AI Devtools Radar

Anthropic API

模型 APIwww.anthropic.com37 条已发布变化

2 个来源在监控

变化时间线

other

UI / 表格结构重组以反映新的定价层级

定价页面表格和对比已重组,将 Max 和 Ultra 显示为主要付费层级,而不是 Max 5x / Max 20x 变体。

证据
−Max 5x Max 20x
+Max Ultra

www.anthropic.com · 另有 1 个来源报告了同一变化

pricing

Ultra 计划现已包含在 Max、Ultra 和 Team 计划的月度 API 点数权益中

Claude Ultra 计划订阅者现在与 Max 和 Team 计划一起获得月度 API 点数,该权益扩展到更多定价层级。

证据
−Claude Max and Team plans now include monthly API credits.
+Claude Max, Ultra, and Team plans now include monthly API credits.

docs.claude.com · 另有 1 个来源报告了同一变化

deprecationhigh

Claude Opus 4.8 的快速模式已弃用,将于 2026 年 11 月 30 日移除

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.

docs.claude.com

featurehigh

使用量和成本分析 API 以测试版推出新端点

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.

docs.claude.com · 另有 1 个来源报告了同一变化

api

Messages API 和 Token Counting API 的最大请求大小从 32 MB 增加到 128 MB

开发者现在可以向 Messages API 和 Token Counting API 发送更大的请求(最大 128 MB),可以处理更大的文档和负载。

证据
+We've raised the maximum request size for the Messages API and the Token Counting API from 32 MB to 128 MB on the first-party Claude API.

docs.claude.com

other

在发布说明中添加发布日期(2026 年 10 月 20 日)

为跟踪 API 变更和功能何时上线提供时间背景信息

证据
+October 20, 2026

docs.claude.com

featurehigh

用户档案功能已为多客户平台推出

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.

docs.claude.com

apihigh

Models API 新增工具间思考能力

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.

docs.claude.com

featurehigh

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.

docs.claude.com

pricing

团队计划定价中添加了最少席位要求

计划使用每席位每月 $20 的团队计划的客户现在必须至少承诺 20 个席位,可能会提高初始成本。

证据
−US$20/seat/month, billed annually. Usage cost scales with model and task.
+US$20/seat/month, billed annually, 20 seat minimum. Usage cost scales with model and task.

www.anthropic.com

other

文档参考从 'Introducing Claude Fable 5 and Claude Mythos 5' 更新为 'Claude Fable 5'

文档进行了小范围重组;用户应参考更新的文档链接了解模型规格、定价和可用性。

证据
−See Introducing Claude Fable 5 and Claude Mythos 5 for capabilities, API changes, and availability.
+See Claude Fable 5 for specifications, pricing, and availability.

docs.claude.com

deprecationhigh

Claude Haiku 4.5 代码在 Haiku 5.5 上中断;手动扩展思考 (budget_tokens) 返回 400 错误

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.

docs.claude.com

api

Models API 现已包含 'line' 字段以按模型族分组

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.

docs.claude.com

deprecationhigh

Claude Sonnet 5.5 引入的破坏性变更影响代码兼容性

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.

docs.claude.com

feature

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.

docs.claude.com · 另有 1 个来源报告了同一变化

positioning

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

docs.claude.com

apihigh

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

docs.claude.com

feature

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.

docs.claude.com · 另有 1 个来源报告了同一变化

featurehigh

Claude Managed Agents 权限策略现在支持 'auto' 评估模式

开发者现在可以配置权限策略以自动评估、拒绝或请求批准 agent 和 MCP 工具调用,并通过 agent.tool_use 和 agent.mcp_tool_use 事件中的新字段获取详细的评估报告。

证据
+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.

docs.claude.com · 另有 1 个来源报告了同一变化

feature

代码执行输出的 C2PA Content Credentials 支持现已包含音频文件

使用 Claude 代码执行工具的开发者现在可以通过 Files API 获取带有 C2PA Content Credentials 的音频文件,扩展了携带内容真实性标记的媒体文件类型。

证据
−supported image and video files that Claude produces through the code execution tool carry C2PA Content Credentials
+supported image, video, and audio files that Claude produces through the code execution tool carry C2PA Content Credentials

docs.claude.com · 另有 1 个来源报告了同一变化

apihigh

Claude Enterprise Admin API、Analytics API 和 Compliance API 现在需要在所有请求上包含 anthropic-version 标头

