Models /GLM 4.5 Air /Where to run

Provider guide

Where to run GLM 4.5 Air

5 live offers tracked.

CHEAPEST

$0.13 / $0.85

per 1M tokens in / out

FASTEST MEASURED

45 tok/s

measured throughput · $0.20 input / $1.10 output per million tokens

ProviderIn / 1MOut / 1MThroughputContextQuantSynced

OpenRouterCHEAPEST$0.13 in/1M$0.85 out/1M—131K—17m ago Novita AI$0.13 in/1M$0.85 out/1M—131K—6h ago Novita AIzero-retention$0.13 in/1M$0.85 out/1M21 tok/s131Kbf1615m ago SiliconFlowzero-retention$0.14 in/1M$0.86 out/1M19 tok/s131Kfp86h ago Z.AIzero-retention$0.20 in/1M$1.10 out/1M45 tok/s131Kfp86h ago

Full specs, hardware verdicts and benchmarks on theGLM 4.5 Air model page →