使用 claude-opus-4-8 快速模式的开发者必须在 2026 年 11 月 30 日之前迁移到 Claude Opus 5.5,否则请求将返回错误。
证据
+We've deprecated fast mode for Claude Opus 4.8, with removal on November 30, 2026. After removal, requests to claude-opus-4-8 with speed: "fast" will return an error. To continue using fast mode, migrate to Claude Opus 5.5.
Claude Console 和 Claude Enterprise 组织现在可以通过新的 /v1/organizations/analytics/usage 和 /v1/organizations/analytics/cost 端点访问令牌使用量和成本数据,提供高级筛选和分组选项。
证据
+We've launched the Usage and Cost Analytics API in beta with the analytics-usage-cost-2026-08-24 beta header. Its /v1/organizations/analytics/usage and /v1/organizations/analytics/cost endpoints report token usage and cost for Claude Console and Claude Enterprise organizations.
平台运营商和 API 转售商现在可以将 API 请求与特定终端客户关联,实现细粒度安全执行操作。SDK 和 CLI 中提供新的 /v1/user_profiles 端点。
证据
+We've launched user profiles, so you can tell Anthropic which of your end customers each API request is for. If you operate a platform or gateway, or resell API access, a safety enforcement action can then apply to one end customer instead of your whole organization. The SDK and the ant CLI support the new /v1/user_profiles endpoints.
API 用户现在可以通过 GET /v1/models 端点查询模型是否支持思考:{type: "between_tools"},从而更好地控制模型何时进行推理。
证据
+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.
OpenTelemetry 导出功能已推出测试版,用于追踪 Messages API 和 Claude Managed Agents
开发者现在可以将 Claude API 请求与其可观测性后端集成,通过 Python、TypeScript、C#、Go、Java、PHP 和 Ruby SDK 追踪和监控 Messages API 请求以及 Claude Managed Agents 会话。
证据
+We've launched OpenTelemetry export in beta, so you can trace Messages API requests and Claude Managed Agents sessions in your observability backend. The Claude SDK emits spans in Python, TypeScript, C#, Go, Java, PHP, and Ruby.
使用 Claude Haiku 4.5 的开发者必须迁移代码至 Haiku 5.5,因为新版本默认启用自适应思考并改变 token 计数方式,破坏现有实现。
证据
+Code written for Claude Haiku 4.5 can break on Claude Haiku 5.5. Manual extended thinking (budget_tokens) returns a 400 error, and adaptive thinking is on by default.
开发者现在可以使用 GET /v1/models 和 GET /v1/models/{model_id} 返回的 'line' 字段来分组和分类模型(例如 opus、sonnet),无需手动解析模型 ID。
证据
+We've added a line field to the Models API. GET /v1/models and GET /v1/models/{model_id} now return the model line each model belongs to. Claude Opus 4.5 and Claude Opus 4.6 both report opus, for example. Use line to group models without parsing their IDs.
为 Claude Sonnet 5 编写的代码可能在 Claude Sonnet 5.5 上出现问题;开发者需要进行迁移。变更包括:thinking 行为修改、forced tool use 返回错误、computer use tool 弃用以及 advisor tool 限制。
证据
+Code written for Claude Sonnet 5 can break on Claude Sonnet 5.5 in five ways. To turn off up-front thinking, send thinking: {"type": "between_tools"} instead of "disabled", at high effort or below. Forced tool use (tool_choice types any and tool) returns a 400 error. Thinking blocks are tied to the model and the conversation. On the Claude API and Google Cloud, the earlier computer_20251124 computer use tool isn't accepted. The advisor tool rejects Claude Opus 4.8, Claude Opus 4.7, and Claude Sonnet 5 as advisors.
Compliance API local session endpoints exit beta for Claude for Microsoft 365 in Office applications.
The Compliance API local session endpoints for Claude in Excel, PowerPoint, Word, and Outlook (office_agents) are now generally available, no longer in beta status.
证据
+The Compliance API local session endpoints are out of beta for Claude for Microsoft 365 sessions in Excel, PowerPoint, Word, and Outlook (product_surface values beginning with office_agents). See Sessions on users' machines.
Claude Fable 5 positioning changed from 'widely released model' to 'model open to all customers'.
Claude Fable 5 availability positioning has been adjusted to emphasize it is available to all customers, indicating a change in access scope or marketing messaging.
证据
−We've launched Claude Fable 5 (claude-fable-5), our most capable widely released model
+We've launched Claude Fable 5 (claude-fable-5), our most capable model open to all customers
Claude Opus 5.5 需要 API 变更:思维字段禁用、使用 effort 参数、新的 computer 工具集
开发者必须更新代码以移除思维字段配置,使用 effort 参数控制思维深度,并在 Claude API / Google Cloud 上迁移至 computer_toolset_20260801(或在 Bedrock 上保持 computer_20251124)
证据
+On Claude Opus 5.5, thinking can't be disabled: thinking: {"type": "disabled"} and thinking: {"type": "enabled", ...} return a 400 error. Omit the thinking field and control thinking depth with the effort parameter. tool_choice types any and tool also return a 400 error, as on Claude Fable 5.1; use auto with strict tool use. On the Claude API and Google Cloud, computer use on this model requires the computer_toolset_20260801 toolset and the earlier computer_20251124 tool returns a 400 error
Compliance API now returns transcripts from Claude in Chrome sessions in beta
Claude Enterprise 组织现在可以通过现有的 Compliance API local session endpoints,使用当前的 Compliance Access Key 和 read:compliance_user_data 范围来访问 Claude in Chrome 会话的转录文本。
证据
+The Compliance API local session endpoints now also return transcripts of Claude in Chrome sessions (product_surface value claude_in_chrome), in beta for Claude Enterprise organizations, with your existing Compliance Access Key and the read:compliance_user_data scope.
