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

# 创建 Responses 请求 (OpenAI)

> OpenAI 新一代对话接口，专为推理模型和高级功能设计

## 简介

Responses API 是 OpenAI 推出的新一代对话接口，专为推理模型（o 系列、GPT-5 系列）和高级功能设计。相比传统的 Chat Completions API，Responses API 提供了更精细的推理控制、内置工具支持和多模态输入能力。

> [!NOTE]
>
> `gpt-6.1-sol`：函数调用和 `reasoning.effort="max"` 使用 Responses。Chat Completions 支持不带工具的请求，`reasoning_effort` 可用值为 `low`、`medium`、`high`、`xhigh`。两种接口均不支持 `none` 或 `minimal`，不要传入 `temperature`、`top_p` 或 logprobs 相关字段。详见 [GPT 6.1 Sol](/docs/zh-Hans/model-api/openai/gpt-6.1-sol)。

## 适用场景

* 推理密集型任务：使用 o1、o3-mini、o4-mini、GPT-5 等推理模型
* 需要联网搜索：内置 Web Search Preview 工具
* 高级工具调用：支持 Function Call 和 Custom Tool Call
* 多轮对话延续：通过 `previous_response_id` 实现对话历史管理

## 认证

Bearer Token，如 `Bearer sk-xxxxxxxxxx`

## 请求参数

**model** `string` *required*

模型标识，如 `gpt-5.5`、`o4-mini`、`o3-mini`

**input** `string | array` *required*

输入文本或 Responses 输入条目数组。

**max\_output\_tokens** `integer`

最大输出 token 数

**stream** `boolean`

是否启用流式输出

**reasoning** `object`

推理配置，如 `{"effort": "high", "summary": "detailed"}`

**tools** `array`

工具列表，支持 Web Search 和函数调用

**previous\_response\_id** `string`

上一条响应的 ID，用于延续对话

## 基础示例

**简单对话（非流式）**

```bash theme={null}
curl -X POST "https://api.mixroute.ai/v1/responses" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-xxxxxxxxxx" \
  -d '{
    "model": "gpt-5.5",
    "max_output_tokens": 2048,
    "input": [
      {"role": "user", "content": "请用中文简要介绍人工智能"}
    ]
  }'
```

**简单对话（流式）**

```bash theme={null}
curl -X POST "https://api.mixroute.ai/v1/responses" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-xxxxxxxxxx" \
  -d '{
    "model": "gpt-5.5",
    "stream": true,
    "max_output_tokens": 2048,
    "input": [
      {"role": "user", "content": "请用中文简要介绍人工智能"}
    ]
  }'
```

**Python SDK**

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

client = OpenAI(
    api_key="sk-xxxxxxxxxx",
    base_url="https://api.mixroute.ai/v1"
)

# 非流式调用
response = client.responses.create(
    model="gpt-5.5",
    max_output_tokens=2048,
    input=[
        {"role": "user", "content": "请用中文简要介绍人工智能"}
    ]
)

print(response.output_text)

# 流式调用
stream = client.responses.create(
    model="gpt-5.5",
    stream=True,
    max_output_tokens=2048,
    input=[
        {"role": "user", "content": "请用中文简要介绍人工智能"}
    ]
)

for event in stream:
    if event.type == "response.output_text.delta":
        print(event.delta, end="", flush=True)
```

## 高级功能

### 联网搜索（Web Search）

**基础示例**

```bash theme={null}
curl -X POST "https://api.mixroute.ai/v1/responses" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-xxxxxxxxxx" \
  -d '{
    "model": "gpt-5.5",
    "stream": true,
    "input": [
      {"role": "user", "content": "今天的新闻头条是什么？"}
    ],
    "tools": [
      {
        "type": "web_search_preview"
      }
    ]
  }'
```

**高级配置**

