更新日: 2026-06-06

​

Reasoning Models

• If you only want stronger reasoning and only need the final answer, use Chat Completions with reasoning_effort
• If you need a stable, inspectable reasoning output, prefer the Responses API and see GPT-5 Thinking Mode

​

Verified combinations

​

Chat Completions: reasoning_effort

curl https://api.crazyrouter.com/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "gpt-5.5",
    "messages": [
      {
        "role": "user",
        "content": "Which is larger, 9.11 or 9.9? Explain briefly."
      }
    ],
    "reasoning_effort": "high",
    "max_tokens": 120
  }'

​

Current response behavior

• the request succeeded
• the final answer was returned in message.content
• message.reasoning_content did not reliably contain usable content

​

When you need inspectable reasoning output

curl https://api.crazyrouter.com/v1/responses \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "gpt-5.5",
    "input": "Which is larger, 9.11 or 9.9? Explain briefly.",
    "reasoning": {
      "effort": "high",
      "summary": "detailed"
    }
  }'

["reasoning", "message"]

• GPT-5 Thinking Mode
• AI Thinking Fields

​

Current recommendation

• For new builds that need to log or display reasoning summaries, start with the Responses API
• For existing Chat Completions integrations that only care about the final answer, reasoning_effort is still a valid path
• Do not assume all OpenAI-compatible reasoning models will reliably expose reasoning_content