Claude Console IP allowlisting is in beta
Anthropic introduced IP allowlisting for organizations in the Claude Console. Administrators can restrict API key usage to specific IPv4 and IPv6 addresses or CIDR ranges.
136 releases · 4 this month
Anthropic introduced IP allowlisting for organizations in the Claude Console. Administrators can restrict API key usage to specific IPv4 and IPv6 addresses or CIDR ranges.
Text generated by Claude Mythos 5, Claude Opus 4.7, and Claude Sonnet 4.6 carries Anthropic’s text watermark on the platforms listed in How Claude marks AI-generated content. On Claude Sonnet 4.6, text generated for a request that sets temperature, top_p, or top_k to a non-default value might not carry it. See Text watermark.
Long conversations and agent loops on the Messages API can now send smaller requests and get a lower time to first token with message threads, in beta with the message-threads-2026-08-12 beta header. The API keeps the conversation on the server, so each later request sends only the new messages.
Fast mode for Claude Opus 4.8 is deprecated and will be removed on November 30, 2026. Users should migrate to Claude Opus 5.5 to continue using fast mode.
Anthropic designated the Usage and Cost API and related usage and cost report endpoints in the Claude Enterprise Analytics API as legacy while maintaining support.
Anthropic increased the maximum request payload size for the Messages API and Token Counting API from 32 MB to 128 MB.
The Claude Tag API is now in beta for Claude Enterprise organizations. It allows programmatic management of Claude Tag settings on Slack channels and workspaces using Admin API keys.
Anthropic has launched Claude Models on Google Cloud, allowing users to access the Claude API through their Google Cloud project with IAM-based access control and marketplace billing.
Anthropic released breaking changes for its client SDKs and ant CLI, relicensing them from the MIT License to Apache 2.0.
The Claude Tag API is available in beta for Claude Enterprise organizations with the experimental-claude-tag-2026-10-21 beta header. Its /v1/organizations/claude_tag/ endpoints read and change Claude Tag settings on Slack channels and Slack workspaces, show which settings apply in a channel and where each comes from, and attach Access bundles.
Fast mode is out of research preview for Claude Opus 5.5, and you no longer need to request access. Requests to Claude Opus 5.5 no longer require the fast-mode-2026-02-01 beta header, and requests that still send it keep working. Claude Opus 5.5 now has a default fast mode rate limit in the Start, Build, and Scale usage tiers.
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. To get spans from the API, add an OpenTelemetry destination in the Claude Console.
You can now let a Claude Managed Agents agent use dynamic workflows, in beta with the managed-agents-2026-04-01 beta header. For work with many pieces, such as reviewing hundreds of documents, the agent can write a workflow. A workflow is a program that runs many agents in phases and combines their results.
The Compliance API can now download Claude Docs documents as Word files, in beta. See Retrieve files and artifacts.
We've lowered the price of prompt cache reads on Claude Sonnet 5.5 from $0.20 USD to $0.10 USD per million tokens: 0.05x the base input price instead of 0.1x. Cache writes and all other prices are unchanged. See Prompt caching pricing.
We've added capabilities.server_tools to the Models API. GET /v1/models and GET /v1/models/{model_id} now report whether each model accepts the web search and code execution tools. To check whether a model accepts the code execution tool, read capabilities.server_tools.code_execution.
We've added capabilities.thinking.types.disabled to the Models API. GET /v1/models and GET /v1/models/{model_id} now report whether each model accepts thinking: {type: "disabled"}, which turns thinking off. See Using the Models API.
In Python SDK 1.10.0, TypeScript SDK 0.130.0, C# SDK 12.52.0, Go SDK 1.77.0, Java SDK 2.67.0, PHP SDK 0.53.0, Ruby SDK 1.75.0, and version 1.37.0 of the ant CLI, the Admin API methods for organization info, members, invites, workspaces, API keys, rate limits, service accounts, workload identity federation, customer-managed encryption keys, and compliance...
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.
Developers can now submit plugins to the Claude directory via a new portal. The portal includes features to track submissions through review and view usage analytics.
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.
Cache diagnostics is out of beta on the Claude API and no longer requires the cache-diagnosis-2026-04-07 beta header. Include the diagnostics object on a Messages request to opt in; requests that still send the header work as before.
Claude Opus 5.5 is the first model in the Claude 5.5 family. It performs at the level of Claude Fable 5.1 while costing 40% less than Opus 5.
For cache diagnostics, a response to a request that sends the cache-diagnosis-2026-04-07 beta header now always includes the diagnostics field. The field is null when the request did not include the diagnostics object. Previously the field was omitted in that case.
Under the thinking-binding-controls-2026-08-01 beta header, input_transformations can report thinking_mismatch_allowed for thinking blocks that failed an unenforced prefix check. Logging these entries helps find conversation history edits in production traffic.
ant beta:sessions connect attaches a terminal to a Claude Managed Agents session so you can follow it live, send messages and approve or deny pending tool calls. --web serves the Console session viewer locally.
