Provider guide
Where to run GLM 4.7 Flash
7 live offers tracked.
FASTEST MEASURED
38 tok/s
measured throughput · $0.060 input / $0.40 output per million tokens
OpenRouterCHEAPEST$0.060 in/1M$0.40 out/1M—203K—15m agoDeepInfra$0.060 in/1M$0.40 out/1M—203Kbfloat166h agoNovita AI$0.070 in/1M$0.40 out/1M—200K—6h agoCloudflare Workers AI$0.060 in/1M$0.40 out/1M31 tok/s131K—13m agoDeepInfrazero-retention$0.060 in/1M$0.40 out/1M38 tok/s203Kbf166h agoNovita AIzero-retention$0.070 in/1M$0.40 out/1M11 tok/s200Kbf166h agoVenice AIzero-retention$0.060 in/1M$0.40 out/1M18 tok/s128Kfp86h ago
Full specs, hardware verdicts and benchmarks on theGLM 4.7 Flash model page →