LLMap
Models /Qwen2.5 72B Instruct /Where to run
Provider guide

Where to run Qwen2.5 72B Instruct

5 live offers tracked.

CHEAPEST
OpenRouter
$0.36 / $0.40
per 1M tokens in / out
FASTEST MEASURED
DeepInfra
27 tok/s
measured throughput · $0.36 input / $0.40 output per million tokens
OpenRouterCHEAPEST$0.36 in/1M$0.40 out/1M—33K—15m agoDeepInfra$0.36 in/1M$0.40 out/1M—33Kfp86h agoNovita AI$0.38 in/1M$0.40 out/1M—32K—6h agoDeepInfrazero-retention$0.36 in/1M$0.40 out/1M27 tok/s33Kfp813m agoNovita AIzero-retention$0.38 in/1M$0.40 out/1M10 tok/s32Kbf1613m ago
Full specs, hardware verdicts and benchmarks on theQwen2.5 72B Instruct model page →