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

# Available Models on Meliai — 60+ Open-Weight Models

> Browse Meliai's catalog of 60+ open-weight models — Llama, Mistral, DeepSeek, Qwen, FLUX, Whisper, and more, all on European infrastructure.

Meliai gives you access to more than 60 open-weight models spanning text generation, image synthesis, audio transcription, embeddings, and reranking — all served exclusively from European infrastructure. Because every model in the catalog is open-weight, your requests are never routed to US- or APAC-based proprietary model APIs. The catalog is continuously updated as new model families are released and validated on the platform.

## Model categories

<CardGroup cols={2}>
  <Card title="Text generation" icon="message" href="/api-reference/chat-completions">
    Chat, instruction-following, and reasoning models from **Llama**, **Mistral**, **DeepSeek**, **Qwen**, **GLM**, and **Kimi**. Suitable for chat completions, agentic pipelines, RAG, and code generation.
  </Card>

  <Card title="Image generation" icon="image" href="/api-reference/images">
    Diffusion models from the **FLUX** family for text-to-image generation via the `/v1/images/generations` endpoint.
  </Card>

  <Card title="Audio / speech" icon="microphone" href="/api-reference/audio">
    **Whisper** for automatic speech recognition and **Voxtral** for advanced audio understanding, available via `/v1/audio/transcriptions`.
  </Card>

  <Card title="Embeddings" icon="brackets-curly" href="/api-reference/embeddings">
    Dense vector embedding models for semantic search, clustering, and retrieval-augmented generation via `/v1/embeddings`.
  </Card>

  <Card title="Reranking" icon="arrow-up-arrow-down" href="/api-reference/rerank">
    Cross-encoder reranking models that score document–query relevance for improved RAG precision via `/v1/rerank`.
  </Card>
</CardGroup>

## Browsing and finding models

### Hub UI

The easiest way to explore the full catalog is the [Meliai Hub](https://meliai.ai/hub). You can filter by category, provider, and routing flavor, and copy model IDs directly into your code.

### List all models via API

Fetch the live catalog programmatically with a `GET /v1/models` request:

```bash theme={null}
curl https://api.meliai.ai/v1/models \
  -H "Authorization: Bearer $MELIAI_API_KEY"
```

The response is an OpenAI-compatible model list object. Each entry includes the model ID, supported endpoints, and metadata about available routing flavors.

### Look up a single model

```bash theme={null}
curl https://api.meliai.ai/v1/models/qwen/qwen3-235b-a22b \
  -H "Authorization: Bearer $MELIAI_API_KEY"
```

## Model IDs

Model IDs follow the format `provider/model-name`, for example:

| Example ID                                 | Family   | Category            |
| ------------------------------------------ | -------- | ------------------- |
| `qwen/qwen3-235b-a22b`                     | Qwen     | Text generation     |
| `meta-llama/llama-3.3-70b-instruct`        | Llama    | Text generation     |
| `mistralai/mistral-small-3.2-24b-instruct` | Mistral  | Text generation     |
| `deepseek/deepseek-r1`                     | DeepSeek | Reasoning           |
| `black-forest-labs/flux-1.1-pro`           | FLUX     | Image generation    |
| `openai/whisper-large-v3`                  | Whisper  | Audio transcription |

Use the exact ID returned by `GET /v1/models` in your request's `model` field.

## Routing suffixes on model IDs

Append a colon-separated flavor suffix to any model ID to control how Meliai selects a provider:

| Suffix   | Effect                         |
| -------- | ------------------------------ |
| *(none)* | Defaults to `balanced` routing |
| `:speed` | Prioritises lowest latency     |
| `:price` | Prioritises lowest cost        |
| `:eco`   | Prioritises greener providers  |
| `:batch` | Optimised for async batch jobs |

For example, `qwen/qwen3-235b-a22b:price` routes to the cheapest available European provider for that model. See [Routing](/concepts/routing) for the full breakdown.

<Note>
  Meliai does not serve proprietary models such as GPT-4o, Claude, or Gemini. For client compatibility, certain well-known OpenAI and Anthropic model name aliases (e.g. `gpt-4o`, `claude-3-5-sonnet`) are mapped to capable open-weight equivalents — your existing client code continues to work while your requests stay on European open-weight infrastructure.
</Note>