LLMap
Models /MiniMax M2.5 /Where to run
Provider guide

Where to run MiniMax M2.5

17 live offers tracked — output prices vary 2.7× between the cheapest and most expensive host, so the provider choice matters as much as the model choice.

CHEAPEST
OpenRouter
$0.15 / $0.90
per 1M tokens in / out
FASTEST MEASURED
Friendli
90 tok/s
measured throughput · $0.30 input / $1.20 output per million tokens
OpenRouterCHEAPEST$0.15 in/1M$0.90 out/1M—205K—15m agoStreamLake$0.27 in/1M$1.08 out/1M80 tok/s200K—15m agoAtlasCloud$0.29 in/1M$1.20 out/1M48 tok/s197Kfp815m agoChutes$0.15 in/1M$1.20 out/1M24 tok/s197Kfp86d agoFriendli$0.30 in/1M$1.20 out/1M90 tok/s197K—15m agoNovita AI$0.60 in/1M$2.40 out/1M—205K—6h agoDigitalOcean Gradientzero-retention$0.23 in/1M$0.90 out/1M53 tok/s66K—15m agoInceptronzero-retention$0.15 in/1M$0.90 out/1M80 tok/s197Kfp815m agoVenice AIzero-retention$0.27 in/1M$0.95 out/1M67 tok/s198K—6h agoMarazero-retention$0.24 in/1M$0.96 out/1M26 tok/s197K—15m agoParasailzero-retention$0.30 in/1M$1.20 out/1M88 tok/s197Kfp815m agoNovita AIzero-retention$0.30 in/1M$1.20 out/1M60 tok/s205Kfp815m agoMinimaxzero-retention$0.30 in/1M$1.20 out/1M58 tok/s205Kfp815m agoSiliconFlowzero-retention$0.30 in/1M$1.20 out/1M42 tok/s197Kfp815m agoCoreWeavezero-retention$0.30 in/1M$1.20 out/1M83 tok/s197Kfp815m agoPhalazero-retention$0.20 in/1M$1.38 out/1M19 tok/s197K—6h agoMinimaxhighspeed tier$0.60 in/1M$2.40 out/1M61 tok/s205Kfp815m ago
Full specs, hardware verdicts and benchmarks on theMiniMax M2.5 model page →