Qwen 模型（OpenAI 兼容）

通过兼容 OpenAI 格式的 Chat API 调用通义千问系列模型，支持文本对话、多模态输入、流式输出、工具调用、联网搜索等能力。

接口地址

http

POST /v1/chat/completions

认证

方式	说明
Bearer Token	在请求头中携带 `Authorization: Bearer <API Key>` 用于验证账户信息。

请求头

参数名	类型	必填	说明
`Content-Type`	`string`	是	请求体的媒介类型，请设置为 `application/json`
`Authorization`	`string`	是	Bearer API Key，用于验证账户信息

请求体

参数名	类型	必填	默认值	说明
`model`	`string`	是	-	模型名称，支持的模型：Qwen 大语言模型等
`messages`	`array`	是	-	传递给大模型的上下文，按对话顺序排列
`stream`	`boolean`	否	`false`	是否以流式输出方式回复
`stream_options`	`object`	否	-	流式输出配置，仅在 `stream` 为 `true` 时生效
`temperature`	`float`	否	`0.7`	采样温度，控制生成多样性，取值范围 `[0, 2)`
`top_p`	`float`	否	`0.8`	核采样概率阈值，取值范围 `(0, 1.0]`
`top_k`	`integer`	否	`20`	采样候选 Token 数量，非 OpenAI 标准参数，SDK 调用时放入 `extra_body`
`max_tokens`	`integer`	否	-	模型回答最大长度（不包含思维链），即将废弃，请用 `max_completion_tokens`
`max_completion_tokens`	`integer`	否	-	模型输出最大长度（包含思维链和回答）
`response_format`	`object`	否	`{"type":"text"}`	返回内容格式，可选 `text` 或 `json_object`
`tools`	`array`	否	-	工具对象数组，供模型在 Function Calling 中调用
`tool_choice`	`string`/`object`	否	`auto`	工具选择策略，可选 `auto`、`none` 或指定工具
`parallel_tool_calls`	`boolean`	否	`false`	是否开启并行工具调用
`enable_search`	`boolean`	否	`false`	是否开启联网搜索，非 OpenAI 标准参数，SDK 调用时放入 `extra_body`
`search_options`	`object`	否	-	联网搜索策略
`enable_thinking`	`boolean`	否	-	是否开启思考模式，适用于混合思考模型，非 OpenAI 标准参数
`thinking_budget`	`integer`	否	-	思考过程最大 Token 数，非 OpenAI 标准参数
`reasoning_effort`	`string`	否	-	推理力度，可选 `low`/`medium`/`high`/`max`/`xhigh`，非 OpenAI 标准参数
`seed`	`integer`	否	`1234`	随机数种子，用于结果可复现，取值范围 `[0, 2^31-1]`
`stop`	`string`/`array`	否	-	停止词，生成文本中出现指定字符串时终止
`n`	`integer`	否	`1`	生成响应数量，取值范围 `1-4`
`logprobs`	`boolean`	否	`false`	是否返回输出 Token 的对数概率
`top_logprobs`	`integer`	否	`0`	返回候选 Token 个数，取值范围 `[0, 5]`
`repetition_penalty`	`float`	否	`1.05`	重复度惩罚，大于 0 即可，非 OpenAI 标准参数
`presence_penalty`	`float`	否	`0.0`	内容重复度控制，取值范围 `[-2.0, 2.0]`

`messages` 消息类型

消息类型	role	说明
System Message	`system`	系统消息，设定模型角色、语气、任务约束，一般放第一位
User Message	`user`	用户消息，传递问题或上下文
Assistant Message	`assistant`	模型回复，用于多轮对话上下文回传
Tool Message	`tool`	工具输出信息

QwQ 模型不建议设置 System Message，QVQ 模型设置 System Message 不会生效。

`stream_options` 参数

参数名	类型	必填	默认值	说明
`include_usage`	`boolean`	否	`false`	是否在最后一个数据块包含 Token 消耗信息

`search_options` 参数

参数名	类型	默认值	说明
`forced_search`	`boolean`	`false`	是否强制开启联网搜索
`search_strategy`	`string`	`turbo`	搜索策略，可选 `turbo`/`max`/`agent`/`agent_max`
`enable_search_extension`	`boolean`	`false`	是否开启垂域搜索

