What's new in Claude

Claude API·Sep 23, 2026

Cache diagnostics is out of beta on the Claude API and no longer requires the cache-diagnosis-2026-04-07…

Include the diagnostics object on a Messages request to opt in; requests that still send the header work as before. Responses from POST /v1/messages now always include the diagnostics field, which is null when the request did not include the diagnostics object.

Claude API·Sep 22, 2026

On Claude Opus 5.5, thinking can't be disabled: thinking: {"type": "disabled"} and thinking: {"type":…

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; on Amazon Bedrock, computer_20251124 keeps working. Fast mode (research preview) is available for Claude Opus 5.5 on the Claude API. Tools can now be defined inside a mid-conversation system message, in beta on the Claude API with the inline-tools-2026-09-15 beta header.

Claude API·Sep 18, 2026

For cache diagnostics, a response to a request that sends the cache-diagnosis-2026-04-07 beta header now…

The field is null when the request did not include the diagnostics object. Previously the field was omitted in that case. 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 API·Sep 14, 2026

The Messages API can now compact a conversation on demand on the Claude API, in beta with the…

Send the top-level compaction parameter, and the API returns a signed compaction block that summarizes the messages you sent. On later requests, send that block first, in place of those messages. You choose when to compact, the request can run in the background, and you can keep recent turns word for word after the summary. On models with preserved thinking, the thinking in those kept turns can stay valid. With the thinking-binding-controls-2026-08-01 beta header, the input_transformations response field gains a second entry type, thinking_mismatch_allowed.

Claude API·Sep 10, 2026

Claude Managed Agents permission policies now include auto: the server evaluates each agent or MCP tool call…

Version 1.32.0 of the ant CLI adds ant beta:sessions connect, which attaches your terminal to a Claude Managed Agents session.

Claude API·Sep 9, 2026

For cache diagnostics, the API now stores a request's fingerprint only when the request includes the…

A request that sends only the cache-diagnosis-2026-04-07 beta header is still accepted, but no fingerprint is stored. A later turn that points previous_message_id at it reports previous_message_not_found. Include diagnostics on every turn, with "previous_message_id": null on the first.

Claude API·Sep 3, 2026

Version 1.30.0 of the ant CLI adds ant apply, which creates and updates agents, environments, skills, memory…

Describe each resource in a file, run ant apply, and approve the plan it prints. Commit the claude-lock.json lockfile it writes so that later runs, on your machine or in CI, update the same resources instead of creating new ones. Per-message effort changes, in beta, are also available on Google Cloud for Claude Fable 5.1, Claude Mythos 5.1, and Claude Opus 5, with the same mid-conversation-output-config-2026-07-01 beta header.

Claude API·Sep 1, 2026

Prompt cache reads on Claude Fable 5.1 and Claude Mythos 5.1 cost $0.25 USD per million tokens: 0.025x the…

Cache writes are unchanged. 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. 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. Per-message effort changes are in beta on Claude Fable 5.1, Claude Mythos 5.1, and Claude Opus 5 on the Claude API. Turn-scoped system messages are in beta (mid-conversation-system-clear-at-2026-08-21 header). thinking.display accepts a third value, "updates", in beta (thinking-display-updates-2026-08-18 header). 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. Like Claude Fable 5, both models require 30-day data retention and aren't available under zero data retention unless expressly authorized by Anthropic. 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.

Claude API·Aug 27, 2026

In Python SDK 1.2.0, TypeScript SDK 0.122.0, Go SDK 1.68.0, Java SDK 2.59.0, Ruby SDK 1.67.0, and C# SDK…

With this change, client.beta.skills.delete() deletes a Skill together with all of its versions, and the beta Messages type BetaSkill (the container Skill reference) is renamed BetaContainerSkill. Requests that still send the beta headers keep receiving the beta shapes. You can now create personal keys and service account keys in the Claude Console.

Claude API·Aug 26, 2026

The Compliance API session endpoints are out of beta for Cowork and Claude Code sessions

The Compliance API local session endpoints now also return transcripts of Claude Science sessions (product_surface value claude_science) and Claude for Microsoft 365 sessions in Excel, PowerPoint, Word, and Outlook (product_surface values beginning with office_agents), in beta for Claude Enterprise organizations, with your existing Compliance Access Key and the read:compliance_user_data scope. 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.

