Provider guide
Where to run Gemma 4 31B
16 live listings tracked — output prices vary 3.5× between the cheapest and most expensive host, so the provider choice matters as much as the model choice.
FASTEST MEASURED
151 tok/s
measured throughput · $0.75 input / $1.00 output per million tokens
DekaLLMzero-retentionCHEAPEST$0.10 in/1M$0.33 out/1M11 tok/s262K—21 hours agoOpenRouter$0.090 in/1M$0.34 out/1M—262K—3 hours agoCoreWeavezero-retention$0.10 in/1M$0.34 out/1M46 tok/s262Kfp43 hours agoVenice AIzero-retention$0.12 in/1M$0.36 out/1M16 tok/s256Kfp43 hours agoChutes$0.12 in/1M$0.37 out/1M19 tok/s131Kfp427 hours agoDeepInfrazero-retention through OpenRouterDirect and through OpenRouter$0.15 in/1M$0.40 out/1M14 tok/sthrough OpenRouter262Kfp89 hours ago direct3 hours ago through OpenRouterNovita AIzero-retention through OpenRouterDirect and through OpenRouter$0.14 in/1M$0.40 out/1M23 tok/sthrough OpenRouter262Kbf169 hours ago direct3 hours ago through OpenRouterCrusoezero-retention$0.14 in/1M$0.40 out/1M24 tok/s262Kbf163 hours agoParasailzero-retention$0.15 in/1M$0.40 out/1M18 tok/s262Kfp83 hours agoFriendli$0.14 in/1M$0.40 out/1M56 tok/s262K—3 hours agoSiliconFlowzero-retention$0.75 in/1M$1.00 out/1M26 tok/s262Kfp83 hours agoModelRunzero-retention$0.75 in/1M$1.00 out/1M151 tok/s262Kfp43 hours agoSambaNova$0.38 in/1M$1.15 out/1M—131K—9 hours agoIo Netzero-retention$0.38 in/1M$1.15 out/1M29 tok/s262K—3 hours agoSambaNovazero-retention$0.38 in/1M$1.15 out/1M28 tok/s262K—15 hours agoDeepInfraturbo tier$0.090 in/1M$0.34 out/1M22 tok/s262Kfp43 hours ago
OpenRouter
DeepInfra
Novita AI
SambaNovaFull specs, hardware verdicts and benchmarks on the Gemma 4 31B model page →