Provider guide
Where to run DeepSeek V3.1 Terminus
13 live offers tracked — output prices vary 4.7× between the cheapest and most expensive host, so the provider choice matters as much as the model choice.
FASTEST MEASURED
57 tok/s
measured throughput · $0.34 input / $1.03 output per million tokens
AtlasCloud$0.30 in/1M$0.95 out/1M45 tok/s131Kfp814m agoOpenRouterCHEAPEST$0.25 in/1M$0.95 out/1M—164K—14m agoDeepInfra$0.25 in/1M$0.95 out/1M—164Kfp46h agoNovita AI$0.27 in/1M$1.00 out/1M—131K—6h agoStreamLake$0.34 in/1M$1.03 out/1M57 tok/s128K—14m agoSambaNova$3.00 in/1M$4.50 out/1M—131K—6h agoDeepInfrazero-retention$0.25 in/1M$0.95 out/1M8 tok/s164Kfp414m agoSiliconFlowzero-retention$0.27 in/1M$1.00 out/1M18 tok/s164Kfp814m agoNovita AIzero-retention$0.27 in/1M$1.00 out/1M26 tok/s131Kfp814m agoSambaNovazero-retention$0.65 in/1M$1.50 out/1M55 tok/s131Kfp814m agoCoreWeavezero-retention$0.55 in/1M$1.65 out/1M52 tok/s161Kfp814m agoGoogle Vertex AIzero-retention$0.60 in/1M$1.70 out/1M38 tok/s164K—14m agoMarazero-retention$0.60 in/1M$1.70 out/1M28 tok/s131K—44h ago
DeepInfra
Novita AI
SambaNova
Google Vertex AIFull specs, hardware verdicts and benchmarks on theDeepSeek V3.1 Terminus model page →