Claude API·Aug 20, 2026

We've released v1.0 of the Python SDK

The SDK's HTTP layer moves from httpx to httpx2, a maintained, API-compatible fork: build custom http_client, Timeout, and transport objects from httpx2 (the DefaultHttpxClient helpers are unchanged), and call httpx2.alias_httpx() at startup if you rely on tracing or mocking libraries that patch httpx. v1.0 requires Python 3.10 or later and removes long-deprecated surface, including the legacy Text Completions API, the temperature, top_p, and top_k parameters on Messages methods, and the tool runner's client-side compaction_control. On the async client,.with_raw_response results now need await response.parse(), and AnthropicBedrock now raises an error when no AWS region is configured instead of defaulting to us-east-1. The computer use and browser use toolsets (computer_toolset_20260801 and browser_toolset_20260801) are now available on Google Cloud for Claude Fable 5, Claude Mythos 5, Claude Opus 5, Claude Sonnet 5, and Claude Opus 4.8.

Claude API·Aug 19, 2026

The computer use tool is out of beta on the Claude API as the computer_toolset_20260801 toolset: no beta…

Earlier beta versions remain available. Upgrading an existing integration changes the request shape and tool handling; see Migrate from computer_20251124. We've launched the browser use tool (browser_toolset_20260801), a client toolset for driving a browser that your application hosts. Both toolsets are available for Claude Fable 5, Claude Mythos 5, Claude Opus 5, Claude Sonnet 5, and Claude Opus 4.8 on the Claude API. The Files API is out of beta on the Claude API. Agent Skills and the Skills API (/v1/skills) are out of beta on the Claude API. The Admin API user-management endpoints for Claude Enterprise (claude.ai) organizations (members, invites, groups, and custom roles) are out of beta. You can now restrict which sites a Claude Managed Agents agent's web_search and web_fetch tools can reach. Claude Managed Agents sessions that run in a self-hosted sandbox can now attach memory stores. The session viewer in the Claude Console has been redesigned with a timeline minimap, a transcript grouped by model request, and an Inspector panel for session details and cost, raw events, per-tool statistics, mounted resources, and per-thread activity.

Claude API·Aug 18, 2026

Workbench is now playground in the Claude Console

Playground supports every Messages API parameter and includes templates that demonstrate API features such as code execution and web search. It shows the full SDK request and the API response for each run, to help you understand the API and build with it. For more, see the Claude Help Center or try it at platform.claude.com/playground.

Claude API·Aug 11, 2026

The Compliance API now returns transcripts of Cowork and Claude Code sessions that run on your users'…

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, all with your existing Compliance Access Key and the read:compliance_user_data scope. We've added the anthropic-workspace-id response header to the Claude API.

Claude API·Aug 10, 2026

The introductory pricing for Claude Sonnet 5 is now the standard price: the previously scheduled increase to…

Claude API·Aug 7, 2026

You can now set a budget on a Claude Managed Agents session: a hard cap on the session's spend, priced at…

A session that reaches its budget pauses with the budget_reached stop reason instead of starting new model requests; changing or removing the budget resumes it. Deployments accept the same budget and apply it to each session they start. You can now give a Claude Managed Agents session an advisor: a model at least as capable as the agent's own that the session's primary thread can consult mid-turn for strategic guidance. You can now control where model inference runs for a Claude Managed Agents agent. Claude Managed Agents sessions can now load skills from a GitHub repository.

Claude API·Aug 5, 2026

Inference hooks are now in beta for Claude Enterprise organizations

Point Claude at your organization's AI security server, and each governed prompt across claude.ai, Cowork, and Claude Code is held for the server's allow or deny verdict before inference proceeds. Requests are signed, failure handling is configurable, and every denial is recorded in the compliance Activity Feed. We've retired the Claude Opus 4.1 model (claude-opus-4-1-20250805).

Claude API·Aug 3, 2026

The Compliance API now returns transcripts of Cowork sessions started on claude.ai web or mobile, in beta…

GET /v1/compliance/apps/sessions/remote lists sessions and GET /v1/compliance/apps/sessions/remote/{session_id}/messages returns one session's transcript, using your existing Compliance Access Key with the read:compliance_user_data scope.

