Models /GLM 4.6 /Where to run

Provider guide

Where to run GLM 4.6

5 live listings tracked.

CHEAPEST

$0.43 / $1.75

per 1M tokens in / out

FASTEST MEASURED

11 tok/s

measured throughput · $0.50 input / $2.00 output per million tokens

ProviderIn / 1MOut / 1MThroughputContextQuantSynced

Venice AIzero-retention$0.43 in/1M$1.75 out/1M5 tok/s198Kfp428 min ago OpenRouterCHEAPEST$0.43 in/1M$1.75 out/1M—205K—30 min ago DeepInfrazero-retention through OpenRouterDirect and through OpenRouter$0.50 in/1M$2.00 out/1M11 tok/sthrough OpenRouter203Kfp46 hours ago direct28 min ago through OpenRouter Novita AIzero-retention through OpenRouterDirect and through OpenRouter$0.55 in/1M$2.20 out/1M1 tok/sthrough OpenRouter205Kbf166 hours ago direct28 min ago through OpenRouter Z.AIzero-retention$0.60 in/1M$2.20 out/1M1 tok/s203Kfp428 min ago

Full specs, hardware verdicts and benchmarks on the GLM 4.6 model page →