LLMap
Models /MiniMax M3 /Where to run
Provider guide

Where to run MiniMax M3

12 live offers tracked.

CHEAPEST
OpenRouter
$0.30 / $1.20
per 1M tokens in / out
FASTEST MEASURED
Venice AI
90 tok/s
measured throughput · $0.30 input / $1.20 output per million tokens
GMICloud$0.24 in/1M$0.96 out/1M18 tok/s1Mfp840m agoDeepInfra$0.30 in/1M$1.20 out/1M—524Kfp87h agoNovita AI$0.30 in/1M$1.20 out/1M—1M—7h agoAtlasCloud$0.30 in/1M$1.20 out/1M21 tok/s524Kfp840m agoOpenRouterCHEAPEST$0.30 in/1M$1.20 out/1M—1M—40m agoMinimax$0.30 in/1M$1.20 out/1M47 tok/s524Kfp840m agoDeepInfrazero-retention$0.30 in/1M$1.20 out/1M29 tok/s524Kfp840m agoNovita AIzero-retention$0.30 in/1M$1.20 out/1M38 tok/s1Mfp840m agoMorphzero-retention$0.30 in/1M$1.20 out/1M23 tok/s256K—40m agoTogether AIzero-retention$0.30 in/1M$1.20 out/1M42 tok/s524K—40m agoVenice AIzero-retention$0.30 in/1M$1.20 out/1M90 tok/s524Kfp840m agoParasailzero-retention$0.30 in/1M$1.20 out/1M56 tok/s1Mfp88h ago
Full specs, hardware verdicts and benchmarks on theMiniMax M3 model page →