精选88Claude Platform 发布说明AI 编程与模型多源精选 ×2
Claude Platform 9月1日更新：Fable/Mythos 5.1发布及API破坏性变更
Claude Platform release notes — September 1, 2026
推荐理由
开发者必须注意：Fable 5.1移除了tool_choice any的支持，且思考块存在严格的模型版本绑定与内容一致性校验，不兼容旧逻辑会导致请求失败。请检查代码中的工具调用配置及历史消息管理策略。
- 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 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 and video 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.
- 我们推出了 Claude Fable 5.1（claude-fable-5-1），作为 Claude Fable 5 的继任者，适用于长期运行的智能体编码、知识工作和研究；同时推出 Claude Mythos 5.1（claude-mythos-5-1），供 Project Glasswing 参与者使用。这两个模型默认支持 1M token 上下文窗口、128k 最大输出 token，并始终启用自适应思考功能，定价为每百万 token（MTok）10/50 美元，与 Claude Fable 5 相同，缓存读取价格降至每百万 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。请参阅《Claude Fable 5.1 新功能》，了解功能、API 变更及迁移指南。
- 在 Claude Fable 5.1 和 Claude Mythos 5.1 上，提示词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。缓存写入费用保持不变。请参阅提示词缓存定价。
- 在 Claude Fable 5.1 和 Claude Mythos 5.1 上，不支持 tool_choice 类型为 any 和 tool，将返回 400 错误。auto 和 none 保持不变。为确保符合 schema 的工具输入，请使用严格工具调用或结构化输出。
- 由 Claude Fable 5.1 和 Claude Mythos 5.1 生成的思考块仅保留给生成它们的模型或更新版本的模型：较早的模型无法读取它们，且若将思考块重放至较早模型，API 会将其丢弃。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 还会检查思考块之前的内容是否未发生变更：对于 2026 年 8 月 31 日或之后创建的新账户，若在系统提示词、工具或更早消息变更后重放思考块，将返回 400 错误。通过添加 thinking-binding-controls-2026-08-01 beta 请求头，被丢弃的思考块将在 input_transformations 响应字段中报告，而 thinking.block_binding.prefix_mismatch_behavior 参数可选择拒绝或丢弃历史发生变化的思考块。请参阅“保留的思考”。
- 在 Claude API 上，Claude Fable 5.1、Claude Mythos 5.1 和 Claude Opus 5 已开放每条消息的努力程度调整功能的测试版。通过在 messages 中添加 role 为 "system" 的消息并在其中包含 output_config.effort，可在保持提示词缓存的同时更改后续轮次的努力程度。请在请求中包含 mid-conversation-output-config-2026-07-01 beta 请求头。请参阅“每条消息的努力程度”。
- 回合级系统消息处于测试阶段（mid-conversation-system-clear-at-2026-08-21 标头）。在角色为“system”的对话中间消息上设置 clear_at: "next_user_message"，它仅在当前回合渲染，随后保留在历史记录中且不产生 token 费用。按回合的提醒不会累积，也不会使提示缓存或后续的推理块失效。
- thinking.display 在测试阶段接受第三个值“updates”（thinking-display-updates-2026-08-18 标头）。推理返回时 thinking 字段为空，与“omitted”情况相同；Claude Fable 5.1、Claude Mythos 5.1 和 Claude Fable 5 在工具调用之间生成的简短进度更新将以文本形式返回，每个工具调用前最多一个 thinking 块。详见工具调用之间的进度更新。
- 由 Claude Fable 5.1 和 Claude Mythos 5.1 生成的文本带有 Anthropic 的文本水印，且通过代码执行工具生成的受支持图像和视频文件，在通过 Claude API 的 Files API 检索时带有 C2PA 内容凭证。标记无需更改您的请求或响应处理逻辑。
- 与 Claude Fable 5 一样，这两个模型都需要 30 天数据保留，除非获得 Anthropic 明确授权，否则不支持零数据保留。详见特定模型的数据保留要求。
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