+Claude Managed Agents permission policies now include auto: the server evaluates each agent or MCP tool call and runs it, denies it, or pauses for your approval. agent.tool_use and agent.mcp_tool_use events report how each call was evaluated in an evaluation field alongside evaluated_permission.
+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.
Ask Docs
+The Admin API is now available in the ant CLI and the Python, TypeScript, C#, Go, Java, PHP, and Ruby SDKs under client.beta.organization. They cover organization info, members, invites, workspaces and workspace members, API keys, rate limits, service accounts, workload identity federation issuers and rules, and customer-managed encryption keys.
使用 Claude Enterprise 的组织现在可以通过 Admin API 管理用户、邀请、群组和自定义角色,无需 beta headers。
证据
+The Admin API user-management endpoints for Claude Enterprise (claude.ai) organizations (members, invites, groups, and custom roles) are now generally available. The anthropic-beta: ce-user-management-2026-07-13 header is no longer required on group and custom-role requests
在 Amazon Bedrock 或 Google Cloud 上使用 Claude Haiku 3.5 的开发者可以继续使用它;只有 Claude API 用户需要迁移到 Claude Haiku 4.5。
证据
−We've retired the Claude Sonnet 3.7 model (claude-3-7-sonnet-20250219) and the Claude Haiku 3.5 model (claude-3-5-haiku-20241022). All requests to these models will now return an error.
+We've retired the Claude Sonnet 3.7 model (claude-3-7-sonnet-20250219) and the Claude Haiku 3.5 model (claude-3-5-haiku-20241022). All requests to Claude Sonnet 3.7 will now return an error. Requests to Claude Haiku 3.5 on the Claude API will now return an error; it remains available on Amazon Bedrock and Google Cloud.
开发者现在可以使用新的 wrkspc_ 前缀的响应头识别 API 响应背后的工作区,从而更好地进行工作区管理和组织跟踪。
证据
+We've added the anthropic-workspace-id response header to the Claude API. It carries the wrkspc_-prefixed ID of the workspace that the request's API key or access token resolved to, including your organization's Default Workspace. See Identify the workspace behind an API response.
Claude Enterprise 组织现在可以使用新端点检索在用户机器上本地运行的 Cowork 和 Claude Code 会话的录音和元数据:GET /v1/compliance/apps/sessions/local、GET /v1/compliance/apps/sessions/local/{session_id} 和 GET /v1/compliance/apps/sessions/local/{session_id}/messages。
证据
+The Compliance API now returns transcripts of Cowork and Claude Code sessions that run on your users' machines, in beta for Claude Enterprise organizations. GET /v1/compliance/apps/sessions/local lists sessions across your organization, GET /v1/compliance/apps/sessions/local/{session_id} retrieves one session's metadata, and GET /v1/compliance/apps/sessions/local/{session_id}/messages returns its transcript
−Input*
Output*
Write*
Read*
*Introductory pricing of $2/$10 per million input/output tokens through August 31, 2026; $3/$15 standard pricing thereafter.
使用 Claude Opus 4.1 的用户和应用将收到错误,必须迁移到 Claude Opus 5。研究人员可以通过外部研究人员访问计划申请继续使用。
证据
+We've retired the Claude Opus 4.1 model (claude-opus-4-1-20250805). All requests to this model will now return an error. We recommend upgrading to Claude Opus 5. Researchers can request ongoing access through the External Researcher Access Program.
用户现在可以在不提供 version 的情况下更新 agent(无条件更新),或提供 version 以实现乐观并发控制,在版本不匹配时返回 409 错误。
证据
+The version field is now optional when updating a Claude Managed Agents agent. Supply it for optimistic concurrency (a mismatch returns a 409 error), or omit it to apply the update unconditionally. See Update semantics.
+The legacy Workbench (platform.claude.com/workbench) in the Claude Console is being sunset with access ending on August 17, 2026. Saved prompts, variables, and evals are not supported in the updated Workbench. You can export any data you want to keep from the banner and under your Organizational Settings.
使用 Claude Fable 5、Claude Mythos 5 和 Claude Opus 4.8 的开发者现在可以在 Claude API、Amazon Bedrock 和 Google Cloud 上使用对话中系统消息,无需 beta 请求头。
证据
+Mid-conversation system messages are available on Claude Fable 5, Claude Mythos 5, and Claude Opus 4.8, on the Claude API, Claude in Amazon Bedrock, and Google Cloud. No beta header is required.