Mistral Provider: Models, Voxtral Transcription, and Embeddings

The bundled mistral plugin registers four contracts: chat completions, media understanding (Voxtral batch transcription), realtime STT for Voice Call (Voxtral Realtime), and memory embeddings (mistral-embed).

Getting started

Get your API key

Generate an API key in the Mistral Console.

Run onboarding

openclaw onboard --auth-choice mistral-api-key

Or supply the key directly:

openclaw onboard --mistral-api-key "$MISTRAL_API_KEY"

Set a default model

{
  env: { MISTRAL_API_KEY: "sk-..." },
  agents: { defaults: { model: { primary: "mistral/mistral-large-latest" } } },
}

Verify the model is available

openclaw models list --provider mistral

Built-in LLM catalog

Browse the bundled catalog row before changing config:

openclaw models list --all --provider mistral --plain

Smoke-test a model without starting the Gateway:

openclaw infer model run --local \
  --model mistral/mistral-medium-3-5 \
  --prompt "Reply with exactly: mistral-ok" \
  --json

Audio transcription (Voxtral)

Use Voxtral for batch audio transcription through the media understanding pipeline:

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

Tip

The media transcription path uses /v1/audio/transcriptions. The default audio model for Mistral is voxtral-mini-latest.

Voice Call streaming STT

The bundled mistral plugin registers Voxtral Realtime as a Voice Call streaming STT provider.

{
  plugins: {
    entries: {
      "voice-call": {
        config: {
          streaming: {
            enabled: true,
            provider: "mistral",
            providers: {
              mistral: {
                apiKey: "${MISTRAL_API_KEY}",
                targetStreamingDelayMs: 800,
              },
            },
          },
        },
      },
    },
  },
}

Note

OpenClaw defaults Mistral realtime STT to pcm_mulaw at 8 kHz so Voice Call can forward Twilio media frames directly. Use encoding: "pcm_s16le" and a matching sampleRate only if your upstream stream is already raw PCM.

Advanced configuration

Adjustable reasoning

mistral/mistral-small-latest, mistral/mistral-small-2603, and mistral/mistral-medium-3-5 support adjustable reasoning on the Chat Completions API via reasoning_effort (none minimizes extra thinking in the output; high surfaces full thinking traces before the final answer).

OpenClaw maps the session thinking level to Mistral's API:

Warning

Avoid combining Medium 3.5 reasoning mode with temperature: 0; the Mistral HTTP API has been reported to reject reasoning_effort="high" plus temperature: 0 with a 400 response. Leave temperature unset, or turn thinking off/minimal so OpenClaw sends reasoning_effort: "none" before you set a low temperature.

Example model-scoped config for Medium 3.5 reasoning:

{
  agents: {
    defaults: {
      model: { primary: "mistral/mistral-medium-3-5" },
      models: {
        "mistral/mistral-medium-3-5": {
          params: { thinking: "high" },
        },
      },
    },
  },
}

Note

Other bundled Mistral catalog models do not use this parameter. Keep using magistral-* models when you want Mistral's native reasoning-first behavior.

Memory embeddings

Mistral can serve memory embeddings via /v1/embeddings (default model: mistral-embed):

{
  memory: {
    search: { provider: "mistral" },
  },
}

Auth and base URL

• Mistral auth uses MISTRAL_API_KEY (Bearer header).
• Provider base URL defaults to https://api.mistral.ai/v1 and accepts the standard OpenAI-compatible chat-completions request shape.
• Onboarding default model is mistral/mistral-large-latest.
• Override the base URL under models.providers.mistral.baseUrl only when Mistral explicitly publishes a regional endpoint you need.

Related

• Model selection, Choosing providers, model refs, and failover behavior.

• Media understanding, Audio transcription setup and provider selection.