---
description: "API 端点总览：兼容 OpenAI / Anthropic / Gemini 的全部接口索引。"
---

# API 总览

> API 端点: `https://oneapi.zaiwenai.com/v1`
>
> 在问的 API 接口与 OpenAI 接口兼容，可直接使用 OpenAI SDK 或其他兼容客户端接入。

## 支持的接口

| 接口 | 端点 | 说明 | 详情 |
|------|------|------|------|
| Chat Completions | `POST /v1/chat/completions` | 文本对话，兼容 OpenAI 格式 | [Chat Completions 文档](./api-chat.md) |
| Responses API | `POST /v1/responses` | OpenAI Responses 格式 | [Responses 文档](./api-responses.md) |
| Anthropic Messages | `POST /v1/messages` | Claude 原生调用格式 | [Messages 文档](./api-messages.md) |
| Embeddings | `POST /v1/embeddings` | 文本向量化 | [Embeddings 文档](./api-embeddings.md) |
| 图片生成 | `POST /v1/images/generations` | 文生图 | [图片文档](./api-images.md) |
| 图片编辑 | `POST /v1/images/edits` | 图片编辑 | [图片文档](./api-images.md) |
| Midjourney | `POST /v1/midjourney/generations` | 异步 Midjourney 图片生成、动作和参考图 | [Midjourney 文档](./api-midjourney.md) |
| 视频生成 | `POST /v1/videos/generations` | 异步文生视频与图生视频 | [视频文档](./api-videos.md) |
| MiniMax-H3 视频生成 | `POST /v1/videos/std/generations` | 任务制视频生成（MiniMax-H3） | [视频文档](./api-videos.md#minimax-h3-视频) |
| 音乐生成 | `POST /v1/music/generations` | 异步生成带人声歌曲或纯音乐 | [音乐文档](./api-music.md) |
| 语音转写 | `POST /v1/audio/transcriptions` | 音频转文本 | [语音文档](./api-audio.md) |
| 语音合成 | `POST /v1/audio/speech` | 文本生成 MP3 或 WAV 音频 | [语音文档](./api-audio.md) |
| Gemini 原生 | `POST /v1beta/models/{model}:generateContent` | Gemini 文/图/语音（透明代理，支持参考图/流式） | [Gemini 文档](./api-gemini.md) |

所有接口均使用 `Authorization: Bearer $YOUR_API_KEY` 进行认证（Anthropic Messages 同时支持 `x-api-key` 头）。

## Curl 示例

```bash
curl https://oneapi.zaiwenai.com/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $YOUR_API_KEY" \
  -d '{
    "model": "deepseek-v4-flash",
    "messages": [
      {
        "role": "system",
        "content": "You are a helpful assistant."
      },
      {
        "role": "user",
        "content": "Hello!"
      }
    ]
  }'
```

## OpenAI Python SDK 示例

```python
from openai import OpenAI

client = OpenAI(
  base_url="https://oneapi.zaiwenai.com/v1",
  api_key="$YOUR_API_KEY",
)

completion = client.chat.completions.create(
    model="deepseek-v4-flash",
  messages=[
    {
      "role": "system",
      "content": "You are a helpful assistant."
    },
    {
      "role": "user",
      "content": "hello!"
    }
  ]
)

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

## LangChain 与工具调用示例

```python
# pip install langchain langchain_openai
from pprint import pprint

from langchain.agents import create_agent
from langchain_openai import ChatOpenAI

model = ChatOpenAI(
    base_url="https://oneapi.zaiwenai.com/v1",
    api_key="$YOUR_API_KEY",
  model="deepseek-v4-flash",
)

# Mock weather data for a more realistic simulation
_weather_db = {
    "Beijing": "Hazy, 28°C",
}


def get_user_city() -> str:
    """
    Asks the user for their current city via command-line input.
    """
    print("+++++ TOOL USER ++++: try to get user's city")
    return "Beijing"


def get_weather(city: str) -> str:
    """
    get weather for a given city from a mock database.
    """
    print(f"+++++ TOOL USER ++++: try to get weather for {city}")
    return _weather_db.get(
        city, f"Sorry, I don't have weather information for {city}."
    )

agent = create_agent(
    model=model,
    tools=[get_weather, get_user_city],
    system_prompt="You are a helpful assistant.",
)

r = agent.invoke(
    {"messages": [{"role": "user", "content": "What's the weather like?"}]}
)

pprint(r)
```