Pricing · ArbitrageUpdated 2026-10-05 · 28 providers

DeepSeek V4.1 Flash · Price by Provider

The cheapest offer (Relace, $0.003/M input) is 99% below the most expensive (Fireworks, $0.45/M). Model details

ProviderPrecisionInput /MOutput /MUptime 24h
Relacecheapest·$0.003$2.4099.9%
InferenceNet·$0.050$0.3099.3%
Morphfp8$0.058$0.4596.1%
Wafer·$0.065$1.2099.9%
Sail Researchfp4$0.080$0.4098.1%
Decartfp4$0.090$0.1898.5%
Ionstream·$0.12$1.1598.8%
DekaLLM·$0.12$2.4097.0%
DeepInfrafp8$0.14$0.42100.0%
AtlasCloudfp8$0.14$0.5699.8%
StreamLakefp8$0.14$0.5699.9%
DigitalOcean·$0.18$0.7299.8%
GMICloudfp8$0.18$0.7299.5%
CoreWeavefp8$0.20$0.6599.0%
NextBitfp8$0.21$0.84100.0%
Phala·$0.21$0.8499.9%
Novitafp8$0.24$0.9699.9%
Makorafp8$0.27$1.1599.9%
Alibaba·$0.30$1.2097.1%
Baidufp8$0.30$1.2099.8%
BaseTenfp8$0.30$1.20100.0%
DeepSeek·$0.30$1.20100.0%
Fireworks·$0.30$1.2092.5%
Modal·$0.30$1.2099.8%
Parasailfp8$0.30$1.2099.8%
SiliconFlowfp8$0.30$1.2099.6%
Together·$0.30$1.2099.9%
Venicefp8$0.30$1.2099.2%
Fireworks·$0.45$1.8097.3%

OpenRouter provider list prices, USD per million tokens, collected daily · all models with price spreads