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

# OpenAI SDK 接入

> 使用 OpenAI 官方 SDK 调用晨羽智云大模型网关

# OpenAI SDK 接入

OpenAI SDK 用户只需要把 `base_url` 指向晨羽智云网关，并使用晨羽智云 API Key。

## 安装

```bash theme={null}
pip install openai
```

## 初始化客户端

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

client = OpenAI(
    base_url="https://api.chenyu.cn/v1",
    api_key="YOUR_API_KEY",
)
```

## 获取模型列表

```python theme={null}
models = client.models.list()
for model in models.data:
    print(model.id)
```

## 文本对话

```python theme={null}
resp = client.chat.completions.create(
    model="doubao-seed-2-0-lite-260428",
    messages=[
        {"role": "user", "content": "你好，简单介绍一下你自己"}
    ],
)

print(resp.choices[0].message.content)
```

## 图生文

```python theme={null}
resp = client.chat.completions.create(
    model="doubao-seed-1-6-vision-250815",
    messages=[
        {
            "role": "user",
            "content": [
                {"type": "text", "text": "这张图里有什么？"},
                {
                    "type": "image_url",
                    "image_url": {
                        "url": "https://example.com/image.png"
                    },
                },
            ],
        }
    ],
)

print(resp.choices[0].message.content)
```

## 多图生文

```python theme={null}
resp = client.chat.completions.create(
    model="doubao-seed-1-6-vision-250815",
    messages=[
        {
            "role": "user",
            "content": [
                {"type": "text", "text": "比较两张图片的差异"},
                {"type": "image_url", "image_url": {"url": "https://example.com/a.png"}},
                {"type": "image_url", "image_url": {"url": "https://example.com/b.png"}},
            ],
        }
    ],
)

print(resp.choices[0].message.content)
```

## Responses API

```python theme={null}
resp = client.responses.create(
    model="doubao-seed-2-0-lite-260428",
    input="用三句话说明 GPU 云服务适合哪些场景",
)

print(resp.output_text)
```

模型专属参数可以通过 `extra_body` 传递：

```python theme={null}
resp = client.responses.create(
    model="doubao-seed-2-0-lite-260428",
    input="分析这个问题",
    extra_body={
        "thinking": {"type": "enabled"},
        "reasoning": {"effort": "low"},
    },
)
```

## 文生图

```python theme={null}
img = client.images.generate(
    model="doubao-seedream-5-0-lite-260128",
    prompt="电商主图，白底，一瓶护肤品，柔和布光",
    size="1024x1024",
)

print(img.data[0].url)
```

## 图片编辑

```python theme={null}
with open("input.png", "rb") as image:
    edited = client.images.edit(
        model="doubao-seedream-5-0-lite-260128",
        image=image,
        prompt="把背景改成浅蓝色，保持主体不变",
        size="1024x1024",
    )

print(edited.data[0].url)
```

## 视频任务

OpenAI SDK 暂未提供通用视频任务方法，视频接口建议直接使用 HTTP 请求：

```python theme={null}
import requests

headers = {
    "Authorization": "Bearer YOUR_API_KEY",
    "Content-Type": "application/json",
}

resp = requests.post(
    "https://api.chenyu.cn/v1/videos",
    headers=headers,
    json={
        "model": "doubao-seedance-2-0-fast-260128",
        "prompt": "一只白色机器人在未来城市街道上行走，电影感镜头",
    },
)
task = resp.json()
print(task["id"])

result = requests.get(
    f"https://api.chenyu.cn/v1/videos/{task['id']}",
    headers=headers,
)
print(result.json())
```