Skip to content

Mistral Small 3.2 24B Instruct 2506 vs Mistral Medium 3.5 128B

Mistral Small 3.2 24B Instruct 2506 is cheaper on output tokens, while Mistral Medium 3.5 128B offers a larger context window. Choose Mistral Small 3.2 24B Instruct 2506 or Mistral Medium 3.5 128B based on the trade-off between cost, context, and the benchmarks that matter for your use case.

SpecMistral Small 3.2 24B Instruct 2506Mistral Medium 3.5 128B
ProviderBerget.AIBerget.AI
Input / 1M tokens$0.33$1.65
Output / 1M tokens$0.33$5.50
Context window32K262K
Parameters
Open weightsYesYes
ReleasedOct 2025Apr 2026

FAQ

Pricing is indicative — confirm with the provider before production use. Highlighted values indicate the better figure for that row.