Provider guide
Where to run Llama 4 Scout
4 live listings tracked — output prices vary 2.3× between the cheapest and most expensive host, so the provider choice matters as much as the model choice.
FASTEST MEASURED
102 tok/s
measured throughput · $0.25 input / $0.70 output per million tokens
OpenRouterCHEAPEST$0.10 in/1M$0.30 out/1M—1.3M—4 hours agoDeepInfrazero-retention through OpenRouterDirect and through OpenRouter$0.10 in/1M$0.30 out/1M32 tok/sthrough OpenRouter328Kfp84 hours agoNovita AIzero-retention through OpenRouterDirect and through OpenRouter$0.18 in/1M$0.59 out/1M28 tok/sthrough OpenRouter131Kbf164 hours agoGoogle Vertex AIzero-retention$0.25 in/1M$0.70 out/1M102 tok/s1.3M—4 hours ago
DeepInfra
Novita AIFull specs, hardware verdicts and benchmarks on the Llama 4 Scout model page →