Skip to content

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

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 Medium 3.5 128B or Mistral Small 3.2 24B Instruct 2506 based on the trade-off between cost, context, and the benchmarks that matter for your use case.

SpecMistral Medium 3.5 128BMistral Small 3.2 24B Instruct 2506
ProviderBerget.AIBerget.AI
Input / 1M tokens$1.65$0.33
Output / 1M tokens$5.50$0.33
Context window262K32K
Parameters
Open weightsYesYes
ReleasedApr 2026Oct 2025

FAQ

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