Provider guide
Where to run Llama 3.1 Euryale 70B v2.2
3 live listings tracked — output prices vary 1.7× between the cheapest and most expensive host, so the provider choice matters as much as the model choice.
FASTEST MEASURED
35 tok/s
measured throughput · $0.85 input / $0.85 output per million tokens
OpenRouterCHEAPEST$0.85 in/1M$0.85 out/1M—131K—5 hours agoDeepInfrazero-retention through OpenRouterDirect and through OpenRouter$0.85 in/1M$0.85 out/1M35 tok/sthrough OpenRouter131Kfp85 hours agoNovita AIzero-retention$1.45 in/1M$1.45 out/1M35 tok/s8Kfp85 hours ago
Novita AIFull specs, hardware verdicts and benchmarks on the Llama 3.1 Euryale 70B v2.2 model page →