Back to models
Mistral logo

Mistral

Mistral Small 3.2

Mistral’s lower-cost small model for efficient production use.

Overall score
82
small-modelbudgetefficient
Context window
128K tokens
Speed
Fast
Input pricing
$0.10 / 1M input tokens
Output pricing
$0.30 / 1M output tokens

Score breakdown

Capability77
Use-case fit81
Cost efficiency96
Speed93
Reliability82
Agent readiness80
Ecosystem82

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

Best for

Agent automation

Works with

Mistral APIclassificationrouting layers

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

  • Strong efficiency tier inside the Mistral stack.
  • Good candidate for routing, extraction, and lighter assistants.

Things to watch

  • Limited headroom for advanced reasoning.
  • Best used with escalation paths to larger models.

Best for