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

# LLM Gateway Overview

> Use HYRE as the LLM provider inside your own product — one OpenAI-compatible endpoint, 20+ models, crypto-native billing.

The HYRE LLM Gateway is an OpenAI-compatible inference API. If your app, agent, or platform already talks to OpenAI, you can switch to HYRE by changing two lines: the base URL and the API key.

```
Base URL   https://gw.hyreagent.fun/api/inference/v1
Auth       Authorization: Bearer hyre_gw_...
```

<Warning>
  Gateway API keys are **not self-serve for integrations**. Access is granted to selected partners — [request an API key](/gateway/get-access) before you start building.
</Warning>

## Why route through HYRE

<CardGroup cols={2}>
  <Card title="One key, 20+ models" icon="layer-group">
    Open-weight models (DeepSeek, GLM, Llama, Qwen, Kimi, MiniMax) plus frontier models (Claude, GPT, Gemini, Grok) behind a single endpoint.
  </Card>

  <Card title="Drop-in OpenAI compatibility" icon="plug">
    `/chat/completions` and `/models` follow the OpenAI schema — the OpenAI SDK, LangChain, and the Vercel AI SDK work unchanged.
  </Card>

  <Card title="Crypto-native billing" icon="coins">
    Prepaid USDC credits, per-call x402 micropayments, or partner invoicing. No card on file, no subscription.
  </Card>

  <Card title="Streaming + tool calls" icon="bolt">
    SSE streaming with usage reporting, function calling (`tools` / `tool_choice`), and `response_format` all pass through.
  </Card>
</CardGroup>

## How access works

<Steps>
  <Step title="Request a key">
    Tell us who you are and what you're building — see [Get Access](/gateway/get-access). Access is selective; we issue keys manually.
  </Step>

  <Step title="Receive your key">
    You get a `hyre_gw_*` key with agreed daily caps and billing terms (prepaid credits or partner invoicing).
  </Step>

  <Step title="Point your app at the gateway">
    Set the base URL and key in your OpenAI client. Done — see the [Quickstart](/gateway/quickstart).
  </Step>
</Steps>

## Endpoints

| Method | Path                                 | Auth            | Description                                                    |
| ------ | ------------------------------------ | --------------- | -------------------------------------------------------------- |
| `POST` | `/api/inference/v1/chat/completions` | API key or x402 | OpenAI-compatible chat completions (streaming + non-streaming) |
| `GET`  | `/api/inference/v1/models`           | none            | Public model catalog with live pricing and free-tier flags     |

<Note>
  No API key? The gateway also accepts per-call [x402 payments](/payment/x402-protocol) (Solana USDC or BSC USD1/USDT/USDC) — a `402` challenge is returned and your wallet or agent pays per request. Keys are the right choice for production integrations; x402 is great for agents paying as they go.
</Note>