Skip to content
Mistral

Mistral Medium 3.1

Mistral Medium 3.1 was the top MT-Bench tier at Mistral's La Plateforme launch (8.6), with multilingual output across English, French, Italian, German, Spanish, and code.

Tool UseVision (Image)
Use with AI GatewayView docs
index.ts
import { streamText } from 'ai'


const result = streamText({
  model: 'mistral/mistral-medium',
  prompt: 'Why is the sky blue?'
})
OverviewAboutProvidersThroughputLatencyUptimeStatusSimilarFAQ

Frequently Asked Questions

  • What was Mistral Medium 3.1's MT-Bench score?

    8.6 on MT-Bench at La Plateforme's launch, per Mistral's announcement.

  • What languages does Mistral Medium 3.1 support?

    English, French, Italian, German, Spanish, and code.

  • How does Mistral Medium 3.1 fit into the La Plateforme lineup?

    Mistral Medium 3.1 sat above Mistral-tiny (efficiency) and Mistral-small (balance) in Mistral's launch lineup and had the highest MT-Bench score of the three.

  • Is Mistral Medium 3.1 a good choice for new projects?

    For new projects, consider more recent models like Mistral Large 3 or Mistral Small. Mistral Medium 3.1 is most relevant for teams with existing integrations.

  • Does Mistral Medium 3.1 support function calling?

    Check the AI Gateway model capabilities documentation for documented capabilities. Function-calling support evolved across Mistral model generations.

  • What is the relationship between Mistral Medium 3.1 and Mistral Small?

    At La Plateforme's launch, Mistral Small occupied the balanced tier between tiny and medium. Mistral Small has since been updated (September 2024) while Medium retains its original profile.

  • How do I access Mistral Medium 3.1 through AI SDK?

    Use Mistral Medium 3.1 through AI Gateway via the AI SDK, Chat Completions API, Responses API, Messages API, or other API formats, from TypeScript or Python.