Release notes
Claude Platform release notes
Updates to the Claude Platform, including the Claude API, client SDKs, and the Claude Console.
The Claude Platform release notes list changes to the Claude API, the client SDKs, and the Claude Console, newest first.
September 10, 2026
- 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_useandagent.mcp_tool_useevents report how each call was evaluated in anevaluationfield alongsideevaluated_permission. See Let the server evaluate each call withauto. - The
antCLI addsant beta:sessions connect, which attaches your terminal to a Claude Managed Agents session. You can follow the session live, send messages, and allow or deny tool calls that are waiting for approval. Pass--webto serve the Claude Console's session viewer locally and open the session there instead. See Connect to a Managed Agents session from your terminal.
September 3, 2026
- Version 1.30.0 of the
antCLI addsant apply, which creates and updates agents, environments, skills, memory stores, and deployments from files in your repository. Describe each resource in a file, runant apply, and approve the plan it prints. Commit theclaude-lock.jsonlockfile it writes so that later runs, on your machine or in CI, update the same resources instead of creating new ones. See Manage resources as code with ant apply. - 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-2026-07-01beta header.
September 1, 2026
- 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_choicetypesanyandtoolaren't supported and return a 400 error.autoandnoneare 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
systemprompt,tools, or an earlier message changed returns a 400 error. With thethinking-binding-controls-2026-08-01beta header, dropped blocks are reported in aninput_transformationsresponse field, andthinking.block_binding.prefix_mismatch_behaviorchooses 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 withoutput_config.effortinsidemessagesto change effort for later turns while preserving the prompt cache. Include themid-conversation-output-config-2026-07-01beta header in your requests. See Per-message effort. - Turn-scoped system messages are in beta (
mid-conversation-system-clear-at-2026-08-21header). Setclear_at: "next_user_message"on a mid-conversationrole: "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.displayaccepts a third value,"updates", in beta (thinking-display-updates-2026-08-18header). Reasoning comes back with an emptythinkingfield, 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 onethinkingblock 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, 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. 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.
- 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-versionheader; send it on every request to these endpoints, as in the rest of the Claude API. See API versions.
August 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 12.44.0,
client.beta.filesandclient.beta.skillsno longer send thefiles-api-2025-04-14andskills-2025-10-02beta headers and return the same shapes asclient.filesandclient.skills. With this change,client.beta.skills.delete()deletes a Skill together with all of its versions, and the beta Messages typeBetaSkill(the container Skill reference) is renamedBetaContainerSkill. Requests that still send the beta headers keep receiving the beta shapes. See Migrate fromfiles-api-2025-04-14and Migrate fromskills-2025-10-02.
- You can now create personal keys and service account keys in the Claude Console. They act as you or as a service account, with the same permissions, and stop working when the linked account is removed from an organization. This lets organization admins more easily track usage for each account, and ensure key usage is legitimate. These API keys can be scoped to a specific workspace or work on admin endpoints and across any workspace the account has access to. Workspace API keys remain supported as a legacy option. See API keys for more information.
August 26, 2026
- The Compliance API session endpoints are out of beta for Cowork and Claude Code sessions. See Retrieve session transcripts.
- The Compliance API local session endpoints now also return transcripts of Claude Science sessions (
product_surfacevalueclaude_science) and Claude for Microsoft 365 sessions in Excel, PowerPoint, Word, and Outlook (product_surfacevalues beginning withoffice_agents), in beta for Claude Enterprise organizations, with your existing Compliance Access Key and theread:compliance_user_datascope. See Sessions on users' machines.
- The Admin API is now available in the
antCLI and the Python, TypeScript, C#, Go, Java, PHP, and Ruby SDKs underclient.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. Usage and cost reports and the Claude Enterprise user-management and analytics endpoints remain curl-only. The CLI and SDKs read an Admin API key fromANTHROPIC_API_KEYor anorg:adminOAuth token fromANTHROPIC_AUTH_TOKEN.
August 20, 2026
- We've released v1.0 of the Python SDK. The SDK's HTTP layer moves from
httpxto httpx2, a maintained, API-compatible fork: build customhttp_client,Timeout, and transport objects fromhttpx2(theDefaultHttpxClienthelpers are unchanged), and callhttpx2.alias_httpx()at startup if you rely on tracing or mocking libraries that patchhttpx. v1.0 requires Python 3.10 or later and removes long-deprecated surface, including the legacy Text Completions API, thetemperature,top_p, andtop_kparameters on Messages methods, and the tool runner's client-sidecompaction_control. On the async client,.with_raw_responseresults now needawait response.parse(), andAnthropicBedrocknow raises an error when no AWS region is configured instead of defaulting tous-east-1. See the v1 migration guide for every change with before-and-after snippets. - The computer use and browser use toolsets (
computer_toolset_20260801andbrowser_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. Requests use the sametoolsentries as on the Claude API.
August 19, 2026
- The computer use tool is out of beta on the Claude API as the
computer_toolset_20260801toolset: no beta header, batch actions (several actions in one turn),zoomenabled by default, and per-member configuration throughconfigs. Earlier beta versions remain available. Upgrading an existing integration changes the request shape and tool handling; see Migrate fromcomputer_20251124. - We've launched the browser use tool (
browser_toolset_20260801), a client toolset for driving a browser that your application hosts. It works inside a browser viewport rather than a whole desktop, reading the page itself (its accessibility tree, elements, forms, and tabs) and adding element references, form input, tab management, download reporting, and opt-in file upload on top of screenshot-and-click control. - 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. Requests to the
/v1/filesendpoints, and Messages API requests that reference an uploaded file, no longer require thefiles-api-2025-04-14beta header. Requests sent without the header use the current response format: file expiration (setexpires_in_secondswhen you upload a file; file objects reportexpires_at), andpageandnext_pagepagination plus anids[]filter when you list files./v1/filesrequests that still send the beta header keep working and return the previous response format. To move an existing integration off the header, see Migrate fromfiles-api-2025-04-14. - Agent Skills and the Skills API (
/v1/skills) are out of beta on the Claude API. Requests no longer require theskills-2025-10-02beta header, including Messages API requests that load Skills through thecontainerparameter. Requests that still send the header continue to work unchanged. See Using Agent Skills with the API. To move an existing integration off the header, see Migrate fromskills-2025-10-02. - The Admin API user-management endpoints for Claude Enterprise (claude.ai) organizations (members, invites, groups, and custom roles) are out of beta. The
anthropic-beta: ce-user-management-2026-07-13header is no longer required on group and custom-role requests; requests that still send it are accepted unchanged. See User management. - You can now restrict which sites a Claude Managed Agents agent's
web_searchandweb_fetchtools can reach. Setallowed_domainsorblocked_domainson the tool's entry in theagent_toolset_20260401configsarray;web_fetchalso acceptsmax_content_tokensandweb_searchacceptsuser_location. Eachconfigsentry is identified by itsnameand typed by an optionaltype, and requests that pass onlyname,enabled, andpermission_policycontinue to work; in the typed SDKs,configsentries become per-tool types. See Restrict web search and web fetch domains. - Claude Managed Agents sessions that run in a self-hosted sandbox can now attach memory stores. The Python, TypeScript, and Go SDK workers download each attached store into the sandbox at its
mount_pathand sync the agent's changes back to the store. See Use 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. See Console observability.