模型说明

支持的模型

qwen-plus、qwen-max、qwen-turbo、qwen-flash
qwen3.5、qwen3.6、qwen3.7 系列

具体模型名称和计费请参见平台控制台模型市场。

请求示例

文本输入

cURLPythonNode.js

bash

curl -X POST 'https://neolink.com/api/v1/chat/completions' \
  -H 'Authorization: Bearer <API Key>' \
  -H 'Content-Type: application/json' \
  -d '{
    "model": "qwen-plus",
    "messages": [
      {"role": "system", "content": "You are a helpful assistant."},
      {"role": "user", "content": "你是谁？"}
    ]
  }'

python

from openai import OpenAI

client = OpenAI(
    api_key="<API Key>",
    base_url="https://neolink.com/api/v1",
)

completion = client.chat.completions.create(
    model="qwen-plus",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "你是谁？"},
    ],
)
print(completion.model_dump_json())

javascript

import OpenAI from "openai";

const openai = new OpenAI({
  apiKey: "<API Key>",
  baseURL: "https://neolink.com/api/v1",
});

async function main() {
  const completion = await openai.chat.completions.create({
    model: "qwen-plus",
    messages: [
      { role: "system", content: "You are a helpful assistant." },
      { role: "user", content: "你是谁？" },
    ],
  });
  console.log(JSON.stringify(completion));
}
main();

流式输出

cURLPythonNode.js

bash

curl --location 'https://neolink.com/api/v1/chat/completions' \
  --header 'Authorization: Bearer <API Key>' \
  --header 'Content-Type: application/json' \
  --data '{
    "model": "qwen-plus",
    "messages": [
      {"role": "system", "content": "You are a helpful assistant."},
      {"role": "user", "content": "你是谁？"}
    ],
    "stream": true,
    "stream_options": {"include_usage": true}
  }'

python

from openai import OpenAI

client = OpenAI(
    api_key="<API Key>",
    base_url="https://neolink.com/api/v1",
)

completion = client.chat.completions.create(
    model="qwen-plus",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "你是谁？"},
    ],
    stream=True,
    stream_options={"include_usage": True},
)
for chunk in completion:
    print(chunk.model_dump_json())

javascript

import OpenAI from "openai";

const openai = new OpenAI({
  apiKey: "<API Key>",
  baseURL: "https://neolink.com/api/v1",
});

async function main() {
  const completion = await openai.chat.completions.create({
    model: "qwen-plus",
    messages: [
      { role: "system", content: "You are a helpful assistant." },
      { role: "user", content: "你是谁？" },
    ],
    stream: true,
    stream_options: { include_usage: true },
  });
  for await (const chunk of completion) {
    console.log(JSON.stringify(chunk));
  }
}
main();

图像输入

cURLPythonNode.js

bash

curl -X POST 'https://neolink.com/api/v1/chat/completions' \
  -H 'Authorization: Bearer <API Key>' \
  -H 'Content-Type: application/json' \
  -d '{
    "model": "qwen-vl-plus",
    "messages": [
      {
        "role": "user",
        "content": [
          {"type": "image_url", "image_url": {"url": "https://dashscope.oss-cn-beijing.aliyuncs.com/images/dog_and_girl.jpeg"}},
          {"type": "text", "text": "这是什么"}
        ]
      }
    ]
  }'

python

from openai import OpenAI

client = OpenAI(
    api_key="<API Key>",
    base_url="https://neolink.com/api/v1",
)

completion = client.chat.completions.create(
    model="qwen-vl-plus",
    messages=[{
        "role": "user",
        "content": [
            {"type": "image_url", "image_url": {"url": "https://dashscope.oss-cn-beijing.aliyuncs.com/images/dog_and_girl.jpeg"}},
            {"type": "text", "text": "这是什么"},
        ],
    }],
)
print(completion.model_dump_json())

javascript

import OpenAI from "openai";

const openai = new OpenAI({
  apiKey: "<API Key>",
  baseURL: "https://neolink.com/api/v1",
});

async function main() {
  const response = await openai.chat.completions.create({
    model: "qwen-vl-max",
    messages: [{
      role: "user",
      content: [
        { type: "image_url", image_url: { url: "https://dashscope.oss-cn-beijing.aliyuncs.com/images/dog_and_girl.jpeg" } },
        { type: "text", text: "这是什么？" },
      ],
    }],
  });
  console.log(JSON.stringify(response));
}
main();

