bot/docs/providers/mistral.md

summary, read_when, title

summary	read_when	title
Use Mistral models and Voxtral transcription with Bot	You want to use Mistral models in Bot You need Mistral API key onboarding and model refs	Mistral

Mistral

Bot supports Mistral for both text/image model routing (mistral/...) and audio transcription via Voxtral in media understanding. Mistral can also be used for memory embeddings (memorySearch.provider = "mistral").

CLI setup

hanzo-bot onboard --auth-choice mistral-api-key
# or non-interactive
hanzo-bot onboard --mistral-api-key "$MISTRAL_API_KEY"

Config snippet (LLM provider)

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

Config snippet (audio transcription with Voxtral)

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

Notes

• Mistral auth uses MISTRAL_API_KEY.
• Provider base URL defaults to https://api.mistral.ai/v1.
• Onboarding default model is mistral/mistral-large-latest.
• Media-understanding default audio model for Mistral is voxtral-mini-latest.
• Media transcription path uses /v1/audio/transcriptions.
• Memory embeddings path uses /v1/embeddings (default model: mistral-embed).