← Back to models
↗↗↗
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.
Mistral official
Official site · Tier 5 · Apr 9, 2026
Official link
Mistral Medium 3 docs
Official docs · Tier 5 · Apr 9, 2026
SummaryDescriptionModalitiesContext windowPricingPricing pageTool support
Mistral Medium 3 VerdictLens review
Manual review · Tier 3 · Apr 9, 2026
Best-fit guidanceWorks-with guidanceStrengthsCaveatsOverall scoreScore breakdown
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.