视频输入（图片列表）

cURLPythonNode.js

bash

curl -X POST 'https://neolink.com/api/v1/chat/completions' \
  -H 'Authorization: Bearer <API Key>' \
  -H 'Content-Type: application/json' \
  -d '{
    "model": "qwen-vl-max",
    "messages": [
      {
        "role": "user",
        "content": [
          {
            "type": "video",
            "video": [
              "https://img.alicdn.com/imgextra/i3/O1CN01K3SgGo1eqmlUgeE9b_!!6000000003923-0-tps-3840-2160.jpg",
              "https://img.alicdn.com/imgextra/i4/O1CN01BjZvwg1Y23CF5qIRB_!!6000000003000-0-tps-3840-2160.jpg"
            ]
          },
          {"type": "text", "text": "描述这个视频的具体过程"}
        ]
      }
    ]
  }'

python

from openai import OpenAI

client = OpenAI(
    api_key="<API Key>",
    base_url="https://neolink.com/api/v1",
)

completion = client.chat.completions.create(
    model="qwen-vl-max",
    messages=[{
        "role": "user",
        "content": [
            {
                "type": "video",
                "video": [
                    "https://img.alicdn.com/imgextra/i3/O1CN01K3SgGo1eqmlUgeE9b_!!6000000003923-0-tps-3840-2160.jpg",
                    "https://img.alicdn.com/imgextra/i4/O1CN01BjZvwg1Y23CF5qIRB_!!6000000003000-0-tps-3840-2160.jpg",
                ],
            },
            {"type": "text", "text": "描述这个视频的具体过程"},
        ],
    }],
)
print(completion.model_dump_json())

javascript

import OpenAI from "openai";

const openai = new OpenAI({
  apiKey: "<API Key>",
  baseURL: "https://neolink.com/api/v1",
});

async function main() {
  const response = await openai.chat.completions.create({
    model: "qwen-vl-max",
    messages: [{
      role: "user",
      content: [
        {
          type: "video",
          video: [
            "https://img.alicdn.com/imgextra/i3/O1CN01K3SgGo1eqmlUgeE9b_!!6000000003923-0-tps-3840-2160.jpg",
            "https://img.alicdn.com/imgextra/i4/O1CN01BjZvwg1Y23CF5qIRB_!!6000000003000-0-tps-3840-2160.jpg",
          ],
        },
        { type: "text", text: "描述这个视频的具体过程" },
      ],
    }],
  });
  console.log(JSON.stringify(response));
}
main();

工具调用（Function Calling）

cURLPythonNode.js

bash

curl -X POST 'https://neolink.com/api/v1/chat/completions' \
  -H 'Authorization: Bearer <API Key>' \
  -H 'Content-Type: application/json' \
  -d '{
    "model": "qwen-plus",
    "messages": [
      {"role": "system", "content": "You are a helpful assistant."},
      {"role": "user", "content": "杭州天气怎么样"}
    ],
    "tools": [
      {
        "type": "function",
        "function": {
          "name": "get_current_time",
          "description": "当你想知道现在的时间时非常有用。",
          "parameters": {}
        }
      },
      {
        "type": "function",
        "function": {
          "name": "get_current_weather",
          "description": "当你想查询指定城市的天气时非常有用。",
          "parameters": {
            "type": "object",
            "properties": {
              "location": {
                "type": "string",
                "description": "城市或县区，比如北京市、杭州市、余杭区等。"
              }
            },
            "required": ["location"]
          }
        }
      }
    ]
  }'

python

from openai import OpenAI

client = OpenAI(
    api_key="<API Key>",
    base_url="https://neolink.com/api/v1",
)

tools = [
    {
        "type": "function",
        "function": {
            "name": "get_current_time",
            "description": "当你想知道现在的时间时非常有用。",
            "parameters": {},
        }
    },
    {
        "type": "function",
        "function": {
            "name": "get_current_weather",
            "description": "当你想查询指定城市的天气时非常有用。",
            "parameters": {
                "type": "object",
                "properties": {
                    "location": {
                        "type": "string",
                        "description": "城市或县区，比如北京市、杭州市、余杭区等。",
                    }
                },
                "required": ["location"],
            },
        }
    },
]

messages = [{"role": "user", "content": "杭州天气怎么样"}]
completion = client.chat.completions.create(
    model="qwen-plus",
    messages=messages,
    tools=tools,
)
print(completion.model_dump_json())

javascript

import OpenAI from "openai";

