LLMap
Models /GLM 5.1 /Where to run
Provider guide

Where to run GLM 5.1

23 live offers tracked.

CHEAPEST
OpenRouter
$0.97 / $3.04
per 1M tokens in / out
FASTEST MEASURED
Wafer
81 tok/s
measured throughput · $1.00 input / $3.20 output per million tokens
Baidu$0.95 in/1M$2.99 out/1M30 tok/s203Kfp85h agoStreamLake$0.97 in/1M$3.04 out/1M56 tok/s200Kfp85h agoOpenRouterCHEAPEST$0.97 in/1M$3.04 out/1M—205K—5h agoGMICloud$0.98 in/1M$3.08 out/1M44 tok/s203Kfp85h agoChutes$0.98 in/1M$3.08 out/1M27 tok/s203Kfp85h agoDeepInfra$1.05 in/1M$3.50 out/1M—203Kfp45h agoAtlasCloud$1.26 in/1M$3.96 out/1M38 tok/s203Kfp85h agoAlibaba Cloud$1.33 in/1M$4.18 out/1M51 tok/s203Kfp85h agoNovita AI$1.38 in/1M$4.40 out/1M—205K—5h agoFireworks AI$1.40 in/1M$4.40 out/1M—203K—6d agoFriendli$1.40 in/1M$4.40 out/1M71 tok/s203K—5h agoWaferzero-retention$1.00 in/1M$3.20 out/1M81 tok/s203Kfp45h agoDeepInfrazero-retention$1.05 in/1M$3.50 out/1M31 tok/s203Kfp45h agoSiliconFlowzero-retention$1.19 in/1M$3.74 out/1M53 tok/s205Kfp85h agoPhalazero-retention$1.21 in/1M$4.20 out/1M27 tok/s203K—5h agoDigitalOcean Gradientzero-retention$0.97 in/1M$4.30 out/1M18 tok/s164K—7h agoZ.AIzero-retention$1.40 in/1M$4.40 out/1M52 tok/s203Kfp85h agoNovita AIzero-retention$1.38 in/1M$4.40 out/1M37 tok/s205Kfp85h agoCrusoezero-retention$1.20 in/1M$4.40 out/1M73 tok/s203Kfp85h agoParasailzero-retention$1.40 in/1M$4.40 out/1M68 tok/s203Kfp85h agoCoreWeavezero-retention$1.40 in/1M$4.40 out/1M72 tok/s203Kfp85h agoNebius AI Studiozero-retention$1.40 in/1M$4.40 out/1M33 tok/s203Kfp85h agoVenice AIzero-retention$1.54 in/1M$4.84 out/1M26 tok/s200Kfp85h ago
Full specs, hardware verdicts and benchmarks on theGLM 5.1 model page →