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

# Welcome to OpenPAI

> A unified LLM API gateway — one API key to reach OpenAI, Claude, Gemini, Midjourney, Suno and dozens of other model providers

<img className="block dark:hidden" src="https://mintcdn.com/op-40ebb09d/mqaqBS-i5c2tOWjh/images/hero-light.png?fit=max&auto=format&n=mqaqBS-i5c2tOWjh&q=85&s=deb1261db492ca6574507da2f48d7091" alt="OpenPAI hero" width="2064" height="1104" data-path="images/hero-light.png" />

<img className="hidden dark:block" src="https://mintcdn.com/op-40ebb09d/mqaqBS-i5c2tOWjh/images/hero-dark.png?fit=max&auto=format&n=mqaqBS-i5c2tOWjh&q=85&s=9e1af92c32bef31782fd89d4c08773d5" alt="OpenPAI hero" width="2064" height="1104" data-path="images/hero-dark.png" />

## What is OpenPAI

**OpenPAI** ([openp.ai](https://openp.ai)) is an LLM API aggregation gateway built for developers and enterprises.
Through a single, OpenAI-compatible interface you can seamlessly call all the major model providers — without registering separate accounts, managing multiple keys, or handling billing for each vendor.

<CardGroup cols={2}>
  <Card title="Unified interface" icon="plug">
    Fully compatible with the OpenAI SDK, with native support for the Claude `/v1/messages` and Google Gemini formats.
  </Card>

  <Card title="Hundreds of models" icon="layer-group">
    OpenAI, Anthropic, Google, DeepSeek, Qwen, Midjourney, Suno, Cohere, Jina and more, continuously added.
  </Card>

  <Card title="Pay as you go" icon="coins">
    Transparent token-based billing, lower rates on cache hits, with top-ups and quota management.
  </Card>

  <Card title="High availability" icon="shield-halved">
    Weighted multi-channel routing + automatic retries, so a single upstream outage won't break your service.
  </Card>
</CardGroup>

## Quickstart

Just three steps to send your first request in five minutes:

<Steps>
  <Step title="Sign up and get an API key">
    Register at [openp.ai](https://openp.ai), then create an API key starting with `sk-` on the **Tokens** page of the console.
  </Step>

  <Step title="Pick a model">
    Browse available models on the **Models** page of the console, or see the [Models overview](/en/models/overview) to choose the right one.
  </Step>

  <Step title="Send your first request">
    Point your OpenAI SDK `base_url` at `https://openp.ai/v1` and replace the API key with your OpenPAI key.
  </Step>
</Steps>

```bash theme={null}
curl https://openp.ai/v1/chat/completions \
  -H "Authorization: Bearer $OPENPAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-3.1-pro-preview",
    "messages": [{"role": "user", "content": "Hello"}]
  }'
```

## Explore the docs

<CardGroup cols={2}>
  <Card title="Quickstart guide" icon="rocket" href="/en/quickstart">
    The full flow from sign-up to your first request.
  </Card>

  <Card title="Supported models" icon="cubes" href="/en/models/overview">
    See every available model, its billing multiplier, and context window.
  </Card>

  <Card title="API reference" icon="code" href="/en/api-reference/introduction">
    Request/response fields, error codes and examples for every endpoint.
  </Card>

  <Card title="Client integrations" icon="puzzle-piece" href="/en/integrations/overview">
    Connect tools like Cherry Studio, LobeChat, Cursor and Dify.
  </Card>
</CardGroup>

## Three native protocols

Beyond full OpenAI compatibility, OpenPAI also exposes native Claude and Gemini protocol endpoints, so you can switch upstreams without rewriting your application:

<CardGroup cols={3}>
  <Card title="OpenAI-compatible" icon="o" href="/en/api-reference/openai/chat-completions">
    `POST /v1/chat/completions`
    `Authorization: Bearer sk-...`
  </Card>

  <Card title="Claude Messages" icon="a" href="/en/api-reference/anthropic/messages">
    `POST /v1/messages`
    `x-api-key: sk-...`
  </Card>

  <Card title="Gemini native" icon="g" href="/en/api-reference/gemini/generate-content">
    `POST /v1beta/models/{model}:generateContent`
    `x-goog-api-key: sk-...`
  </Card>
</CardGroup>

## Need help?

<Card title="FAQ" icon="circle-question" href="/en/support/faq" horizontal>
  Answers to common questions about top-ups, models, billing and errors.
</Card>