Polarison

DeepSeek · open weights

DeepSeek V4.1 Flash API pricing by provider

DeepSeek V4.1 Flash is available from 32 providers. The cheapest is Sail Research at $0.09 input / $0.25 output per 1M tokens (FP4). The priciest host, Fireworks, charges 6.1x the cheapest.

Prices from the OpenRouter API, retrieved October 26, 2026. Weights: deepseek-ai/DeepSeek-V4.1-Flash.

ProviderPrecisionInput / 1MOutput / 1MDocument Q&A / monthContextMax output
Sail Researchfp4$0.09$0.25$43.501.05M384K
DeepInfrafp8$0.112$0.336$54.881.05M131K
Relace—$0.07$0.50$43.001.05M944K
DeepInfrafp8$0.14$0.42$68.601.05M131K
Morphfp8$0.048$0.80$43.201.05M944K
AtlasCloudfp8$0.135$0.54$70.201.05M393K
InferenceNetfp8$0.103$0.645$60.551.04M393K
Baidufp8$0.1398$0.5592$72.701.05M393K
StreamLakefp8$0.147$0.588$76.441.02M384K
OpenInferencefp4$0.02$1.00$38.001.05M944K
CoreWeavefp8$0.15$0.65$79.501.05M944K
Reka—$0.105$0.84$67.201.05M393K
Alibaba—$0.165$0.66$85.801M393K
ModelRunfp4$0.17$0.67$88.101.05M131K
Wafermxfp4$0.19$0.65$95.501.05M944K
GMICloudfp8$0.18$0.72$93.601.05M944K
DeepInfrafp8$0.21$0.63$102.901.05M131K
Novitafp8$0.195$0.78$101.401.05M393K
Phala—$0.21$0.84$109.201.05M944K
DigitalOcean—$0.225$0.90$117.001.05M944K
Mancer 2fp8$0.20$1.00$110.001.05M944K
Makorafp8$0.26$1.17$139.101.05M944K
Crusoefp8$0.29$1.20$152.001.05M944K
Google—$0.30$1.20$156.001.05M944K
Nebiusfp8$0.30$1.20$156.001.05M943K
PrimeIntellect—$0.30$1.20$156.001.05M131K
Cohere—$0.30$1.20$156.001.05M384K
BaseTen—$0.30$1.20$156.001.05M262K
Together—$0.30$1.20$156.001.05M944K
SiliconFlowfp8$0.30$1.20$156.001.05M393K
Modal—$0.30$1.20$156.001.05M944K
Parasailfp8$0.30$1.20$156.001.05M944K
Fireworks—$0.30$1.20$156.001.05M944K
Venicefp8$0.30$1.20$156.001M131K
Fireworks—$0.45$1.80$234.001.05M944K

Sorted by blended price (3 input : 1 output). Document Q&A assumes 50,000 questions a month with 8,000 input and 600 output tokens each. Precision is reported by the provider; “—” means not disclosed.

Compare with DeepSeek’s API page

See benchmarks, cached-input pricing and comparisons for DeepSeek V4.1 Flash on its model page.

Frequently asked questions

What is the cheapest DeepSeek V4.1 Flash API provider?
Sail Research is the cheapest healthy provider we track at $0.09 per 1M input tokens and $0.25 per 1M output tokens.
How much does DeepSeek V4.1 Flash cost?
Across 32 providers, input prices range from $0.02 to $0.45 per 1M tokens and output prices from $0.25 to $1.80.
What is DeepSeek V4.1 Flash’s context window?
DeepSeek V4.1 Flash supports up to 1.05M tokens, but some providers serve a smaller context window — check the table before choosing.

Other open-weight models