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

Where to run Qwen2.5 VL 72B Instruct

4 live offers tracked.

CHEAPEST
OpenRouter
$0.80 / $1.00
per 1M tokens in / out
FASTEST MEASURED
Parasail
30 tok/s
measured throughput · $0.80 input / $1.00 output per million tokens
Novita AI$0.80 in/1M$0.80 out/1M—33K—10h agoOpenRouterCHEAPEST$0.80 in/1M$1.00 out/1M—128K—4h agoNebius AI Studiozero-retention$0.25 in/1M$0.75 out/1M25 tok/s32Kfp84h agoParasailzero-retention$0.80 in/1M$1.00 out/1M30 tok/s128Kfp84h ago
Full specs, hardware verdicts and benchmarks on theQwen2.5 VL 72B Instruct model page →