> ## Documentation Index
> Fetch the complete documentation index at: https://docs.crazyrouter.com/llms.txt
> Use this file to discover all available pages before exploring further.

# GPT-5 思考模式

> 基于生产环境复核，通过 Responses API 使用 GPT-5.4 的 reasoning 模式

> 更新日期：2026-06-06

# GPT-5 思考模式

本文页只写入 `2026-03-22` 已在 Crazyrouter 生产环境复核过的 GPT reasoning 行为。

当前主示例使用：

* `gpt-5.5`
* `POST /v1/responses`

<Note>
  Claude 当前不支持 `POST /v1/responses`。如果你在接 Claude，请使用 `POST /v1/messages` 或 `POST /v1/chat/completions`，不要套用本页的 Responses 请求形态。
</Note>

```
POST /v1/responses
```

***

## 基本用法

<CodeGroup>
  ```bash cURL theme={null}
  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"
      }
    }'
  ```

  ```python Python theme={null}
  from openai import OpenAI

  client = OpenAI(
      api_key="YOUR_API_KEY",
      base_url="https://api.crazyrouter.com/v1"
  )

  response = client.responses.create(
      model="gpt-5.5",
      input="Which is larger, 9.11 or 9.9? Explain briefly.",
      reasoning={
          "effort": "high",
          "summary": "detailed"
      }
  )

  print(response.output_text)
  ```

  ```javascript Node.js theme={null}
  import OpenAI from "openai";

  const client = new OpenAI({
    apiKey: "YOUR_API_KEY",
    baseURL: "https://api.crazyrouter.com/v1",
  });

  const response = await client.responses.create({
    model: "gpt-5.5",
    input: "Which is larger, 9.11 or 9.9? Explain briefly.",
    reasoning: {
      effort: "high",
      summary: "detailed",
    },
  });

  console.log(response.output_text);
  ```
</CodeGroup>

***

## 生产验证到的响应结构

当前生产返回的关键 `output.type`：

```json theme={null}
["reasoning", "message"]
```

其中 `reasoning` item 的典型结构为：

```json theme={null}
{
  "id": "rs_xxx",
  "type": "reasoning",
  "encrypted_content": "...",
  "summary": [
    {
      "type": "summary_text",
      "text": "..."
    }
  ]
}
```

`message` item 中则包含最终输出文本：

```json theme={null}
{
  "type": "message",
  "content": [
    {
      "type": "output_text",
      "text": "..."
    }
  ]
}
```

***

## `reasoning` 参数

| 字段        | 类型     | 说明                                   |
| --------- | ------ | ------------------------------------ |
| `effort`  | string | 推理力度，当前实测可用值包括 `low`、`medium`、`high` |
| `summary` | string | 思考摘要粒度，当前实测 `concise`、`detailed` 可用  |

### 一个实用判断

* 只要更强推理，不关心摘要：只传 `effort`
* 需要拿到可展示的 reasoning 摘要：同时传 `summary`

在当前复核中：

* 只传 `effort` 时，`reasoning` item 存在，但 `summary` 可能为空数组
* 传 `summary: "detailed"` 时，可以稳定拿到 `summary_text`

***

## 提取思考摘要

```python Python theme={null}
response = client.responses.create(
    model="gpt-5.5",
    input="Design a high-concurrency message queue architecture.",
    reasoning={
        "effort": "high",
        "summary": "detailed"
    }
)

for item in response.output:
    if item.type == "reasoning":
        for part in item.summary:
            if part.type == "summary_text":
                print("思考摘要:", part.text)
    elif item.type == "message":
        for content in item.content:
            if content.type == "output_text":
                print("最终回答:", content.text)
```

***

## 流式思考

当前生产环境已复核到以下 Responses SSE 事件名：

* `response.reasoning_summary_part.added`
* `response.reasoning_summary_text.delta`
* `response.reasoning_summary_text.done`
* `response.output_text.delta`
* `response.output_text.done`
* `response.completed`

示例：

```python Python theme={null}
stream = client.responses.create(
    model="gpt-5.5",
    input="Explain briefly why 9.9 is larger than 9.11.",
    reasoning={
        "effort": "high",
        "summary": "detailed"
    },
    stream=True
)

for event in stream:
    if event.type == "response.reasoning_summary_text.delta":
        print(f"[思考摘要] {event.delta}", end="")
    elif event.type == "response.output_text.delta":
        print(event.delta, end="")
```

***

## 当前建议

* 需要可见 reasoning 字段时，优先选 `gpt-5.5` + Responses API
* 不要把 `gpt-5.5` Chat Completions 的 `reasoning_content` 当成当前主依赖字段
* 如果你只关心最终答案，可在 Chat Completions 继续使用 `reasoning_effort`

<Warning>
  reasoning 模式会提高延迟与 Token 消耗。`effort` 越高，成本通常越高。
</Warning>