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
Responses API	POST /v1/responses	OpenAI Responses 格式	Responses 文档
Anthropic Messages	POST /v1/messages	Claude 原生调用格式	Messages 文档
Embeddings	POST /v1/embeddings	文本向量化	Embeddings 文档
图片生成	POST /v1/images/generations	文生图	图片文档
图片编辑	POST /v1/images/edits	图片编辑	图片文档
Midjourney	POST /v1/midjourney/generations	异步 Midjourney 图片生成、动作和参考图	Midjourney 文档
视频生成	POST /v1/videos/generations	异步文生视频与图生视频	视频文档
MiniMax-H3 视频生成	POST /v1/videos/std/generations	任务制视频生成（MiniMax-H3）	视频文档
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
语音转写	POST /v1/audio/transcriptions	音频转文本	语音文档
语音合成	POST /v1/audio/speech	文本生成 MP3 或 WAV 音频	语音文档
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

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

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

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

# 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)