All AI models · LLM benchmarks · Methodology

Mistral

Mistral Small 3.2 24B Instruct (2506)

Efficient Mistral model for fast chat, extraction, and production assistants

Model facts

Context window
131K tokens
Maximum output
131K tokens
Cheapest paid input
$0.1 per 1M tokens
Cheapest paid output
$0.31 per 1M tokens
Open weights
yes
Providers
4

Capabilities and modalities

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

Observed price history

  • 2026-08-24: $0.1 input / $0.31 output per 1M tokens

API providers

  • OVHcloud AI Endpoints — model id mistral-small-3.2-24b-instruct-2506; $0.1 input / $0.31 output per 1M tokens; provider documentation
  • Cortecs — model id mistral-small-3.2-24b-instruct-2506; $0.1 input / $0.312 output per 1M tokens; provider documentation
  • Scaleway — model id mistral-small-3.2-24b-instruct-2506; $0.15 input / $0.35 output per 1M tokens; provider documentation
  • Berget.AI — model id mistralai/Mistral-Small-3.2-24B-Instruct-2506; $0.33 input / $0.33 output per 1M tokens; provider documentation