> ## Documentation Index
> Fetch the complete documentation index at: https://docs.a2agent.me/llms.txt
> Use this file to discover all available pages before exploring further.

# A2Agent: One API Key for All Affordable LLM 

> A2Agent is an API gateway for GLM, Kimi, DeepSeek, Qwen, and MiniMax — one key, OpenAI-compatible, at a fraction of official pricing. Free trial credits included.

A2Agent is an API gateway that gives developers outside mainland China a single API key to access all major Chinese large language models — GLM, Kimi, DeepSeek, Qwen, and MiniMax — through a unified, OpenAI-compatible interface. Instead of juggling separate accounts, billing portals, and authentication schemes for every provider, you point your existing OpenAI or Anthropic client at `https://api.a2agent.me,`drop in your A2Agent key and start calling any supported model immediately.

## Key Features

<CardGroup cols={2}>
  <Card title="All Major Frontier Models" icon="layer-group">
    Access GLM, Kimi, DeepSeek, Qwen, and MiniMax through one unified endpoint. Switch between models with a single parameter change — no extra accounts or keys required.
  </Card>

  <Card title="OpenAI & Anthropic Compatible" icon="plug">
    The API speaks the OpenAI Chat Completions protocol and supports the Anthropic message format. Any client that accepts a custom base URL works out of the box.
  </Card>

  <Card title="Pay As You Go" icon="wallet">
    No monthly subscription and no seat fees. Your balance never expires, so you only pay for what you use. Top up anytime via USDT, Stripe, PayPal, or an overseas card.
  </Card>

  <Card title="Private & Secure" icon="shield-halved">
    A2Agent does not persist your request payloads. Your prompts and completions pass through and are never stored on our infrastructure.
  </Card>
</CardGroup>

## How It Works

When you send a request to `https://api.a2agent.me`, A2Agent authenticates your key, routes the request to the upstream model provider you specified, and streams the response back to you — all in the same shape your client already expects. You get access to deeply discounted wholesale pricing across all supported providers, billed to a single prepaid balance.

New accounts receive free trial credits on signup so you can explore models and measure latency before adding funds.

## Quick Links

<CardGroup cols={2}>
  <Card title="Quickstart" icon="rocket" href="/quickstart">
    Sign up, create a key, and send your first request in under five minutes.
  </Card>

  <Card title="API Reference" icon="code" href="/api-reference/overview">
    Explore the full Chat Completions and Anthropic-compatible endpoints.
  </Card>

  <Card title="Models" icon="microchip" href="/models/overview">
    Browse all supported models with context windows, pricing, and capability notes.
  </Card>

  <Card title="Billing" icon="credit-card" href="/account/billing">
    Add credits, view invoices, and manage your payment methods.
  </Card>
</CardGroup>