Mistral Provider: Models, Voxtral Transcription, and Embeddings

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

Getting started

Install the plugin

openclaw plugins install @openclaw/mistral-provider
openclaw gateway restart

Get your API key

Head to the Mistral Console to generate an API key.

Run onboarding

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

Alternatively, supply the key directly:

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

Set a default model

{
  env: { vars: { 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

Before changing config, inspect the plugin catalog row:

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

Test a model without launching the Gateway:

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

Audio transcription (Voxtral)

Batch audio transcription via the media understanding pipeline is handled with Voxtral:

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

Tip

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

Voice Call streaming STT

Voxtral Realtime is registered as a Voice Call streaming STT provider by the mistral plugin.

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

Note

OpenClaw sets Mistral realtime STT to pcm_mulaw at 8 kHz by default, which lets Voice Call pass Twilio media frames straight through. Only apply encoding: "pcm_s16le" together with a matching sampleRate when 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 work with adjustable reasoning on the Chat Completions API through reasoning_effort (none cuts down on extra thinking in responses; high shows complete reasoning traces before the final answer).

The session thinking level is translated by OpenClaw into Mistral's API:

Warning

Do not pair Medium 3.5 reasoning mode with temperature: 0; the Mistral HTTP API reportedly returns a 400 error when reasoning_effort="high" and temperature: 0 are combined. Keep temperature unset, or set thinking to off/minimal so OpenClaw sends reasoning_effort: "none" before you apply a low temperature.

Here is an example model-scoped configuration for Medium 3.5 reasoning:

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

Note

This parameter is not used by other Mistral catalog models. Mistral's native Magistral models are deprecated; for current API models, use adjustable reasoning on Mistral Small 4 or Mistral Medium 3.5.

Memory embeddings

Memory embeddings can be served by Mistral through /v1/embeddings (default model: mistral-embed):

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

Auth and base URL

• Authentication for Mistral relies on MISTRAL_API_KEY (Bearer header).
• The provider base URL defaults to https://api.mistral.ai/v1 and supports the standard OpenAI-compatible chat-completions request format.
• The onboarding default model is mistral/mistral-large-latest.
• Only override the base URL under models.providers.mistral.baseUrl when Mistral explicitly publishes a regional endpoint you require.

Related

• Model selection, How to choose providers, model refs, and failover behavior.

• Media understanding, Audio transcription setup and provider selection.