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

Where to run DeepSeek V4 Pro

26 live listings tracked — output prices vary 2.8× between the cheapest and most expensive host, so the provider choice matters as much as the model choice.

CHEAPEST
OpenRouter
$0.78 / $1.57
per 1M tokens in / out
FASTEST MEASURED
Wafer
137 tok/s
measured throughput · $0.33 input / $4.20 output per million tokens
OpenRouterCHEAPEST$0.78 in/1M$1.57 out/1M—1M—27 hours agoStreamLake$0.78 in/1M$1.57 out/1M41 tok/s1Mfp827 hours agoRekazero-retention$0.58 in/1M$1.74 out/1M2 tok/s1M—3 hours agoAlibaba Cloud$0.58 in/1M$1.74 out/1M63 tok/s1M—9 hours agoIonstreamzero-retention$1.24 in/1M$1.85 out/1M82 tok/s1M—2 days agoGMICloud$0.96 in/1M$1.91 out/1M34 tok/s1Mfp83 hours agoStreamLake$0.66 in/1M$1.98 out/1M47 tok/s1M—3 hours agoDigitalOcean Gradientzero-retention$1.04 in/1M$2.09 out/1M54 tok/s1M—3 hours agoCloudflare Workers AI$1.15 in/1M$2.55 out/1M39 tok/s1M—9 hours agoDeepInfrazero-retention through OpenRouterDirect and through OpenRouter$1.30 in/1M$2.60 out/1M50 tok/sthrough OpenRouter1Mfp89 hours ago direct3 hours ago through OpenRouterAlibaba Cloud$1.42 in/1M$2.83 out/1M41 tok/s1Mfp815 hours agoNovita AIzero-retention through OpenRouterDirect and through OpenRouter$1.60 in/1M$0.99 in/1M$3.20 out/1Mdirect$2.97 out/1Mthrough OpenRouter79 tok/sthrough OpenRouter1Mfp89 hours ago direct3 hours ago through OpenRouterSiliconFlowzero-retention$1.50 in/1M$3.13 out/1M35 tok/s1Mfp83 hours agoNextBitzero-retention$1.06 in/1M$3.17 out/1M29 tok/s1Mfp83 hours agoVenice AIzero-retention$1.65 in/1M$3.30 out/1M8 tok/s1M—3 hours agoAtlasCloud$1.68 in/1M$3.38 out/1M30 tok/s1Mfp43 hours agoRelacezero-retention$0.14 in/1M$3.50 out/1M91 tok/s1Mfp43 hours agoMicrosoft Azure AIzero-retention$1.91 in/1M$3.83 out/1M48 tok/s1M—3 hours agoAtlasCloud$1.32 in/1M$3.96 out/1M40 tok/s1Mfp83 hours agoBaidu$1.32 in/1M$3.96 out/1M45 tok/s1Mfp845 hours agoDeepSeek$1.32 in/1M$3.96 out/1M38 tok/s1M—3 hours agoCoreWeavezero-retention$1.31 in/1M$3.96 out/1M131 tok/s1Mfp83 hours agoTogether AIzero-retention$1.32 in/1M$3.96 out/1M17 tok/s1M—3 hours agoParasailzero-retention$1.32 in/1M$3.96 out/1M53 tok/s1Mfp83 hours agoWaferzero-retention$0.33 in/1M$4.20 out/1M137 tok/s1M—3 hours agoPhalazero-retention$1.45 in/1M$4.36 out/1M44 tok/s1M—3 hours ago
Full specs, hardware verdicts and benchmarks on the DeepSeek V4 Pro model page →