Skip to content
EverrunsEverruns
Everruns Cloud is open in early access. Run agents without operating the platform.

Mistral AI

Everruns runs agents on Mistral AI models through La Plateforme’s Chat Completions API: Mistral Large 4, Mistral Medium, Mistral Small, Ministral and Codestral, with the same agent, prompt, and capabilities you run on any other provider.

What you get

Section titled “What you get”
  • Mistral Large 4: Mistral’s 1T-parameter multimodal model with a 512K context window, tool calling, image input, structured output, and reasoning.
  • Reasoning on demand: Mistral Large 4’s thinking is on or off. Set the agent’s reasoning effort to On (high) to stream its reasoning separately from the answer; the default, Off, answers directly.
  • Automatic model discovery: Mistral’s /models endpoint advertises chat, tool calling, vision and reasoning support per model, which Everruns turns into capability profiles on sync. Aliases are folded into one entry per model, and models Mistral has scheduled for retirement are skipped.
  • Host-gated discovery: model sync runs only against api.mistral.ai, so a custom proxy base URL is never probed.

Configure in Everruns

Section titled “Configure in Everruns”

The Mistral AI provider is behind the mistral feature flag, which is off by default. A self-hosted deployment turns it on by setting FEATURE_MISTRAL=prod (on for every organization) or adoption (organizations opt in). Until then, Mistral AI does not appear in the provider picker and the API refuses to create a mistral provider. Mistral models remain reachable through OpenRouter either way.

  1. Go to Settings → Providers and click Add provider.
  2. Choose Mistral AI.
  3. Paste your API key. Create one in Mistral Studio.
  4. Save. Everruns discovers the available models and their capabilities.

You can optionally set a base URL to route through a proxy; leave it blank to use https://api.mistral.ai/v1.

Models

Section titled “Models”

Use Mistral’s model ids, for example mistral-large-4 (alias mistral-large-4-0), mistral-medium-latest, or codestral-latest. Mistral Large 4 is also reachable through OpenRouter as mistralai/mistral-large-4-0, with the same profile.

Framework

Section titled “Framework”
// Reads MISTRAL_API_KEY, and MISTRAL_BASE_URL when set.
let provider = everruns_drivers::mistral::from_env("mistral")?;

Enable the mistral feature of everruns-drivers.

Section titled “Links”