Before you start Replace $AAA_TOKEN_API_KEY in the samples below with your own API key, and store it in an environment variable rather than hard-coding it.

The quickest way to test: call the OpenAI-compatible chat completions endpoint directly with curl.

cURL

curl https://aaa.ashp.tw/v1/chat/completions \
  -H "Authorization: Bearer $AAA_TOKEN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-sonnet-4-6",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

With the official OpenAI Python SDK, just change base_url and api_key and your existing code keeps working.

OpenAI Python SDK

from openai import OpenAI

client = OpenAI(
    api_key="$AAA_TOKEN_API_KEY",
    base_url="https://aaa.ashp.tw/v1",
)

resp = client.chat.completions.create(
    model="gpt-5.4",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(resp.choices[0].message.content)

With the official Anthropic SDK, point base_url at the AAA TOKEN Anthropic-compatible endpoint to use the Claude Messages API.

Anthropic Python SDK

from anthropic import Anthropic

client = Anthropic(
    api_key="$AAA_TOKEN_API_KEY",
    base_url="https://aaa.ashp.tw/v1/anthropic",
)

msg = client.messages.create(
    model="claude-sonnet-4-6",
    max_tokens=1024,
    messages=[{"role": "user", "content": "Hello!"}],
)
print(msg.content[0].text)

Use the official OpenAI SDK in Node.js by setting just the baseURL and your API key.

OpenAI Node.js SDK

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.AAA_TOKEN_API_KEY,
  baseURL: "https://aaa.ashp.tw/v1",
});

const resp = await client.chat.completions.create({
  model: "gpt-5.4",
  messages: [{ role: "user", content: "Hello!" }],
});
console.log(resp.choices[0].message.content);

Set stream=True to receive output incrementally. The Python example below reuses the client created above.

Python streaming

stream = client.chat.completions.create(
    model="claude-sonnet-4-6",
    messages=[{"role": "user", "content": "Hello!"}],
    stream=True,
)
for chunk in stream:
    delta = chunk.choices[0].delta.content
    if delta:
        print(delta, end="", flush=True)

Cursor, Cline and other dev tools

Cursor: in Settings → Models, enter your API key, enable Override OpenAI Base URL and paste the base URL below, then add the model names you want to use.

Cline (VS Code extension): choose OpenAI Compatible as the API provider, then enter the base URL below, your API key and a model name.

Base URL https://aaa.ashp.tw/v1

Replace $AAA_TOKEN_API_KEY with your own API key (it starts with sk-). It is sent in the Authorization header.

Get your API key Quick Start →

Integration examples