Claude API·Aug 1, 2026

Dreams now supports Claude Opus 5

Claude API·Jul 24, 2026

On Claude Opus 5, disabling thinking is allowed only at effort high or below: thinking: {"type": "disabled"}…

Effort is the primary control for steering Claude Opus 5: the model supports the full ladder (low, medium, high, xhigh, max), with max for capability-critical work. Mid-conversation tool changes are now in beta on Claude Fable 5, Claude Mythos 5, Claude Opus 4.8, and Claude Opus 5: add or remove tools between turns of a conversation while preserving the prompt cache. The fallbacks parameter now supports a "default" mode, which applies Anthropic's recommended fallback models by refusal category. We've removed fast mode for Claude Opus 4.7.

Claude API·Jul 22, 2026

You can now set an effort level on a Claude Managed Agents agent's model configuration

Pass effort inside the model object when you create the agent. Webhooks for Claude Managed Agents now cover the environment and memory store lifecycle: four environment.* event types and three memory_store.* event types. When creating a Claude Managed Agents session, you can now seed it with initial events. The version field is now optional when updating a Claude Managed Agents agent. Claude Managed Agents session thread event streams now support event deltas.

Claude API·Jul 17, 2026

The legacy 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. For more, see How do I use the Workbench? in the Claude Help Center. The experimental prompt tools APIs for generating, improving, and templatizing prompts (/v1/experimental/generate_prompt, /v1/experimental/improve_prompt, and /v1/experimental/templatize_prompt) are being retired along with the Workbench on August 17, 2026.

Claude API·Jul 15, 2026

Mid-conversation system messages are available on Claude Fable 5, Claude Mythos 5, and Claude Opus 4.8, on…

No beta header is required. This corrects earlier availability notes.

Claude API·Jul 14, 2026

You can now manage the people in your Claude Enterprise organization with the Admin API, in beta for all…

Group and custom-role requests require the anthropic-beta: ce-user-management-2026-07-13 beta header; member and invite requests take no beta header. An Admin API key with the read:org_audit scope can also call every user-management GET endpoint.

Claude API·Jul 10, 2026

Dreams now supports Claude Fable 5 and Claude Sonnet 5

We've expanded the Access Transparency documentation of cmek_preserve events with a filter example, an example event payload, and two preservation reason codes (policy_violation_investigation, csae_report).

Claude API·Jul 8, 2026

You can now set an expiration when you create an API key or an Admin API key in the Claude Console

Choose a preset, a custom duration, or Never. For keys with a lifetime of at least 7 days, Anthropic emails the creator before expiration. Existing keys are unaffected. The Admin API reports each key's expiration in the expires_at field.

Claude API·Jul 2, 2026

We've added the agent-memory-2026-07-22 beta header, which changes how listing memories behaves: results are…

Page cursors issued without the header aren't valid with it, so restart from the first page when you adopt it. On memory store endpoints, agent-memory-2026-07-22 replaces managed-agents-2026-04-01; sending both returns a 400 error. On July 22, 2026, the managed-agents-2026-04-01 header adopts the same list behavior. The Python (0.116.0), TypeScript (0.110.0), Go (1.56.0), Java (2.48.0), Ruby (1.55.0), PHP (0.36.0), C# (12.35.0), and CLI (1.16.0) SDKs now send agent-memory-2026-07-22 on all memory store calls instead of managed-agents-2026-04-01.

Claude API·Jul 1, 2026

We've restored access to Claude Fable 5 and Claude Mythos 5

Claude API·Jun 30, 2026

Claude Managed Agents session event streams now support event deltas

Opt in with the event_deltas[] query parameter on GET /v1/sessions/{session_id}/events/stream. The event_start and event_delta events preview an agent message's text as it's generated, before the complete agent.message event arrives. Listing sessions for Claude Managed Agents now supports backward pagination. When creating a Claude Managed Agents session, you can now override the agent's configuration for that session. Claude Managed Agents vaults now support an injection_location setting on environment variable credentials (the Environment variable tab). Webhooks for Claude Managed Agents now cover the agent, deployment, and deployment run lifecycle.