What changed in the Anthropic API

Manage resources as code with ant apply

, which creates and updates agents, environments, skills, memory stores, and deployments from files in your repository. Describe each resource in a file, run 
, and approve the plan it prints. Commit the 
 lockfile 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

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

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 
The guides for the Claude Enterprise endpoints of the 
Claude Enterprise Analytics API
 header; send it on every request to these endpoints, as in the rest of the Claude API. See 

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

), the successor to Claude Fable 5 for long-running agentic coding, knowledge work, and research, alongside 
, 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, 
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 
On Claude Fable 5.1 and Claude Mythos 5.1, 
 aren't supported and return a 400 error. 
 are unchanged. To guarantee schema-conformant tool inputs, use 
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 
, or an 

no beta header is required. It's available on Claude Fable 5, Claude Mythos 5, Claude Opus 4.5 and newer, and Claude Sonnet 4.5 and newer; see the code execution tool's

; no beta header is required. It's available on Claude Fable 5, Claude Mythos 5, Claude Opus 4.5 and newer, and Claude Sonnet 4.5 and newer; see the code execution tool's 

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 leg

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, 
 beta headers and return the same shapes as 
client.beta.skills.delete()
 deletes a Skill together with all of its versions, and the beta Messages type 
 (the container Skill reference) is renamed 
. Requests that still send the beta headers keep receiving the beta shapes. See 
 in the Claude Console. They act as you or as a 
, 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 
To move an existing integration off the header, see 
To move an existing integration off the header, see 

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 encrypti

 session endpoints are out of beta for Cowork and Claude Code sessions. See 
Retrieve session transcripts
 local session endpoints now also return transcripts of Claude Science sessions (
) and Claude for Microsoft 365 sessions in Excel, PowerPoint, Word, and Outlook (
), in beta for Claude Enterprise organizations, with your existing Compliance Access Key and the 
 CLI and the Python, TypeScript, C#, Go, Java, PHP, and Ruby SDKs under 
. 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 from 
 for Claude Fable 5, Claude Mythos 5, Claude Opus 5, Claude Sonnet 5, and Claude Opus 4.8. Requests use the same 
 entries as on the Claude API.

The 1-hour cache duration for prompt caching no longer requires a beta header. Learn more in

. The SDK's HTTP layer moves from 
, a maintained, API-compatible fork: build custom 
, and transport objects from 
 helpers are unchanged), and call 
 at startup if you rely on tracing or mocking libraries that patch 
. v1.0 requires Python 3.10 or later and removes long-deprecated surface, including the legacy Text Completions API, the 
 parameters on Messages methods, and the tool runner's client-side 
 now raises an error when no AWS region is configured instead of defaulting to 
 for every change with before-and-after snippets.
 is out of beta on the Claude API as the 
 is out of beta on the Claude API. Requests to the 
 beta header. Requests sent without the header use the current response format: 
) are out of beta on the Claude API. Requests no longer require the 
 (claude.ai) organizations (members, invites, groups, and custom roles) are out of beta. The 
), our most capable widely released model. Claude Opus 4.8 supports a 
. Authenticate workloads to the Claude API with short-lived OIDC tokens from your own identity provider (AWS IAM, Google Cloud, GitHub Actions, Kubernetes, Microsoft Entra ID, Okta, SPIFFE, and more) instead of long-lived static API keys. Configure iss

), 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,

The Claude Platform release notes list changes to the Claude API, the client SDKs, and the Claude Console, newest first.
 is now generally available on the Claude API as the 
computer_toolset_20260801
 toolset: no beta header, batch actions (several actions in one turn), 
 enabled by default, and per-member configuration through 
. Earlier beta versions remain available. Upgrading an existing integration changes the request shape and tool handling; see 
), 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.

