Skip to content

Mistral

Mistral's OpenAI-compatible chat-completions endpoint, selected with LLM_PROVIDER=mistral, used to extract facts from conversations.

Enable it

bash
LLM_PROVIDER=mistral
OPENAI_API_KEY=<mistral-api-key>
OPENAI_BASE_URL=https://api.mistral.ai/v1
OPENAI_LLM_MODEL=mistral-small-latest

Configuration

VariableDefaultDescription
LLM_PROVIDERopenaiSet to mistral.
OPENAI_API_KEY(none)Mistral API key, sent as a bearer token.
OPENAI_BASE_URLhttps://api.openai.com/v1Point at Mistral's endpoint: https://api.mistral.ai/v1.
OPENAI_LLM_MODELgpt-4.1-nanoA Mistral model, e.g. mistral-small-latest.

Notes

  • OpenAI-compatible: the provider reuses the OpenAI request handling and only differs by base URL, key, and model.
  • You must override OPENAI_BASE_URL to Mistral's endpoint; its default points at OpenAI.

The memory layer for AI agents.