使用 OpenAI SDK

把 base_url 指向 Allen API，其余代码不用改。

Python

from openai import OpenAI

client = OpenAI(
    base_url="https://api.allenyeahger.xyz/v1",
    api_key="sk-your-key",
)

resp = client.chat.completions.create(
    model="your-model-id",
    messages=[{"role": "user", "content": "请只回复：接入成功"}],
)
print(resp.choices[0].message.content)

流式：

stream = client.chat.completions.create(
    model="your-model-id",
    messages=[{"role": "user", "content": "写一句自我介绍"}],
    stream=True,
)
for chunk in stream:
    if chunk.choices and chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="", flush=True)

Node.js

import OpenAI from 'openai';

const client = new OpenAI({
  baseURL: 'https://api.allenyeahger.xyz/v1',
  apiKey: 'sk-your-key',
});

const resp = await client.chat.completions.create({
  model: 'your-model-id',
  messages: [{ role: 'user', content: '请只回复：接入成功' }],
});

console.log(resp.choices[0].message.content);

不要硬编码密钥

import os
from openai import OpenAI

client = OpenAI(
    base_url=os.environ.get("ALLEN_API_BASE", "https://api.allenyeahger.xyz/v1"),
    api_key=os.environ.get("ALLEN_API_KEY"),
)

export ALLEN_API_KEY=sk-your-key

列表可用模型

models = client.models.list()
for m in models.data:
    print(m.id)

常见问题

404 Not Found：base_url 重复了 /v1，去掉一个。

超时：大上下文请求耗时较长，显式设置超时：

client = OpenAI(
    base_url="https://api.allenyeahger.xyz/v1",
    api_key="sk-your-key",
    timeout=120.0,
    max_retries=2,
)