Skip to main content
Claude 3.7 Sonnet Thinking is the extended thinking variant of Claude 3.7 Sonnet, available through AnyFast via an OpenAI-compatible interface. With extended thinking enabled by default, the model performs step-by-step internal reasoning before generating a response, delivering significantly improved accuracy on complex tasks.

Key capabilities

  • OpenAI-compatible — Works as a drop-in replacement with the OpenAI SDK
  • Extended thinking — Step-by-step internal reasoning enabled by default
  • Deep reasoning — Excels at math, logic, and multi-step problem solving
  • Long context — Handles large documents and multi-turn conversations
  • Streaming — Supports real-time token streaming via SSE

Quick example

Thinking sampling compatibility: For reliable requests, omit temperature and top_k. Anthropic accepts the unchanged default temperature: 1 and top_p values from 0.95 to 1. A non-default temperature, any top_k, or a top_p below 0.95 returns a 400 error while Thinking is enabled. See Anthropic’s Thinking limits and API usage primer.

Parameters

API Reference

View the interactive API playground for Claude 3.7 Sonnet Thinking.