Skip to main content
Claude Opus 4 Thinking is the extended thinking variant of Claude Opus 4, available through AnyFast via an OpenAI-compatible interface. With step-by-step internal reasoning enabled by default, it delivers exceptional accuracy on complex tasks including advanced mathematics, scientific research, and large-scale coding projects.

​
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 advanced math, science, and complex problem solving
  • Advanced coding — Large-scale code generation, debugging, and architecture
  • Long context — Handles large documents and multi-turn conversations
  • Streaming — Supports real-time token streaming via SSE

​
Quick example

curl https://www.anyfast.ai/v1/messages \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-opus-4-20250514-thinking",
    "messages": [
      { "role": "user", "content": "Solve step by step: If a train travels 120 km in 2 hours, then slows down and travels 80 km in 3 hours, what is the average speed for the entire trip?" }
    ]
  }'

​
Parameters

ParameterTypeRequiredDescription
modelstringYesMust be claude-opus-4-20250514-thinking
messagesarrayYesList of { role, content } objects
max_tokensintegerNoMaximum tokens to generate
temperaturefloatNo0–2. Controls randomness. Default: 1
streambooleanNoEnable SSE streaming. Default: false
top_pfloatNoNucleus sampling threshold. Default: 1
stopstring / arrayNoSequences that stop generation

API Reference

View the interactive API playground for Claude Opus 4 Thinking.