Anthropic API Release Notes

We’ve unified our developer offerings under the Claude brand. You should see updated naming and URLs across our platform and documentation, but our developer interfaces will remain the same. Here are some notable changes:

• Anthropic Console (console.anthropic.com) → Claude Console (platform.claude.com). The console will be available at both URLs until December 16, 2025. After that date, console.anthropic.com will automatically redirect to platform.claude.com.
• Anthropic Docs (docs.claude.com) → Claude Docs (docs.claude.com)
• Anthropic Help Center (support.claude.com) → Claude Help Center (support.claude.com)
• API endpoints, headers, environment variables, and SDKs remain the same. Your existing integrations will continue working without any changes.

New features and improvements

• We launched a beta version of the PHP SDK.
• The 1m token context window is now available on Google Cloud’s Vertex AI. For more information, see Claude on Vertex AI.
• The 1-hour cache duration for prompt caching is now generally available. You can now use the extended cache TTL without a beta header. Learn more in our prompt caching documentation.
• Search result content blocks are now generally available on the Anthropic API and Google Cloud’s Vertex AI. This feature enables natural citations for RAG applications with proper source attribution. The beta header search-results-2025-06-09 is no longer required. Learn more in our search results documentation.
• We’ve launched Claude Opus 4.1, an incremental update to Claude Opus 4 with enhanced capabilities and performance improvements. Learn more in our Models & Pricing documentation.
• We’ve released text_editor_20250728, an updated text editor tool that fixes some issues from the previous versions and adds an optional max_characters parameter that allows you to control the truncation length when viewing large files.
• We’ve increased rate limits for Claude Opus 4 on the Anthropic API to give you more capacity to build and scale with Claude. For customers with usage tier 1-4 rate limits, these changes apply immediately to your account - no action needed.
• We’ve increased rate limits for Claude Sonnet 4 on the Anthropic API to give you more capacity to build and scale with Claude. For customers with usage tier 1-4 rate limits, these changes apply immediately to your account - no action needed.
• Console users with the Developer role can now access the Cost page. Previously, the Developer role allowed access to the Usage page, but not the Cost page.

API changes and deprecations

• Request IDs are now included directly in error response bodies alongside the existing request-id header. Learn more in our error documentation.
• We’ve added a new endpoint to the Admin API for retrieving organization information. For details, see the Organization Info Admin API reference.
• We’ve released the Usage & Cost API, allowing administrators to programmatically monitor their organization’s usage and cost data.
• We announced the deprecation of the Claude Sonnet 3.5 models (claude-3-5-sonnet-20240620 and claude-3-5-sonnet-20241022). These models will be retired on October 22, 2025. We recommend migrating to Claude Sonnet 4 (claude-sonnet-4-20250514) for improved performance and capabilities. Read more in the Model deprecations documentation.
• The 1M token context window is now available on Claude Sonnet 4 on the Anthropic API and Amazon Bedrock. (Note: this is a follow-up feature under new access)
• The 1M token context window is now available on Google Cloud’s Vertex AI. For more information, see Claude on Vertex AI.
• We’ve announced the deprecation of the Claude Opus 3 model. Read more in our documentation.
• We’ve retired the Claude 2.0, Claude 2.1, and Claude Sonnet 3 models. All requests to these models will now return an error. Read more in our documentation.

Stability, reliability, and other improvements

• Some customers might encounter 429 (rate_limit_error) errors following a sharp increase in API usage. Previously, 529 (overloaded_error) errors would occur in similar scenarios.
• Search result content blocks in beta have launched, enabling natural citations for RAG applications. Tools can now return search results with proper source attribution, and Claude will automatically cite these sources in its responses — matching the citation quality of web search. This eliminates the need for document workarounds in custom knowledge base applications. Learn more in our search results documentation. To enable this feature, use the beta header search-results-2025-06-09.
• We’ve launched beta support for a 1M token context window in Claude Sonnet 4 on the Anthropic API and Amazon Bedrock.
• The 1m token context window is now available on Google Cloud’s Vertex AI. For more information, see Claude on Vertex AI.
• The 1m token context window is now available on Claude Sonnet 4 on the Anthropic API and Amazon Bedrock.