) are now generally available on the Claude API. Requests no longer require the

 user-management endpoints for 
 (claude.ai) organizations (members, invites, groups, and custom roles) are now generally available. The 
 header is no longer required on group and custom-role requests; requests that still send it are accepted unchanged. See 
 is now generally available on the Claude API. Requests to the 
 endpoints, and Messages API requests that reference an uploaded file, no longer require the 
 beta header. Requests sent without the header use the GA response format: 
 when you upload a file; file objects report 
. Storage is 1 TB per organization and the rate limit is 500 requests per minute. 
 requests that still send the beta header keep working and return the previous response format.
) are now generally available on the Claude API. Requests no longer require the 
 beta header, including Messages API requests that load Skills through the 
 parameter. Requests that still send the header continue to work unchanged. See 
Using Agent Skills with the API
You can now restrict which sites a Claude Managed Agents agent's 
 on the tool's entry in the 
 entry is identified by its 
, and requests that pass only 
 continue to work; in the typed SDKs, 
 entries become p

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 th

 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 
platform.claude.com/playground

). 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. We reco

 response header to the Claude API. It carries the 
-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
override it for a single session
). All requests to this model on the Claude API will now return an error. We recommend upgrading to 
). All requests to these models on the Claude API will now return an error. We recommend upgrading to 
). 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. We recommend upgrading to 

), the next generation of our Sonnet model family, at introductory pricing of $2 / $10 per MTok (made the standard price on August 10, 2026). Claude Sonnet 5 supports a

Responsible Scaling Policy
Responsible disclosure policy
Terms of service: Commercial
Terms of service: Consumer
 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, all with your existing Compliance Access Key and the 
read:compliance_user_data
The introductory pricing for 
 ($2 / $10 per MTok) is now the standard price: the previously scheduled increase to $3 / $15 per MTok on September 1, 2026 will not occur. See 
 now returns transcripts of Cowork sessions started on claude.ai web or mobile, in beta for Claude Enterprise organizations. 
GET /v1/compliance/apps/sessions/remote
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
), the next generation of our Sonnet model family, at introductory pricing of $2 / $10 per 

on by default, at $5 / $25 USD per MTok, the same pricing as Claude Opus 4.8. It's available on the Claude API,

 on by default, at $5 / $25 USD per MTok, the same pricing as Claude Opus 4.8. It's available on the Claude API, 

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. Configure it

You can now set a budget on a Claude Managed Agents session: a hard cap on the session's spend, priced at public list rates. A session that reaches its budget pauses with the 
 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. See 
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. Configure it as a 
 entry in the agent's multiagent roster, naming the 
Give the session an advisor
You can now control where model inference runs for a Claude Managed Agents agent. Set 
, or override it for a single session. See 
 for the available geos and pricing.
Claude Managed Agents sessions can now 
load skills from a GitHub repository
 directory are discovered automatically at session start and available to the agent for that session.

We've deprecated the Build and Scale plans in favor of a standard feature suite (formerly referred to as Build), along with additional features that are available through sales. Read more in our

 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 
We've retired the Claude Opus 4.1 model (
 on by default, at $5 / $25 per MTok, the same pricing as Claude Opus 4.8. It's available on the Claude API, 
What's new in Claude Opus 5
What's new in Claude Opus 5
 mode, which applies Anthropic's recommended fallback models by refusal category. Server-side fallback is in beta, and the 
 level on a Claude Managed Agents agent's model configuration. Pass 
 events. A non-empty list starts the agent loop in the same call, so you don't need a separate send-events request to start work.
 query parameter as the session-level stream, so you can preview a subagent's text as the model generates it. A connection previews only the thread it's reading. See 
, in beta for all Claude Enterprise organizations: list members and look them up by email address, change a member's role, remove members, send and 

We've retired the Claude Opus 4.1 model

 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 
We've retired the Claude Opus 4.1 model (
. Researchers can request ongoing access through the 

(research preview) now supports Claude Opus 5.

 (research preview) now supports Claude Opus 5. See 
GET /v1/compliance/activities