我们在 Models API 中新增了 capabilities.thinking.types.between_tools

我们已在 Models API 中添加了 capabilities.thinking.types.between_tools。GET /v1/models 和 GET /v1/models/{model_id} 现在会报告每个模型是否接受 thinking: {type: "between_tools"}，该设置会关闭预先思考。请参阅使用 Models API。Compliance API 现在会返回每个组织成员在 claude.ai 中保存为 Claude 的 Instructions 以及在 Cowork 中保存为 Global instructions 的文本，该功能面向 Claude Enterprise 组织处于测试阶段。请使用您现有的 Compliance Access Key 和 read:compliance_user_data 作用域调用 GET /v1/compliance/organizations/{org_uuid}/user_preferences。请参阅列出用户偏好设置。Fast mode 已结束针对 Claude Opus 5.5 的研究预览，您不再需要申请访问权限。向 Claude Opus 5.5 发出的请求不再需要 fast-mode-2026-02-01 beta 标头，仍然发送该标头的请求也可继续正常工作。Claude Opus 5.5 现在在 Start、Build 和 Scale 使用层级中具有默认的 fast mode 速率限制。Claude Opus 5 和 Claude Opus 4.8 的 Fast mode 仍处于研究预览阶段。向这些模型发送 fast mode 请求时请继续发送 beta 标头。Claude Opus 5.5 的 Fast mode 现已在 Microsoft Foundry 中的 Claude 上适用于托管在 Azure 上的部署。

We’ve added capabilities.thinking.types.between_tools to the Models API. GET /v1/models and GET /v1/models/{model_id} now report whether each model accepts thinking: {type: "between_tools"}, which turns off up-front thinking. See Using the Models API. The Compliance API now returns the text each organization member saved as Instructions for Claude in claude.ai and as Global instructions in Cowork, in beta for Claude Enterprise organizations. Call GET /v1/compliance/organizations/{org_uuid}/user_preferences with your existing Compliance Access Key and the read:compliance_user_data scope. See List user preferences. Fast mode is out of research preview for Claude Opus 5.5, and you no longer need to request access. Requests to Claude Opus 5.5 no longer require the fast-mode-2026-02-01 beta header, and requests that still send it keep working. Claude Opus 5.5 now has a default fast mode rate limit in the Start, Build, and Scale usage tiers. Fast mode for Claude Opus 5 and Claude Opus 4.8 remains in research preview. Keep sending the beta header with fast mode requests to those models. Fast mode for Claude Opus 5.5 is now available on Claude in Microsoft Foundry for deployments hosted on Azure.