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
113 tok/s
measured throughput · $1.74 input / $3.48 output per million tokens
OpenRouterCHEAPEST$0.43 in/1M$0.87 out/1M—1M—5h agoDeepSeek$0.43 in/1M$0.87 out/1M27 tok/s1M—5h agoBaidu$0.54 in/1M$1.08 out/1M61 tok/s1Mfp843h agoStreamLake$0.61 in/1M$1.22 out/1M32 tok/s1Mfp85h agoGMICloud$0.68 in/1M$1.36 out/1M29 tok/s1Mfp85h agoWafer$1.20 in/1M$2.40 out/1M—1Mfp47d agoDeepInfra$1.30 in/1M$2.60 out/1M—1Mfp45h agoAlibaba Cloud$1.42 in/1M$2.83 out/1M50 tok/s1Mfp85h agoAlibaba Cloud$1.42 in/1M$2.83 out/1M53 tok/s1M—6d agoNovita AI$1.60 in/1M$3.20 out/1M—1M—5h agoAtlasCloud$1.68 in/1M$3.38 out/1M36 tok/s1Mfp45h agoCloudflare Workers AI$1.74 in/1M$3.48 out/1M36 tok/s393K—5h agoIonstreamzero-retention$1.13 in/1M$2.26 out/1M14 tok/s1Mfp425h agoNovita AIzero-retention$1.17 in/1M$2.34 out/1M38 tok/s1Mfp85h agoDeepInfrazero-retention$1.30 in/1M$2.60 out/1M18 tok/s1Mfp45h agoDigitalOcean Gradientzero-retention$1.39 in/1M$2.78 out/1M8 tok/s262K—5h agoSiliconFlowzero-retention$1.50 in/1M$3.13 out/1M40 tok/s1Mfp85h agoVenice AIzero-retention$1.65 in/1M$3.30 out/1M43 tok/s1M—5h agoBasetenzero-retention$1.74 in/1M$3.48 out/1M113 tok/s262Kfp45h agoCoreWeavezero-retention$1.74 in/1M$3.48 out/1M12 tok/s1Mfp85h agoTogether AIzero-retention$1.74 in/1M$3.48 out/1M55 tok/s512K—5h agoParasailzero-retention$1.74 in/1M$3.48 out/1M47 tok/s1Mfp85h agoFireworks AIzero-retention$1.74 in/1M$3.48 out/1M43 tok/s1M—5h ago
Full specs, hardware verdicts and benchmarks on theDeepSeek V4 Pro model page →