Skip to main content
A2Agent gives you a single API key that unlocks every supported Chinese LLM through an OpenAI-compatible endpoint. This guide walks you from account creation to a live chat completion request in four steps — no provider-specific setup required.
1

Sign Up for an Account

Go to https://a2agent.me/register and create a free account. A2Agent credits your new account with free trial credits automatically — no payment method needed to get started. You can use those credits to explore models and test latency before adding funds.
2

Create an API Key

  • Sign in at https://a2agent.me/login.
  • Open the “API Keys” page from the console navigation.
  • Click “Create Key.”
  • Enter a name, select one or more groups, and then confirm. Selecting all groups is recommended. Image
  • After the key is created, copy its value.
Your base URL for all requests is:
You will pass this base URL to any client that requires a custom endpoint.
3

Make Your First Request

After obtaining your API key, run one of the following commands in your terminal. Replace YOUR_API_KEY with the key you copied earlier.Image

OpenAI-Compatible API

A successful response returns a JSON object with a choices array containing the model’s reply. You can swap "deepseek-v4-pro" for any model listed on the Models Page without changing anything else.

OpenAI SDK

If you prefer to use the Python or Node.js OpenAI SDK, only the API key and base URL need to be configured.

Python

Node.js

Anthropic-Compatible API

A2Agent also supports the Anthropic API format. Send requests to the Anthropic messages endpoint:
Replace deepseek-v4-pro with any compatible model listed on the Models Page .
A2Agent uses Bearer Token authentication for Anthropic-compatible requests. When using an Anthropic SDK, configure it to send the Authorization: Bearer YOUR_API_KEY header. Depending on the SDK version, this may require the auth_token or authToken option instead of the default api_key or apiKey option.
4

Check Your Usage

Log in at https://a2agent.me/login and navigate to the Usage section of the console to see a breakdown of requests, token counts, and spend by model. Your remaining balance is displayed at the top of the page.
A2Agent is fully compatible with the OpenAI Chat Completions protocol. Any SDK or tool that lets you configure a custom base URL — including the official openai Python and Node.js libraries — works with A2Agent out of the box. Set base_url (or OPENAI_BASE_URL) to https://api.a2agent.me/v1 and point api_key at your A2Agent key.

Next Steps

AI Coding Clients

Configure Claude Code, Cursor, Codex, and other AI coding tools to use A2Agent as their backend.

All Models

Browse the full model list — GLM, Kimi, DeepSeek, Qwen, and MiniMax — with pricing and context-window details.