```bash theme={null}
curl -X POST "https://api.mixroute.ai/v1/responses" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-xxxxxxxxxx" \
  -d '{
    "model": "gpt-5.5",
    "stream": true,
    "input": [
      {"role": "user", "content": "搜索最新的人工智能研究进展"}
    ],
    "tools": [
      {
        "type": "web_search_preview",
        "search_context_size": "high",
        "user_location": {
          "type": "approximate",
          "country": "CN"
        }
      }
    ]
  }'
```

**配置说明：**

* `search_context_size`: 搜索上下文大小，可选 `low`、`medium`、`high`
* `user_location`: 用户位置，影响搜索结果的地区相关性

### 推理控制（Reasoning）

**自动推理摘要**

```bash theme={null}
curl -X POST "https://api.mixroute.ai/v1/responses" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-xxxxxxxxxx" \
  -d '{
    "model": "o4-mini",
    "stream": true,
    "reasoning": {
      "effort": "medium",
      "summary": "auto"
    },
    "max_output_tokens": 4096,
    "input": [
      {"role": "user", "content": "计算 1+2+3+...+100 的和"}
    ]
  }'
```

**说明：** `summary: "auto"` 会自动生成推理摘要，适合快速获取结果。

**详细推理过程**

```bash theme={null}
curl -X POST "https://api.mixroute.ai/v1/responses" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-xxxxxxxxxx" \
  -d '{
    "model": "o4-mini",
    "stream": true,
    "reasoning": {
      "effort": "high",
      "summary": "detailed"
    },
    "max_output_tokens": 8192,
    "input": [
      {"role": "user", "content": "证明根号2是无理数"}
    ]
  }'
```

**推理配置参数：**

* `effort`: 推理强度，可选 `low`、`medium`、`high`
* `summary`: 摘要模式，可选 `auto`、`concise`、`detailed`

### 自定义函数调用

Responses 的函数定义将 name、description、parameters、strict 与 type 放在同一层，不嵌套 function 对象。按类型处理 output 条目；执行函数后通过 function\_call\_output 和对应 call\_id 回传结果。无状态请求需在后续 input 中保留完整 output 数组，包括可能出现的 reasoning 条目；同时将 tool\_choice 恢复为 "auto"，让模型继续生成回答。

```bash theme={null}
curl --request POST "https://api.mixroute.ai/v1/responses" \
  --header "Authorization: Bearer $MIXROUTE_API_KEY" \
  --header "Content-Type: application/json" \
  --data '{
  "model": "gpt-6.1-sol",
  "input": "Call lookup_status for service demo.",
  "reasoning": {
    "effort": "low"
  },
  "tools": [
    {
      "type": "function",
      "name": "lookup_status",
      "description": "Return the status of a named service.",
      "parameters": {
        "type": "object",
        "properties": {
          "service": {
            "type": "string"
          }
        },
        "required": [
          "service"
        ],
        "additionalProperties": false
      },
      "strict": true
    }
  ],
  "tool_choice": {
    "type": "function",
    "name": "lookup_status"
  },
  "include": [
    "reasoning.encrypted_content"
  ],
  "max_output_tokens": 1024,
  "store": false
}'
```

### 多模态输入

**图片输入**

```bash theme={null}
curl -X POST "https://api.mixroute.ai/v1/responses" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-xxxxxxxxxx" \
  -d '{
    "model": "gpt-5.5",
    "input": [
      {
        "role": "user",
        "content": [
          {
            "type": "input_text",
            "text": "这张图片里有什么？"
          },
          {
            "type": "input_image",
            "image_url": "https://api.mixroute.ai/demo/sample-image.jpg"
          }
        ]
      }
    ]
  }'
```

**文件输入**

```bash theme={null}
curl -X POST "https://api.mixroute.ai/v1/responses" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-xxxxxxxxxx" \
  -d '{
    "model": "gpt-5.5",
    "input": [
      {
        "role": "user",
        "content": [
          {
            "type": "input_text",
            "text": "请总结这份文档的主要内容"
          },
          {
            "type": "input_file",
            "file_id": "file-xxxxxxxx"
          }
        ]
      }
    ]
  }'
```

> [!NOTE]
>
> 使用文件输入前，需要先通过 Files API 上传文件获取 `file_id`。

### 对话延续

通过 `previous_response_id` 实现多轮对话的上下文延续：