const openai = new OpenAI({
  apiKey: "<API Key>",
  baseURL: "https://neolink.com/api/v1",
});

const tools = [
  {
    type: "function",
    function: {
      name: "get_current_time",
      description: "当你想知道现在的时间时非常有用。",
      parameters: {},
    },
  },
  {
    type: "function",
    function: {
      name: "get_current_weather",
      description: "当你想查询指定城市的天气时非常有用。",
      parameters: {
        type: "object",
        properties: {
          location: {
            type: "string",
            description: "城市或县区，比如北京市、杭州市、余杭区等。",
          },
        },
        required: ["location"],
      },
    },
  },
];

async function main() {
  const response = await openai.chat.completions.create({
    model: "qwen-plus",
    messages: [{ role: "user", content: "杭州天气怎么样" }],
    tools: tools,
  });
  console.log(JSON.stringify(response));
}
main();

联网搜索

cURLPythonNode.js

bash

curl -X POST 'https://neolink.com/api/v1/chat/completions' \
  -H 'Authorization: Bearer <API Key>' \
  -H 'Content-Type: application/json' \
  -d '{
    "model": "qwen-plus",
    "messages": [
      {"role": "system", "content": "You are a helpful assistant."},
      {"role": "user", "content": "中国队在巴黎奥运会获得了多少枚金牌"}
    ],
    "enable_search": true
  }'

python

from openai import OpenAI

client = OpenAI(
    api_key="<API Key>",
    base_url="https://neolink.com/api/v1",
)

completion = client.chat.completions.create(
    model="qwen-plus",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "中国队在巴黎奥运会获得了多少枚金牌"},
    ],
    extra_body={"enable_search": True},
)
print(completion.model_dump_json())

javascript

import OpenAI from "openai";

const openai = new OpenAI({
  apiKey: "<API Key>",
  baseURL: "https://neolink.com/api/v1",
});

async function main() {
  const completion = await openai.chat.completions.create({
    model: "qwen-plus",
    messages: [
      { role: "system", content: "You are a helpful assistant." },
      { role: "user", content: "中国队在巴黎奥运会获得了多少枚金牌" },
    ],
    enable_search: true,
  });
  console.log(JSON.stringify(completion));
}
main();

异步调用

PythonNode.js

python

import asyncio
from openai import AsyncOpenAI

client = AsyncOpenAI(
    api_key="<API Key>",
    base_url="https://neolink.com/api/v1",
)

async def main():
    response = await client.chat.completions.create(
        messages=[{"role": "user", "content": "你是谁"}],
        model="qwen-plus",
    )
    print(response.model_dump_json())

asyncio.run(main())

javascript

import OpenAI from "openai";

const openai = new OpenAI({
  apiKey: "<API Key>",
  baseURL: "https://neolink.com/api/v1",
});

async function main() {
  const completion = await openai.chat.completions.create({
    model: "qwen-plus",
    messages: [{ role: "user", content: "你是谁" }],
  });
  console.log(JSON.stringify(completion));
}
main();

响应体

非流式响应

参数名	类型	说明
`id`	`string`	本次调用的唯一标识符
`choices`	`array`	模型生成内容的数组
`choices[].message.content`	`string`	模型的回复内容
`choices[].message.reasoning_content`	`string`	模型的思维链内容（思考模式）
`choices[].message.role`	`string`	消息角色，固定为 `assistant`
`choices[].message.tool_calls`	`array`	工具调用信息（Function Calling 时返回）
`choices[].finish_reason`	`string`	停止原因：`stop`/`length`/`tool_calls`
`choices[].index`	`integer`	在 `choices` 数组中的索引
`choices[].logprobs`	`object`	Token 概率信息
`created`	`integer`	请求创建时的 Unix 时间戳（秒）
`model`	`string`	本次请求使用的模型
`object`	`string`	固定为 `chat.completion`
`usage`	`object`	Token 消耗信息
`usage.prompt_tokens`	`integer`	输入 Token 数
`usage.completion_tokens`	`integer`	输出 Token 数
`usage.total_tokens`	`integer`	总 Token 数
`usage.prompt_tokens_details.cached_tokens`	`integer`	命中缓存的 Token 数
`usage.completion_tokens_details.text_tokens`	`integer`	输出文本 Token 数

