Back to models

Mistral Small

Cost-efficient reasoning model for low-latency workloads

Context window32,000 tokens
Max output tokens8,192 tokens

Pricing

TypeInputOutput
Standard$0.10 / 1M tokens$0.30 / 1M tokens

Parameters

ParameterDefaultRange
Max stop sequences0

Supported features

Capabilities

  • Streaming
  • Function Calling
  • Structured Output
  • Json Mode
  • System Prompt

Endpoints

  • Chat Completions

Use cases

  • text-chat
  • function-calling

Model specifications

Model IDmistral-small-latest
FamilyMistral Small
Access typeClosed
Input modalitiestext
Output modalitiestext
Last updatedDecember 31, 2025