LLMap
Models /DeepSeek V4 Pro /Where to run
Provider guide

Where to run DeepSeek V4 Pro

23 live offers tracked — output prices vary 4.0× between the cheapest and most expensive host, so the provider choice matters as much as the model choice.

CHEAPEST
OpenRouter
$0.43 / $0.87
per 1M tokens in / out
FASTEST MEASURED
Baseten
120 tok/s
measured throughput · $1.74 input / $3.48 output per million tokens
OpenRouterCHEAPEST$0.43 in/1M$0.87 out/1M—1M—14m agoDeepSeek$0.43 in/1M$0.87 out/1M23 tok/s1M—14m agoBaidu$0.54 in/1M$1.08 out/1M61 tok/s1Mfp844h agoStreamLake$0.61 in/1M$1.22 out/1M32 tok/s1Mfp86h agoGMICloud$0.66 in/1M$1.32 out/1M28 tok/s1Mfp814m agoWafer$1.20 in/1M$2.40 out/1M—1Mfp47d agoDeepInfra$1.30 in/1M$2.60 out/1M—1Mfp46h agoAlibaba Cloud$1.42 in/1M$2.83 out/1M53 tok/s1M—6d agoAlibaba Cloud$1.42 in/1M$2.83 out/1M51 tok/s1Mfp814m agoNovita AI$1.60 in/1M$3.20 out/1M—1M—6h agoAtlasCloud$1.68 in/1M$3.38 out/1M38 tok/s1Mfp414m agoCloudflare Workers AI$1.74 in/1M$3.48 out/1M34 tok/s393K—14m agoIonstreamzero-retention$1.13 in/1M$2.26 out/1M14 tok/s1Mfp426h agoNovita AIzero-retention$1.17 in/1M$2.34 out/1M35 tok/s1Mfp814m agoDeepInfrazero-retention$1.30 in/1M$2.60 out/1M28 tok/s1Mfp414m agoDigitalOcean Gradientzero-retention$1.39 in/1M$2.78 out/1M8 tok/s262K—6h agoSiliconFlowzero-retention$1.50 in/1M$3.13 out/1M34 tok/s1Mfp814m agoVenice AIzero-retention$1.65 in/1M$3.30 out/1M43 tok/s1M—6h agoBasetenzero-retention$1.74 in/1M$3.48 out/1M120 tok/s262Kfp414m agoCoreWeavezero-retention$1.74 in/1M$3.48 out/1M12 tok/s1Mfp86h agoTogether AIzero-retention$1.74 in/1M$3.48 out/1M46 tok/s512K—14m agoParasailzero-retention$1.74 in/1M$3.48 out/1M36 tok/s1Mfp814m agoFireworks AIzero-retention$1.74 in/1M$3.48 out/1M48 tok/s1M—14m ago
Full specs, hardware verdicts and benchmarks on theDeepSeek V4 Pro model page →