Skip to main content

Models / Mistral

Model · Mistral

Mistral

Efficient European models, with availability governed by the platform privacy policy.

Mistral builds lean, capable models that get a lot done per dollar. They are a natural fit for the synthesis step in a weave, where the job is to read several answers and combine them well.

The lineup

ModelBest forPlan
Mistral Medium 3.1Efficient synthesis when a privacy-compatible route is available.Paid
Mistral Large 2512Higher-capability Mistral analysis and synthesis.Paid

What it is good for

  • Synthesizing and judging several model answers
  • Efficient, cost-effective general work
  • A European-built perspective in the mix

In a weave

Mistral can serve as a distinct European voice in a paid weave when an endpoint compatible with the platform privacy policy is available.

These Mistral versions are currently hidden because no OpenRouter endpoint satisfies LLMWeave’s account-level privacy policy. The privacy policy is not relaxed to make a model route.

Common questions

What does the judge model do?

In a weave, the judge reads the answers from the responding models and merges or ranks them into one result. Nemotron 3 Super is the current included default for that role.

More models

Try Mistral in a weave

Run it next to other models on your own task. Free to start, no card.

Get started