GPT-5触发深度思考示例

{
  "model": "gpt-5",
  "reasoning": {
    "effort": "high",
    "summary": "detailed"
  },
  "input": [
    {
      "role": "user",
      "content": "你好"
    }
  ]
}

"reasoning": { "effort": "high", "summary": "detailed" }

{
  "id": "resp_6896d2b375dc81a28350f5fadd358f42024e3675a933bcbc",
  "object": "response",
  "created_at": 1754714803,
  "status": "completed",
  "background": false,
  "error": null,
  "incomplete_details": null,
  "instructions": null,
  "max_output_tokens": null,
  "max_tool_calls": null,
  "model": "gpt-5-2025-08-07",
  "output": [
    {
      "id": "rs_6896d2b3d47081a2a249ad0cdee872c2024e3675a933bcbc",
      "type": "reasoning",
      "summary": [
        {
          "type": "summary_text",
          "text": "Responding in Chinese\n\nI want to respond with a Chinese greeting, like \"你好\" (hello), and say something like \"你好，有什么可以帮你?\" to keep it polite and simple. I should avoid using heavy formatting and just focus on being concise. It's good to check how I can help, but I want to keep my response brief and friendly. Let's make sure the greeting feels warm and inviting!"
        }
      ]
    },
    {
      "id": "msg_6896d2b9bcd481a28bc8f672c534b4e3024e3675a933bcbc",
      "type": "message",
      "status": "completed",
      "content": [
        {
          "type": "output_text",
          "annotations": [],
          "logprobs": [],
          "text": "你好！我是ChatGPT，有什么可以帮你的吗？"
        }
      ],
      "role": "assistant"
    }
  ],
  "parallel_tool_calls": true,
  "previous_response_id": null,
  "reasoning": {
    "effort": "high",
    "summary": "detailed"
  },
  "service_tier": "default",
  "store": true,
  "temperature": 1.0,
  "text": {
    "format": {
      "type": "text"
    },
    "verbosity": "medium"
  },
  "tool_choice": "auto",
  "tools": [],
  "top_logprobs": 0,
  "top_p": 1.0,
  "truncation": "disabled",
  "usage": {
    "input_tokens": 7,
    "input_tokens_details": {
      "cached_tokens": 0
    },
    "output_tokens": 82,
    "output_tokens_details": {
      "reasoning_tokens": 64
    },
    "total_tokens": 89
  },
  "user": null,
  "metadata": {}
}