Back to models
Mistral logo

Mistral

Mistral Medium 3

Mistral’s mid-tier enterprise model with strong function calling and agent-oriented features.

Overall score
86
mid-tieragentsfunction-calling
Context window
128K tokens
Speed
Balanced
Input pricing
$0.40 / 1M input tokens
Output pricing
$2 / 1M output tokens

Score breakdown

Capability86
Use-case fit86
Cost efficiency90
Speed84
Reliability84
Agent readiness87
Ecosystem83

Scores combine benchmark signals, product experience, and editorial weighting. Use them as a practical guide, not an absolute truth claim.

Best for

CodingAgent automation

Works with

Mistral APIagent toolchainsdocument Q&A

Modalities

textimage

Sources & trust

Officially verified core fields
Official linkSummaryDescriptionModalitiesContext windowPricingPricing pageTool support

Editorial fields such as shortlist guidance, strengths, caveats, and scoring remain clearly separated from official provider data.

Last verified: Apr 9, 2026

Strengths

  • Looks like a practical middle tier for cost-aware teams.
  • Official docs expose agent and structured-output features clearly.

Things to watch

  • Less ecosystem gravity than the biggest model platforms.
  • Teams should test model behavior carefully on their own evals.

Best for