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

# Mistral AI

# Mistral AI

Mistral AI provides a range of open-weight and proprietary models for text and vision, plus audio transcription via Voxtral, and memory embeddings. OpenClaw supports all three use cases with a single `MISTRAL_API_KEY`.

## Requirements

* A Mistral API key from [console.mistral.ai](https://console.mistral.ai)

## Quickstart

```bash theme={"dark"}
openclaw onboard --auth-choice mistral-api-key
# or non-interactive
openclaw onboard --mistral-api-key "$MISTRAL_API_KEY"
```

Then verify the default model was set:

```bash theme={"dark"}
openclaw models status
```

## Configuration

### Environment variable

```bash theme={"dark"}
export MISTRAL_API_KEY="..."
```

OpenClaw reads `MISTRAL_API_KEY` automatically and enables the `mistral` provider.

### Config snippet (LLM provider)

```json5 theme={"dark"}
{
  env: { MISTRAL_API_KEY: "..." },
  agents: {
    defaults: {
      model: { primary: "mistral/mistral-large-latest" },
    },
  },
}
```

### Provider settings

| Setting                | Value                                    |
| ---------------------- | ---------------------------------------- |
| Provider ID            | `mistral`                                |
| Base URL               | `https://api.mistral.ai/v1`              |
| API                    | OpenAI-compatible (`openai-completions`) |
| Auth env var           | `MISTRAL_API_KEY`                        |
| Default model          | `mistral-large-latest`                   |
| Default context window | 262,144 tokens                           |
| Default max tokens     | 262,144                                  |

## Available models

| Model ID                  | Name                    | Context | Notes           |
| ------------------------- | ----------------------- | ------- | --------------- |
| `mistral-large-latest`    | Mistral Large (latest)  | 262K    | Default; vision |
| `mistral-large-2512`      | Mistral Large 2512      | 262K    | Vision          |
| `mistral-large-2411`      | Mistral Large 2411      | 131K    |                 |
| `mistral-medium-latest`   | Mistral Medium (latest) | 128K    | Vision          |
| `mistral-medium-2508`     | Mistral Medium 2508     | 262K    | Vision          |
| `mistral-medium-2505`     | Mistral Medium 2505     | 131K    | Vision          |
| `mistral-small-latest`    | Mistral Small (latest)  | 128K    | Vision          |
| `mistral-small-2506`      | Mistral Small 2506      | 128K    | Vision          |
| `mistral-nemo`            | Mistral NeMo            | 128K    |                 |
| `ministral-8b-latest`     | Ministral 8B            | 128K    |                 |
| `ministral-3b-latest`     | Ministral 3B            | 128K    |                 |
| `magistral-medium-latest` | Magistral Medium        | 128K    | Reasoning       |
| `magistral-small`         | Magistral Small         | 128K    | Reasoning       |
| `codestral-latest`        | Codestral (latest)      | 256K    | Coding          |
| `devstral-medium-latest`  | Devstral Medium         | 262K    | Coding          |
| `devstral-small-2507`     | Devstral Small 2507     | 128K    | Coding          |
| `pixtral-large-latest`    | Pixtral Large           | 128K    | Vision          |
| `pixtral-12b`             | Pixtral 12B             | 128K    | Vision          |
| `open-mixtral-8x22b`      | Open Mixtral 8×22B      | 64K     |                 |
| `open-mixtral-8x7b`       | Open Mixtral 8×7B       | 32K     |                 |
| `open-mistral-7b`         | Open Mistral 7B         | 8K      |                 |

Use model IDs as `mistral/<model-id>` (example: `mistral/mistral-large-latest`).

## Audio transcription with Voxtral

Mistral's Voxtral model handles audio transcription. Configure it under `tools.media`:

```json5 theme={"dark"}
{
  tools: {
    media: {
      audio: {
        enabled: true,
        models: [{ provider: "mistral", model: "voxtral-mini-latest" }],
      },
    },
  },
}
```

Transcription requests go to `/v1/audio/transcriptions`.

## Memory embeddings

You can use Mistral for memory search embeddings:

```json5 theme={"dark"}
{
  agents: {
    defaults: {
      memorySearch: {
        provider: "mistral",
      },
    },
  },
}
```

The default embedding model is `mistral-embed`. Requests go to `/v1/embeddings`.

## Troubleshooting

**401 Unauthorized**

* Verify your API key is copied in full.
* Re-run onboarding: `openclaw onboard --auth-choice mistral-api-key`.

**Model not found**

* Confirm the model ID matches exactly (case-sensitive).
* Check that your Mistral plan includes the requested model.

**Rate limits**

Add multiple API keys for rotation: `openclaw models auth add-key --provider mistral`.

## Related

* [Model providers](/concepts/model-providers)
* [Models](/concepts/models)
* [Model failover](/concepts/model-failover)
* [Gateway configuration](/gateway/configuration)