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

# Models

> Every model Opper supports, with EU-hosted options marked.

Opper supports 300+ models from every major provider through one gateway and key. Browse the full, always-current catalog — with pricing, context windows, capabilities, and EU-hosted models marked — at [opper.ai/models](https://opper.ai/models).

<Card title="Browse all models" icon="brain" href="https://opper.ai/models" horizontal>
  The complete model catalog. Copy a model id to use it from the SDK or any drop-in client.
</Card>

Call any model by its provider-prefixed name (`openai/gpt-5.5`, `anthropic/claude-sonnet-4-6`, `gemini/gemini-2.5-pro`) from any SDK. See [Drop-in SDKs](/build/gateway/drop-in-sdks).

## Multimodal models

Beyond text, the catalog includes models that accept images, audio, and video, and models that generate images, speech, and video. Filter the [catalog](https://opper.ai/models) by capability — `vision`, `audio`, `video`, `image gen` — to see what each model supports.

For the modality-specific endpoints, a discovery call returns the usable models and their capabilities at runtime, so you don't have to hardcode a list:

| Endpoint                | Models for                                                                                              |
| ----------------------- | ------------------------------------------------------------------------------------------------------- |
| `GET /v3/images/models` | [Image generation](/build/multimodal/images) (`POST /v3/images`)                                        |
| `GET /v3/audio/models`  | [Speech & transcription](/build/multimodal/audio) (`POST /v3/audio/speech`, `/v3/audio/transcriptions`) |
| `GET /v3/videos/models` | [Video generation](/build/multimodal/video) (`POST /v3/videos`)                                         |

For sending images and PDFs into a text model, see [Vision & PDFs](/build/multimodal/vision-pdfs).

## Aliases and backup chains

An **alias** is a stable name you define in the platform that maps to an *ordered list* of models — a primary plus fallbacks. Call the alias name like any other model, and the gateway tries the first model in the list, falling through to the next if one is unavailable or errors. That ordered list is the **backup chain**.

```text theme={null}
production/main  →  anthropic/claude-sonnet-4-6   (primary)
                →  openai/gpt-5.5                 (fallback)
                →  mistral/mistral-large          (last resort, EU-hosted)
```

Two things this buys you:

* **Resilience.** If the primary provider is down or rate-limited, the call automatically continues down the chain instead of failing.
* **Swap models without touching code.** Point your app at `production/main`, then reorder or repoint the chain in the platform — no deploy.

Set aliases in the platform under **Settings → Models**. The gateway resolves them on every call (a built-in model name still wins; an alias is used when you call its name). To pin your own provider deployments into a chain, register them as [custom models](/capabilities/custom-models) first.

## What's next

<CardGroup cols={2}>
  <Card title="Custom models" icon="plus" href="/capabilities/custom-models">
    Register your own model deployments and API keys, plus aliases.
  </Card>

  <Card title="Integrations" icon="plug" href="/overview/integrations">
    Use Opper as the provider for your editor, agent, or CLI.
  </Card>
</CardGroup>