LLMap
Models /Mistral Small 3.2 24B /Where to run
Provider guide

Where to run Mistral Small 3.2 24B

6 live offers tracked.

CHEAPEST
OpenRouter
$0.075 / $0.20
per 1M tokens in / out
FASTEST MEASURED
Mistral AI
102 tok/s
measured throughput · $0.10 input / $0.30 output per million tokens
OpenRouterCHEAPEST$0.075 in/1M$0.20 out/1M—256K—16m agoDeepInfra$0.075 in/1M$0.20 out/1M—128Kfp86h agoMistral AI$0.10 in/1M$0.30 out/1M102 tok/s131K—4d agoDeepInfrazero-retention$0.075 in/1M$0.20 out/1M28 tok/s128Kfp816m agoVenice AIzero-retention$0.094 in/1M$0.25 out/1M21 tok/s256Kfp816m agoParasailzero-retention$0.090 in/1M$0.30 out/1M14 tok/s131Kbf1616m ago
Full specs, hardware verdicts and benchmarks on theMistral Small 3.2 24B model page →