非流式响应示例

json

{
  "choices": [
    {
      "message": {
        "role": "assistant",
        "content": "我是阿里云开发的一款超大规模语言模型，我叫千问。"
      },
      "finish_reason": "stop",
      "index": 0,
      "logprobs": null
    }
  ],
  "object": "chat.completion",
  "usage": {
    "prompt_tokens": 3019,
    "completion_tokens": 104,
    "total_tokens": 3123,
    "prompt_tokens_details": {
      "cached_tokens": 2048
    }
  },
  "created": 1735120033,
  "model": "qwen-plus",
  "id": "chatcmpl-6ada9ed2-7f33-9de2-8bb0-78bd4035025a"
}

流式响应

流式输出时，每个 chunk 的 object 为 chat.completion.chunk，choices 中通过 delta 字段返回增量内容：

参数名	类型	说明
`id`	`string`	本次调用的唯一标识符，每个 chunk 相同
`choices[].delta.content`	`string`	增量消息内容
`choices[].delta.reasoning_content`	`string`	增量思维链内容
`choices[].delta.role`	`string`	角色，只在第一个 chunk 中有值
`choices[].delta.tool_calls`	`array`	增量工具调用信息
`choices[].finish_reason`	`string`	停止原因，未结束时为 `null`
`created`	`integer`	请求创建时间戳
`model`	`string`	本次请求使用的模型
`object`	`string`	固定为 `chat.completion.chunk`
`usage`	`object`	Token 消耗信息，仅在 `include_usage` 为 `true` 时的最后一个 chunk 返回

流式响应示例

json

{"id":"chatcmpl-e30f5ae7","choices":[{"delta":{"content":"","role":"assistant"},"finish_reason":null,"index":0}],"created":1735113344,"model":"qwen-plus","object":"chat.completion.chunk","usage":null}

{"id":"chatcmpl-e30f5ae7","choices":[{"delta":{"content":"我是"}}],"created":1735113344,"model":"qwen-plus","object":"chat.completion.chunk","usage":null}

{"id":"chatcmpl-e30f5ae7","choices":[{"delta":{"content":"阿里云的超大规模语言模型"}}],"created":1735113344,"model":"qwen-plus","object":"chat.completion.chunk","usage":null}

{"id":"chatcmpl-e30f5ae7","choices":[{"delta":{"content":""},"finish_reason":"stop","index":0}],"created":1735113344,"model":"qwen-plus","object":"chat.completion.chunk","usage":null}

{"id":"chatcmpl-e30f5ae7","choices":[],"created":1735113344,"model":"qwen-plus","object":"chat.completion.chunk","usage":{"completion_tokens":17,"prompt_tokens":22,"total_tokens":39,"prompt_tokens_details":{"cached_tokens":0}}}

错误码

如果模型调用失败并返回报错信息，请参见用户错误码指南进行解决。

MiniMax/hailuo

MiniMax-H3

MiniMax

Suno

OpenAI 兼容接口

Seedance资源管理

Qwen 模型（OpenAI 兼容）

接口地址

认证

请求头

请求体

`messages` 消息类型

`stream_options` 参数

`search_options` 参数

模型说明

支持的模型

请求示例

文本输入

流式输出

图像输入

视频输入（图片列表）

工具调用（Function Calling）

联网搜索

异步调用

响应体

非流式响应

非流式响应示例

流式响应

流式响应示例

错误码

MiniMax/hailuo

MiniMax-H3

MiniMax

Suno

OpenAI 兼容接口

Seedance资源管理

Qwen 模型（OpenAI 兼容） ​

接口地址 ​

认证 ​

请求头 ​

请求体 ​

messages 消息类型 ​

stream_options 参数 ​

search_options 参数 ​

模型说明 ​

支持的模型 ​

请求示例 ​

文本输入 ​

流式输出 ​

图像输入 ​

视频输入（图片列表） ​

工具调用（Function Calling） ​

联网搜索 ​

异步调用 ​

响应体 ​

非流式响应 ​

非流式响应示例 ​

流式响应 ​

流式响应示例 ​

错误码 ​

Qwen 模型（OpenAI 兼容）

接口地址

认证

请求头

请求体

`messages` 消息类型

`stream_options` 参数

`search_options` 参数

模型说明

支持的模型

请求示例

文本输入

流式输出

图像输入

视频输入（图片列表）

工具调用（Function Calling）

联网搜索

异步调用

响应体

非流式响应

非流式响应示例

流式响应

流式响应示例

错误码