Per-message effort changes are now available in beta on Google Cloud for Claude Fable 5.1, Claude Mythos 5.1 and Claude Opus 5, using the same mid-conversation-output-config-2026-07-01 beta header.
Anthropic launched Claude Fable 5.1 and Claude Mythos 5.1, designed for coding and knowledge work.
Personal and service account keys act as a user or service account with the same permissions and stop working when that account leaves the organization. Admins can track usage per account, and keys can be scoped to one workspace or used on admin endpoints.
The ant CLI and the Python, TypeScript, C#, Go, Java, PHP and Ruby SDKs now cover Admin API resources including members, workspaces, API keys, rate limits, service accounts and encryption keys. Usage and cost reports remain curl-only.
The Python SDK v1.0 switches its HTTP layer to httpx2, an API-compatible httpx fork, requires Python 3.10 or later and removes long-deprecated surface including the legacy Text Completions API. Tracing or mocking libraries that patch httpx need httpx2.alias_httpx().
Agent Skills and /v1/skills no longer require the skills-2025-10-02 beta header, including Messages requests that load Skills via the container parameter. Requests still sending the header continue to work unchanged.
Playground supports every Messages API parameter, includes templates for features such as code execution and web search, and shows the full SDK request and API response for each run.
Responses now carry the wrkspc_-prefixed ID of the workspace the API key or access token resolved to, including the Default Workspace, making it easier to attribute traffic to workspaces.
The introductory Claude Sonnet 5 price is now standard, and the scheduled increase to $3 / $15 per MTok on September 1, 2026 will not happen.
A session budget caps spend at public list rates; when reached, the session pauses with the budget_reached stop reason instead of starting new model requests. Deployments can apply the same budget to every session they start.
All requests to claude-opus-4-1-20250805 now return an error. Anthropic recommends upgrading to Claude Opus 5; researchers can request continued access through the External Researcher Access Program.
New /v1/compliance/apps/sessions/remote endpoints list Cowork sessions started on claude.ai web or mobile and return their transcripts for Claude Enterprise organizations.
Dreams, in research preview, now supports Claude Opus 5.
Requests to claude-opus-4-7 with speed fast now return an error rather than falling back to standard speed. The model stays available at standard speed; migrate to Opus 5 or Opus 4.8 to keep fast mode.
Supply version for optimistic concurrency, where a mismatch returns 409, or omit it to apply the update unconditionally.
The generate_prompt, improve_prompt and templatize_prompt experimental endpoints are being retired along with the Workbench on August 17, 2026, after which requests will return an error.
Mid-conversation system messages work on Claude Fable 5, Mythos 5 and Opus 4.8 on the Claude API, Amazon Bedrock and Google Cloud with no beta header required, correcting earlier availability notes.
Claude Enterprise organizations can list and look up members, change roles, remove members, manage invites and groups, and read custom roles through the Admin API. Group and custom-role requests need the ce-user-management-2026-07-13 beta header.
Dreams, in research preview, now supports Claude Fable 5 and Claude Sonnet 5.
Choose a preset, custom duration or Never when creating a key, and keys with a lifetime of at least 7 days trigger an email before expiry. The Admin API reports expiration in expires_at; existing keys are unaffected.
With the new header, listing memories returns a stable server-defined order, depth accepts only 0 or 1, and path_prefix must end with / and match whole segments. Page cursors issued without the header are not valid with it.
Anthropic has restored access to Claude Fable 5 and Claude Mythos 5 and published a statement with more information.
Claude Sonnet 5 supports a 1M token context, 128k max output and the same tools as Sonnet 4.6 except Priority Tier. Migrating teams should note that adaptive thinking is on by default and manual extended thinking changes.
Requests to claude-opus-4-6 with speed fast now run at standard speed and standard rates without erroring, and usage.speed reports the speed used. Migrate to Claude Opus 4.8 to keep fast mode.
Claude Sonnet and Haiku rate limits now match Claude Opus at every tier, and tiers are consolidated into Start, Build and Scale. No organization gets lower limits and no action is required.
After July 24, 2026, requests to claude-opus-4-7 with speed fast will return an error. Anthropic recommends migrating to fast mode on Claude Opus 4.8.
Claude models, the Claude API, SDKs and the Console.
Other Anthropic products: Claude Agent SDK, Claude apps, Claude Code
| Release-notes page | Site | Feed |
|---|---|---|
| Claude Platform release notes platform.claude.com | platform.claude.com | None |
| Claude Agent SDK (Python) releases github.com | github.com | RSS |
| Claude Agent SDK (TS) releases github.com | github.com | RSS |
| Python SDK releases github.com | github.com | RSS |
| System prompts release notes platform.claude.com | platform.claude.com | None |
| TypeScript SDK releases github.com | github.com | RSS |