使用 Claude Enterprise Admin API、Analytics API 或 Compliance API 的开发者现在必须在对这些端点的每个请求中包含 anthropic-version 标头,与 Claude API 其余部分的要求保持一致。

证据
−Loading Loading Loading Loading Loading Loading Loading Loading Loading Loading Loading Loading Ask Docs
+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

docs.claude.com

pricinghigh

Claude 3.5 Fable (Fable 5.1) 读取定价从 $1 降至 $0.25 per MTok

用户将看到新 Fable 5.1 模型读取 token 成本减少 75%,使其对输入量大的工作负载更经济。

证据
−Fable 5 Read $1 / MTok
+Fable 5.1 Read $0.25 / MTok

www.anthropic.com · 另有 1 个来源报告了同一变化

featurehigh

Compliance API 会话端点结束 beta,覆盖 Cowork 和 Claude Code 会话

企业审计与数据留存流程可以在正式接口上使用会话转录获取能力,不再依赖 beta 请求头。

证据
+The Compliance API session endpoints are out of beta for Cowork and Claude Code sessions. See Retrieve session transcripts.

docs.claude.com · 另有 1 个来源报告了同一变化

apihigh

Admin API 进入 ant CLI 和 Python、TypeScript 等多语言 SDK

组织信息、成员、邀请等管理操作可以直接在 CLI 和各语言 SDK 的 client.beta.organization 下调用,不用再手写 HTTP 请求。

证据
+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.

docs.claude.com

featurehigh

Claude Enterprise 的 Admin API 用户管理端点现已正式上线

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

docs.claude.com

deprecation

明确说明:Claude Haiku 3.5 停用是 API 特定的,而不是通用的

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.

docs.claude.com

apihigh

Claude API 新增 anthropic-workspace-id 响应头

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.

docs.claude.com

feature

Compliance API 扩展支持来自 Cowork 和 Claude Code 的本地会话

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

docs.claude.com

other

为 Claude Opus 5 定价增加了美元货币标注

明确定价以美元计价,减少了国际用户的歧义。

证据
−$5 / $25 per MTok
+$5 / $25 USD per MTok

docs.claude.com

pricinghigh

移除 Claude API 的介绍性定价符号和条款

开发者将不再看到明确的介绍性定价费率 ($2/$10) 和日落日期 (2026 年 8 月 31 日),或之后的标准定价 ($3/$15)。这可能会影响开发者的定价决策和对费率变化的理解。

证据
−Input* Output* Write* Read* *Introductory pricing of $2/$10 per million input/output tokens through August 31, 2026; $3/$15 standard pricing thereafter.
+Input Output Write Read

www.anthropic.com · 另有 1 个来源报告了同一变化

deprecationhigh

Claude Opus 4.1(claude-opus-4-1-20250805)模型已停用

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.

docs.claude.com

feature

Dreams(研究预览版)现已支持 Claude Opus 5 模型

使用 Dreams 功能的开发者现在可以利用 Claude Opus 5,为研究预览版功能扩展了模型选择。

证据
+Dreams (research preview) now supports Claude Opus 5. See Supported models.

docs.claude.com · 另有 1 个来源报告了同一变化

api

Claude Managed Agents 更新语义现在使 version 字段可选

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.

docs.claude.com

deprecationhigh

Legacy Workbench 将于 2026 年 8 月 17 日停用

用户将失去对 Claude Console 中旧版 Workbench (platform.claude.com/workbench) 的访问权限。旧版 Workbench 中保存的提示词、变量和 evals 在更新版本中不受支持。用户需要在 2026 年 8 月 17 日之前导出他们想保留的任何数据。

证据
+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.

docs.claude.com

pricing

Team 计划最少成员数从 5 人降低至 2 人

较小规模的团队现在可以获得企业/团队级定价,降低了小型组织的准入门槛。

证据
−For teams of 5 to 150
+For teams of 2 to 150

www.anthropic.com

other

销售沟通措辞从「联系销售」更改为「与采购专家聊天」

营销信息已更新,强调与销售专家进行实时聊天交互,而不是一般性销售联系。

证据
−Contact sales
+Chat with buying specialist

www.anthropic.com · 另有 1 个来源报告了同一变化

feature

对话中系统消息功能现已在多个 Claude 模型和平台上正式推出

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.

docs.claude.com · 另有 1 个来源报告了同一变化