```bash theme={null}
# 第一轮对话
curl -X POST "https://api.mixroute.ai/v1/responses" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-xxxxxxxxxx" \
  -d '{
    "model": "gpt-5.5",
    "input": [
      {"role": "user", "content": "我叫小明，请记住我的名字"}
    ]
  }'

# 响应中会返回 id: "resp_abc123"

# 第二轮对话（延续上下文）
curl -X POST "https://api.mixroute.ai/v1/responses" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-xxxxxxxxxx" \
  -d '{
    "model": "gpt-5.5",
    "previous_response_id": "resp_abc123",
    "input": [
      {"role": "user", "content": "我叫什么名字？"}
    ]
  }'
```

## 响应格式

**非流式响应**

```json theme={null}
{
  "id": "resp_xxx",
  "object": "response",
  "created_at": 1709123456,
  "model": "gpt-5.5",
  "status": "completed",
  "output": [
    {
      "type": "message",
      "role": "assistant",
      "content": [
        {
          "type": "output_text",
          "text": "人工智能（Artificial Intelligence，简称AI）是计算机科学的一个分支..."
        }
      ]
    }
  ],
  "usage": {
    "input_tokens": 25,
    "output_tokens": 150,
    "total_tokens": 175
  }
}
```

**流式响应（SSE 事件）**

流式响应使用 Server-Sent Events (SSE) 格式返回：

```text theme={null}
event: response.created
data: {"type":"response.created","response":{"id":"resp_xxx","status":"in_progress"}}

event: response.output_item.added
data: {"type":"response.output_item.added","output_index":0,"item":{"type":"message","role":"assistant"}}

event: response.content_part.added
data: {"type":"response.content_part.added","part":{"type":"output_text","text":""}}

event: response.output_text.delta
data: {"type":"response.output_text.delta","delta":"人工"}

event: response.output_text.delta
data: {"type":"response.output_text.delta","delta":"智能"}

event: response.output_text.delta
data: {"type":"response.output_text.delta","delta":"是..."}

event: response.output_text.done
data: {"type":"response.output_text.done","text":"人工智能是..."}

event: response.completed
data: {"type":"response.completed","response":{"id":"resp_xxx","status":"completed","usage":{"input_tokens":25,"output_tokens":150}}}
```

**常见 SSE 事件类型：**

| 事件类型 | 说明 |
| - | - |
| `response.created` | 响应创建 |
| `response.output_text.delta` | 文本增量输出 |
| `response.output_text.done` | 文本输出完成 |
| `response.completed` | 响应完成 |
| `response.failed` | 响应失败 |

## 对比：Responses API vs Chat Completions API

| 特性 | Responses API | Chat Completions API |
| - | - | - |
| 推理模型支持 | ✅ 完整支持 | ⚠️ 有限支持 |
| 内置 Web Search | ✅ 原生支持 | ❌ 不支持 |
| 推理控制 | ✅ 精细控制 | ❌ 不支持 |
| 对话延续 | ✅ `previous_response_id` | ❌ 需手动管理 |
| 多模态输入 | ✅ 完整支持 | ✅ 支持 |
| 适用场景 | 推理、搜索、高级功能 | 通用对话 |

