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

# LLM Catalog

> Every AI provider and model your organisation can reach, in one governed place.

The LLM catalog is the Model Catalog: a single pane over every AI provider and model in your organisation. It replaces raw API keys and scattered environment variables with governed Provider Integrations, so you can see what is available, who can use it, and what it costs.

<CardGroup cols={2}>
  <Card title="Model Catalog" icon="microchip-ai" href="/docs/aigw/product/model-catalog">
    Providers, models, and the `@provider/model` slug you use in code
  </Card>

  <Card title="Gateway Models" icon="server" href="/docs/aigw/product/model-catalog/gateway-models">
    The models the AI Gateway serves and how they are named
  </Card>
</CardGroup>

## Getting models into the catalog

An **Integration** connects the AI Gateway to a provider — OpenAI, Anthropic, Bedrock, or a self-hosted endpoint. Creating one is what puts that provider's models in the catalog, and it is also where you decide which workspaces see them and what they are allowed to spend.

<CardGroup cols={2}>
  <Card title="LLM Integrations" icon="plug" href="/docs/aigw/product/model-catalog/integrations">
    Create an Integration and connect a provider
  </Card>

  <Card title="Custom Models" icon="wrench" href="/docs/aigw/product/model-catalog/custom-models">
    Add models the AI Gateway does not know about yet
  </Card>
</CardGroup>

## Tuning what the catalog reports

Pricing and model metadata come from the provider by default. Where your contract differs, or where a model behaves differently in your deployment, override it.

<CardGroup cols={2}>
  <Card title="Pricing Adjustments" icon="tag" href="/docs/aigw/product/model-catalog/pricing-adjustments">
    Apply your negotiated rates so cost reporting is accurate
  </Card>

  <Card title="Model Overrides" icon="sliders" href="/docs/aigw/product/model-catalog/model-overrides">
    Change token limits, capabilities, and other model details
  </Card>
</CardGroup>

## Related

* [Workspace Provisioning](/docs/aigw/product/model-catalog/workspace-provisioning) — which workspaces get an Integration
* [Model Provisioning](/docs/aigw/product/model-catalog/model-provisioning) — which models within it they may call
* [Budget Limits](/docs/aigw/product/policies/budget-limits) and [Rate Limits](/docs/aigw/product/policies/rate-limits) — the guardrails on that access
* [Bedrock with an assumed role](/docs/aigw/product/model-catalog/connect-bedrock-with-amazon-assumed-role) — AWS-specific setup


## Related topics

- [Bring Your Own LLM](/docs/aigw/integrations/llms/byollm.md)
- [Model Catalog](/docs/aigw/product/model-catalog.md)
- [Agent Catalog](/docs/aigw/product/catalogs/agents.md)
- [MCP Catalog](/docs/aigw/product/catalogs/mcps.md)
- [Deepbricks](/docs/aigw/integrations/llms/deepbricks.md)