OpenAI-Compatible API

Multi-model Claude, GPT and Gemini with one key

Flexible payment USDT, PayPal and cards accepted

Dual protocol OpenAI and Anthropic formats

Quick start Make calls minutes after signup

Quick answer

The AAA TOKEN /v1 endpoint follows the OpenAI Chat Completions format, so the official OpenAI SDKs, LangChain, LlamaIndex and most developer tools work after you change only the base_url and API key. You can even set the model parameter to a Claude or Gemini model.

Why use an OpenAI-compatible endpoint

Zero-change migration

Keep your existing OpenAI SDK and code. Change the base_url and key and you are live in minutes.

Switch models across vendors

Call Claude, GPT and Gemini through one interface. Changing models is just a different model name, with no need to integrate several SDKs.

One balance, pay as you go

Top up once and share one balance across every model. You pay only for the tokens you use, with no monthly commitment.

Flexible payment options

Top up with PayPal, USDT or Paddle, so you can get started even without an international credit card.

Connect in four steps

Sign up and top up — Create an AAA TOKEN account and add funds to your balance with PayPal, USDT or Paddle.
Create an API key — Generate your own API key in the account dashboard and keep it safe. Never share it publicly.
Change the base_url — In your OpenAI SDK, set base_url to the AAA TOKEN /v1 endpoint and enter your key.
Pick a model and call it — Set the model parameter to a Claude, GPT or Gemini model name and send your request to get a response.

Python example

This example uses the official OpenAI Python SDK. Only api_key and base_url change, and you can call a Claude model.

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="claude-3-5-sonnet",
    messages=[{"role": "user", "content": "Hello from AAA TOKEN"}],
)
print(resp.choices[0].message.content)

Is it right for you?

Good fit

Individual developers and teams who want one key for Claude, GPT and Gemini, pay with USDT or PayPal, and are billed only for actual usage.

Not a good fit

Organizations that need enterprise contracts, dedicated private deployments, or a direct agreement and official account with the model vendor.

Ready to try it?

Sign up free, claim your trial credit, and make your first call with your existing SDK in minutes.

Sign up free

Tài nguyên

AI API You Can Pay for with USDT | AAA TOKEN AI API Without a Credit Card: Claude, GPT & Gemini OpenAI API Alternative | Multi-Model API Gateway | AAA TOKEN OpenAI-Compatible API Proxy Anthropic-Compatible API Claude vs GPT vs Gemini pricing Cheap LLM API LLM API Proxy LLM API gateway Cursor with Claude OpenRouter alternative LiteLLM alternative Cursor GPT API Ví dụ Bắt đầu nhanh

Frequently asked questions

What is an OpenAI-compatible API?

It is a service whose request and response format matches the OpenAI API, so OpenAI SDKs and related tools work as-is. AAA TOKEN offers Claude, GPT, Gemini and other models on top of that format.

Can I call Claude with the OpenAI SDK?

Yes. Point base_url at AAA TOKEN and put a Claude model name in the model field. Your existing chat.completions code will return Claude's reply.

How much code do I need to change?

Usually only three settings: the API key, base_url and model name. The rest of your logic stays the same.

Are streaming and tool calling supported?

Streaming output is supported, along with common chat and tool-calling formats. Available features depend on the capabilities of each model.

How is usage billed?

Each request is deducted from your account balance in real time based on input and output tokens, with no monthly fee. See the pricing page for per-model rates.

How can I top up?

PayPal, USDT and Paddle are supported. Developers without an international credit card can still top up and start calling the API.

OpenAI-Compatible API: One Key for Claude, GPT and Gemini