1 are preserved only for the model that produced them or a newer one: earlier models can’t read them, and the API drops one replayed to an earlier model. Claude Fable 5.1 accepts thinking blocks from Claude Opus 5, Claude Fable 5, Claude Mythos 5, and earlier Claude models. On Claude Fable 5.1, the API also checks that nothing before a block has changed: for new accounts created on or after August 31, 2026, replaying one after the system prompt, tools, or an earlier message changed returns a 400 error. With the thinking-binding-controls-2026-08-01 beta header, dropped blocks are reported in an input_transformations response field, and thinking.block_binding.prefix_mismatch_behavior chooses between rejecting and dropping blocks whose history changed. See Preserved thinking. Per-message effort changes are in beta on Claude Fable 5.1, Claude Mythos 5.1, and Claude Opus 5 on the Claude API. Add a role: "system" message with output_config.effort inside messages to change effort for later turns while preserving the prompt cache. Include the mid-conversation-output-config-2026-07-01 beta header in your requests. See Per-message effort. Turn-scoped system messages are in beta (mid-conversation-system-clear-at-2026-08-21 header). Set clear_at: "next_user_message" on a mid-conversation role: "system" message and it renders for the current turn only, then stays in the history at no token cost. Per-turn reminders don’t accumulate and don’t invalidate the prompt cache or later thinking blocks. thinking.display accepts a third value, "updates", in beta (thinking-display-updates-2026-08-18 header). Reasoning comes back with an empty thinking field, as under "omitted", and the short progress updates that Claude Fable 5.1, Claude Mythos 5.1, and Claude Fable 5 write between tool calls come back as text, at most one thinking block before a tool call. See Progress updates between tool calls. Text generated by Claude Fable 5.1 and Claude Mythos 5.1 carries Anthropic’s text watermark, and supported image, video, and audio files that Claude produces through the code execution tool carry C2PA Content Credentials when you retrieve them through the Files API on the Claude API. Marking requires no changes to your requests or response handling. Like Claude Fable 5, both models require 30-day data retention and aren’t available under zero data retention unless expressly authorized by Anthropic. See Model-specific data retention requirements. The guides for the Claude Enterprise endpoints of the Admin API (user management and spend limits), the Claude Enterprise Analytics API, and the Compliance API now show the anthropic-version header; send it on every request to these endpoints, as in the rest of the Claude API. See API versions.