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

# LLM Gateway

> Access multiple LLM providers through a single OpenAI-compatible API

# LLM Gateway

Access Claude, GPT, Gemini, Llama, and other models through a single, unified API. The ATXP LLM Gateway provides OpenAI-compatible endpoints that work with any client supporting the OpenAI chat-completions interface.

## Why use the LLM Gateway?

* **Unified access**: Use multiple LLM providers through a single endpoint
* **No vendor lock-in**: Switch between models without changing your code
* **Pay-per-use**: Only pay for tokens you use, with transparent pricing
* **OpenAI compatibility**: Works with any OpenAI-compatible client or SDK
* **Streaming support**: Full support for chat completions and streaming

## Quick example

```bash theme={null}
curl -X POST "https://llm.atxp.ai/v1/chat/completions" \
  -H "Authorization: Bearer $ATXP_CONNECTION" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4.1",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'
```

## Get started

<CardGroup cols={3}>
  <Card title="Code integration" href="/agents/llm-gateway/code" icon="code">
    Integrate the LLM Gateway using JavaScript, Python, or HTTP with OpenAI-compatible SDKs.
  </Card>

  <Card title="Desktop apps" href="/agents/llm-gateway/desktop" icon="laptop">
    Configure apps like Goose to use the LLM Gateway.
  </Card>

  <Card title="Available models" href="/agents/llm-gateway/models" icon="list">
    Browse available models and current pricing.
  </Card>
</CardGroup>