Skip to content
Back

AnthropicClaude API

We've added capabilities.thinking.types.between_tools to the Models API

AI summary

Written by AI from the official notes. Check them for exact details.

Anthropic added new capabilities to the Models API and made fast mode generally available for Claude Opus 5.5.

  • New capabilities.thinking.types.between_tools added to Models API.
  • Compliance API now shows saved instructions for Claude users.
  • Fast mode for Claude Opus 5.5 is out of research preview.
  • Fast mode available on Claude in Microsoft Foundry for Azure deployments.

Why it matters: Developers and organizations using Claude should review these updates for improved functionality and compliance tracking.

Official notes on platform.claude.com

Full release notes4 changes

  • We've added capabilities.thinking.types.between_tools to the Models API. GET /v1/models and GET /v1/models/{model_id} now report whether each model accepts thinking: {type: "between_tools"}, which turns off up-front thinking. See Using the Models API.
  • The Compliance API now returns the text each organization member saved as Instructions for Claude in claude.ai and as Global instructions in Cowork, in beta for Claude Enterprise organizations. Call GET /v1/compliance/organizations/{org_uuid}/user_preferences with your existing Compliance Access Key and the read:compliance_user_data scope. See List user preferences.
  • 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. Fast mode for Claude Opus 5 and Claude Opus 4.8 remains in research preview. Keep sending the beta header with fast mode requests to those models.
  • Fast mode for Claude Opus 5.5 is now available on Claude in Microsoft Foundry for deployments hosted on Azure.