Models /GLM 4.6 /Where to run
Provider guide

Where to run GLM 4.6

8 live offers tracked.

CHEAPEST
$0.50 / $2.00
per 1M tokens in / out
FASTEST MEASURED
40 tok/s
measured throughput · $0.60 input / $2.20 output per million tokens
DeepInfra$0.50 in/1M$2.00 out/1M203Kfp46h agoOpenRouterCHEAPEST$0.50 in/1M$2.00 out/1M205K15m agoNovita AI$0.55 in/1M$2.20 out/1M205K6h agoAtlasCloud$0.60 in/1M$2.20 out/1M40 tok/s203Kfp813m agoVenice AIzero-retention$0.43 in/1M$1.75 out/1M13 tok/s198Kfp413m agoDeepInfrazero-retention$0.50 in/1M$2.00 out/1M26 tok/s203Kfp413m agoZ.AIzero-retention$0.60 in/1M$2.20 out/1M36 tok/s203Kfp48h agoNovita AIzero-retention$0.55 in/1M$2.20 out/1M25 tok/s205Kbf166h ago
Full specs, hardware verdicts and benchmarks on theGLM 4.6 model page →