ModelStack 官方文档

Appearance

基本信息 ​

公开的服务地址 ​

https://modelstack.app/v1

TIP

某些应用可能会自动帮你添加 /v1 后缀。因此如果发现 404 错误，请尝试删除 /v1 后缀。

ModelStack 提供基于 HTTP 的 API 服务接入，并且提供 OpenAI SDK 兼容接口。

OpenAI Chat Completion 接口使用 ​

安装 OpenAI Python SDK

bash
pip install openai
# 推荐使用 uv
# uv init
# uv add openai

同步请求 ​

python
from openai import OpenAI
 
client = OpenAI(
    api_key = "your-api-key",
    base_url = "https://modelstack.app/v1",
)

completion = client.chat.completions.create(
    model = "gemini-2.5-pro",
    messages = [
        {"role": "system", "content": "你是一个智能助手，请根据用户的问题给出回答。"},
        {"role": "user", "content": "你好，Flash Attention 是什么？"}
    ],
    temperature = 0.6,
)

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

异步请求 ​

python
import asyncio

from openai import AsyncOpenAI

client = AsyncOpenAI(
    api_key="your-api-key",
    base_url="https://modelstack.app/v1",
)


async def main():
    completion = await client.chat.completions.create(
        model="gemini-2.5-pro",
        messages=[
            {
                "role": "system",
                "content": "你是一个智能助手，请根据用户的问题给出回答。",
            },
            {"role": "user", "content": "你好，Flash Attention 是什么？"},
        ],
        temperature=0.6,
    )
    print(completion.choices[0].message.content)


asyncio.run(main())

流式请求 ​

python
import asyncio

from openai import AsyncOpenAI

client = AsyncOpenAI(
    api_key="your-api-key",
    base_url="https://modelstack.app/v1",
)


async def main():
    stream = await client.chat.completions.create(
        stream=True,
        model="gemini-2.5-pro",
        messages=[
            {
                "role": "system",
                "content": "你是一个智能助手，请根据用户的问题给出回答。",
            },
            {"role": "user", "content": "你好，Flash Attention 是什么？"},
        ],
        temperature=0.6,
    )
    async for chunk in stream:
        print(chunk.choices[0].delta.content, end="", flush=True)


asyncio.run(main())