All AI models · LLM benchmarks · Methodology

Mistral

Mistral Small 4

Fast Mistral production model for chat, extraction, and cost-sensitive agents

Model facts

Context window
256K tokens
Maximum output
256K tokens
Cheapest paid input
$0.143 per 1M tokens
Cheapest paid output
$0.568 per 1M tokens
Open weights
yes
Providers
13

Capabilities and modalities

reasoning, tool calling, structured output, attachments, temperature control, open weights, text, image.

Artificial Analysis benchmarks

Compare this model on the full LLM benchmark leaderboard.

ConfigurationAAICodingMathOutput tokens/s
Reasoning19.726.6not measured152.8
Non-reasoning12.3not measurednot measured144.1

Observed price history

  • 2026-08-24: $0.143 input / $0.568 output per 1M tokens

API providers

  • Cortecs — model id mistral-small-2603; $0.143 input / $0.568 output per 1M tokens; provider documentation
  • Eden AI — model id mistral/mistral-small-2603; $0.15 input / $0.6 output per 1M tokens; provider documentation
  • EmpirioLabs AI — model id mistral-small-4; $0.15 input / $0.6 output per 1M tokens; provider documentation
  • Kilo Gateway — model id mistralai/mistral-small-2603; $0.15 input / $0.6 output per 1M tokens; provider documentation
  • Mistral — model id mistral-small-2603; $0.15 input / $0.6 output per 1M tokens; provider documentation
  • OpenRouter — model id mistralai/mistral-small-2603; $0.15 input / $0.6 output per 1M tokens; provider documentation
  • Opper — model id mistral/mistral-small-2603; $0.15 input / $0.6 output per 1M tokens; provider documentation
  • Pioneer — model id mistralai/Mistral-Small-4-119B-2603; $0.15 input / $0.6 output per 1M tokens; provider documentation
  • AKI.IO — model id mistral4-119b; $0.2 input / $0.6 output per 1M tokens; provider documentation
  • Requesty — model id mistral-small-2603; $0.165 input / $0.66 output per 1M tokens; provider documentation
  • Requesty (EU) — model id mistral-small-2603@eu; $0.165 input / $0.66 output per 1M tokens; provider documentation
  • Venice AI — model id mistral-small-2603; $0.188 input / $0.75 output per 1M tokens; provider documentation
  • Infomaniak — model id mistralai/Mistral-Small-4-119B-2603; $0.25 input / $0.93 output per 1M tokens; provider documentation