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

# AI Gateway

> AI Gateway is a standalone LLM routing layer. Connect any provider, route requests across 300+ models, and track cost and latency, no additional tooling required.

## What is AI Gateway?

**AI Gateway** is a standalone product for teams and developers who need a production-grade LLM routing layer.

Point any OpenAI-compatible client at the **AI Gateway** endpoint and immediately gain:

<CardGroup cols={3}>
  <Card title="Model routing" icon="arrow-right-arrow-left">
    Route requests to 300+ models across 20+ providers through a single unified endpoint. Switch models without touching application code.
  </Card>

  <Card title="Reliability" icon="shield-check">
    Automatic retries, fallbacks, load balancing, and timeouts. Traffic keeps flowing when a provider goes down.
  </Card>

  <Card title="Cost and activity tracking" icon="chart-bar">
    Every request is logged in the **Overview** page with model, latency, token counts, and cost. No extra instrumentation needed.
  </Card>
</CardGroup>

## Who is it for?

**AI Gateway** is designed for:

* **Developers and technical teams** who want a drop-in routing layer on top of their existing LLM calls
* **Companies focused on routing and cost control** who do not need prompt management, agent orchestration, or experiment tooling
* **Teams already on a framework** (LangChain, Vercel AI, OpenAI Agents SDK, etc.) who want provider flexibility with a single base URL change

## Get started

<CardGroup cols={2}>
  <Card title="Quick Start" icon="rocket" href="/docs/ai-gateway/get-started/quickstart">
    Connect a provider, get an API key, and route the first request in under five minutes.
  </Card>

  <Card title="Supported Models" icon="list" href="/docs/ai-gateway/supported-models">
    Browse the full model catalog across OpenAI, Anthropic, Google, AWS, Azure, and more.
  </Card>
</CardGroup>

## Key capabilities

<CardGroup cols={3}>
  <Card title="Auto Router" icon="wand-magic-sparkles" href="/docs/ai-gateway/auto-router">
    Let **AI Gateway** pick the best model for each request based on quality, cost, and latency targets.
  </Card>

  <Card title="Multimodal" icon="image" href="/docs/ai-gateway/features/multimodal">
    Send images, PDFs, audio, and files through the same unified endpoint. No API changes needed.
  </Card>

  <Card title="Guardrails" icon="lock" href="/docs/ai-gateway/configuration/guardrail-rules">
    Attach LLM-as-a-judge or Python guardrails to guardrail rules for input and output filtering.
  </Card>

  <Card title="Fallbacks and retries" icon="shuffle" href="/docs/ai-gateway/features/retries">
    Define ordered fallback chains so requests automatically retry on a backup model.
  </Card>

  <Card title="Identities" icon="user-tag" href="/docs/ai-gateway/identities">
    Attribute requests to a specific user or tenant for per-identity cost and usage visibility.
  </Card>

  <Card title="Load balancing" icon="scale-balanced" href="/docs/ai-gateway/features/load-balancing">
    Distribute traffic across multiple provider configurations or API keys to stay within rate limits.
  </Card>
</CardGroup>

## How it works

Send any OpenAI-compatible request to the **AI Gateway** endpoint using a provider-prefixed model ID (e.g. `openai/gpt-4o`). The gateway resolves the provider, applies policies and guardrails, routes to the model, and logs the result in **Activity**. See the [Quick Start](/docs/ai-gateway/get-started/quickstart) for a step-by-step walkthrough.