```bash cURL theme={null}
curl --request POST \
  --url https://api.mixroute.ai/v1/responses \
  --header 'Authorization: Bearer sk-xxxxxxxxxx' \
  --header 'Content-Type: application/json' \
  --data '{
    "model": "gpt-5.5",
    "max_output_tokens": 2048,
    "input": [
      {"role": "user", "content": "请用中文简要介绍人工智能"}
    ]
  }'
```

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

client = OpenAI(
    api_key="sk-xxxxxxxxxx",
    base_url="https://api.mixroute.ai/v1"
)

response = client.responses.create(
    model="gpt-5.5",
    max_output_tokens=2048,
    input=[
        {"role": "user", "content": "请用中文简要介绍人工智能"}
    ]
)
print(response.output_text)
```

```javascript JavaScript theme={null}
const OpenAI = require('openai');

const client = new OpenAI({
  apiKey: 'sk-xxxxxxxxxx',
  baseURL: 'https://api.mixroute.ai/v1'
});

const response = await client.responses.create({
  model: 'gpt-5.5',
  max_output_tokens: 2048,
  input: [
    { role: 'user', content: '请用中文简要介绍人工智能' }
  ]
});
console.log(response.output_text);
```

```php PHP theme={null}
<?php
$client = new GuzzleHttp\Client();
$response = $client->post('https://api.mixroute.ai/v1/responses', [
    'headers' => [
        'Authorization' => 'Bearer sk-xxxxxxxxxx',
        'Content-Type' => 'application/json',
    ],
    'json' => [
        'model' => 'gpt-5.5',
        'max_output_tokens' => 2048,
        'input' => [
            ['role' => 'user', 'content' => '请用中文简要介绍人工智能']
        ]
    ]
]);
echo $response->getBody();
```

```go Go theme={null}
package main

import (
    "bytes"
    "encoding/json"
    "net/http"
)

func main() {
    payload := map[string]interface{}{
        "model": "gpt-5.5",
        "max_output_tokens": 2048,
        "input": []map[string]string{
            {"role": "user", "content": "请用中文简要介绍人工智能"},
        },
    }
    body, _ := json.Marshal(payload)
    req, _ := http.NewRequest("POST", "https://api.mixroute.ai/v1/responses", bytes.NewBuffer(body))
    req.Header.Set("Authorization", "Bearer sk-xxxxxxxxxx")
    req.Header.Set("Content-Type", "application/json")
    http.DefaultClient.Do(req)
}
```

```java Java theme={null}
import java.net.http.*;
import java.net.URI;

HttpClient client = HttpClient.newHttpClient();
String json = """
    {
        "model": "gpt-5.5",
        "max_output_tokens": 2048,
        "input": [{"role": "user", "content": "请用中文简要介绍人工智能"}]
    }
    """;
HttpRequest request = HttpRequest.newBuilder()
    .uri(URI.create("https://api.mixroute.ai/v1/responses"))
    .header("Authorization", "Bearer sk-xxxxxxxxxx")
    .header("Content-Type", "application/json")
    .POST(HttpRequest.BodyPublishers.ofString(json))
    .build();
HttpResponse<String> response = client.send(request, HttpResponse.BodyHandlers.ofString());
System.out.println(response.body());
```

```ruby Ruby theme={null}
require 'net/http'
require 'json'

uri = URI('https://api.mixroute.ai/v1/responses')
http = Net::HTTP.new(uri.host, uri.port)
http.use_ssl = true

request = Net::HTTP::Post.new(uri)
request['Authorization'] = 'Bearer sk-xxxxxxxxxx'
request['Content-Type'] = 'application/json'
request.body = {
  model: 'gpt-5.5',
  max_output_tokens: 2048,
  input: [{ role: 'user', content: '请用中文简要介绍人工智能' }]
}.to_json

response = http.request(request)
puts response.body
```

```json Response theme={null}
{
  "id": "resp_xxx",
  "object": "response",
  "created_at": 1768271369,
  "model": "gpt-5.5",
  "status": "completed",
  "output": [
    {
      "id": "msg_xxx",
      "type": "message",
      "status": "completed",
      "role": "assistant",
      "content": [
        {
          "type": "output_text",
          "text": "人工智能（AI）是计算机科学的一个分支...",
          "annotations": []
        }
      ]
    }
  ],
  "usage": {
    "input_tokens": 25,
    "output_tokens": 150,
    "total_tokens": 175
  }
}
```

/


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.