Skip to content

Gemma 4 31B Instruct vs Mistral Small 3.2 24B Instruct 2506

Mistral Small 3.2 24B Instruct 2506 is cheaper on output tokens, while Gemma 4 31B Instruct offers a larger context window. Choose Gemma 4 31B Instruct 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.

SpecGemma 4 31B InstructMistral Small 3.2 24B Instruct 2506
ProviderBerget.AIBerget.AI
Input / 1M tokens$0.28$0.33
Output / 1M tokens$0.55$0.33
Context window128K32K
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.