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

# Portrix: Unified AI Gateway for 400+ Language Models

> Portrix gives you access to 400+ large language models through a single OpenAI-compatible API. One key, one endpoint, every model.

Welcome to Portrix — the unified AI gateway that gives you instant access to more than 400 large language models through a single endpoint. Whether you're building a chatbot, an autonomous agent, or a cost-optimized inference pipeline, Portrix lets you focus on your product instead of managing a sprawl of provider integrations, API keys, and SDK versions.

<CardGroup cols={2}>
  <Card title="Introduction" icon="book" href="/introduction">
    Learn what Portrix is, why it exists, and how the gateway works.
  </Card>

  <Card title="Quickstart" icon="rocket" href="/quickstart">
    Send your first request in under 5 minutes using any OpenAI-compatible SDK.
  </Card>

  <Card title="API Reference" icon="code" href="/api-reference/overview">
    Explore every endpoint, parameter, and response schema in the full API reference.
  </Card>

  <Card title="Supported Models" icon="layer-group" href="/help/supported-models">
    Browse all 400+ models available through Portrix, from GPT-4o to Gemini to Claude.
  </Card>
</CardGroup>

## How it works

Getting started with Portrix takes three steps — and if you already use the OpenAI SDK, step two is just a one-line change.

<Steps>
  <Step title="Get an API key">
    Sign up at [app.portrix.ai](https://app.portrix.ai), navigate to **Settings → API Keys**, and create your first key. One key unlocks every model in the catalog.
  </Step>

  <Step title="Point your SDK at Portrix">
    Set the base URL of your OpenAI-compatible SDK to `https://api.portrix.ai/v1` and swap in your Portrix API key. No other code changes are required.
  </Step>

  <Step title="Choose any model">
    Pass the model you want in the `model` field using the `provider/model-name` format — for example, `openai/gpt-4o`, `anthropic/claude-3-5-sonnet`, or `google/gemini-2.0-flash`. Portrix handles the rest.
  </Step>
</Steps>

## Key features

<CardGroup cols={3}>
  <Card title="Universal Access" icon="globe">
    Reach 400+ models from OpenAI, Anthropic, Google, Mistral, and dozens more through a single endpoint, with no extra integrations to maintain.
  </Card>

  <Card title="Drop-in Compatible" icon="plug">
    Portrix is fully OpenAI-compatible. Point your existing SDK at `https://api.portrix.ai/v1` and your current code works without modification.
  </Card>

  <Card title="Smart Routing" icon="shuffle">
    Automatic fallbacks, load balancing, and protocol conversion keep your requests flowing even when individual providers experience downtime or rate limits.
  </Card>
</CardGroup>