One LLM API Proxy for Claude, GPT and Gemini with a Single Key
Reach multiple model providers through one OpenAI-compatible endpoint. Switch models by changing a single parameter, with no rewrites and no juggling of separate accounts or bills.
AAA TOKEN is an LLM API proxy: your app connects to a single endpoint with one API key and can call Claude, GPT, Gemini and other leading models. Requests are compatible with OpenAI and Anthropic formats, so existing SDKs and tools work by changing only the base URL, and usage is billed from a single balance.
AAA TOKEN is an LLM API proxy: your app connects to a single endpoint with one API key and can call Claude, GPT, Gemini and other leading models. Requests are compatible with OpenAI and Anthropic formats, so existing SDKs and tools work by changing only the base URL, and usage is billed from a single balance.
Why use an LLM API proxy
One key, many models
No need to sign up with each provider separately. A single AAA TOKEN key reaches Claude, GPT and Gemini.
Switch models in one line
Every model shares the same request format. Change the model parameter to compare or switch, and leave the rest of your code untouched.
One balance, transparent usage
All models draw from the same balance, and the dashboard shows usage and cost per request, with no multiple invoices to reconcile.
Flexible ways to top up
Top up with USDT, PayPal and more. Billing follows usage with no monthly minimum, so you simply add funds when the balance runs low.
Get started with the LLM API proxy in four steps
- Sign up and top up — Create an AAA TOKEN account and add any amount to your balance.
- Create an API key — Create a key in your account dashboard, and set a quota or a note for its purpose if you like.
- Set the endpoint — Point your SDK or tool's base URL at 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.
Code examples
These examples use the OpenAI Python SDK. The same code calls models from different providers by changing only the model name, and you can also test directly with curl.
from openai import OpenAI
client = OpenAI(
api_key="$AAA_TOKEN_API_KEY",
base_url="https://aaa.ashp.tw/v1",
)
messages = [{"role": "user", "content": "Compare these two options"}]
claude = client.chat.completions.create(model="claude-3-5-sonnet", messages=messages)
gpt = client.chat.completions.create(model="gpt-4o", messages=messages)
gemini = client.chat.completions.create(model="gemini-1.5-pro", messages=messages)
curl https://aaa.ashp.tw/v1/chat/completions \
-H "Authorization: Bearer $AAA_TOKEN_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"claude-3-5-sonnet","messages":[{"role":"user","content":"Hello from one LLM proxy"}]}'
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 free리소스
LLM API proxy FAQ
What is an LLM API proxy?
An LLM API proxy sits between your app and the model providers so you can call several of them through one endpoint and one key. AAA TOKEN forwards your requests and bills them in one place.
Which models can I call?
You can call leading models such as Claude, GPT and Gemini. See the pricing page and the model list in your dashboard for what is currently available and what it costs.
Do I need to rewrite my existing code?
Usually not. Change the SDK base URL to the AAA TOKEN endpoint and swap in your key, and most of your code keeps working as is.
Is streaming supported?
Yes. As with the official APIs, set stream to true to receive the response in chunks.
How does billing and top-up work?
Usage is deducted from your balance with no monthly minimum. You can top up with USDT, PayPal and other methods, and review every charge in the dashboard.
How do I get help if something goes wrong?
Open a ticket from your dashboard or email [email protected], and we will reply as soon as we can.
가입하고 $1 무료 크레딧 받기
Reach multiple model providers through one OpenAI-compatible endpoint. Switch models by changing a single parameter, with no rewrites and no juggling of separate accounts or bills.
무료로 시작하기