reroute

DeepSeek: DeepSeek V4.1 Flash

deepseek/deepseek-v4.1-flash

DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B parameters on input and 16B on...

Modalities
In / Out Price
$0.30 / $1.20 per 1M
Context
1M
Released
Sep 10, 2026
Knowledge Cutoff
—

Providers

Different carriers host the same model. Reroute routes each request to the best one on price and uptime, and fails over to the next if a carrier goes down.

ProviderContextInput /MOutput /MCache read /MLatencyThroughputUptime
Relace1M$0.0283$1.20$0.005——100.00%
Baidufp81M$0.0354$0.142$0.000708——83.33%
Wafer1M$0.045$0.60$0.044——100.00%
Morphfp81M$0.045$0.60$0.01——100.00%
Ionstream1M$0.05$1.15$0.006——100.00%
Sail Researchfp41M$0.08$0.40$0.01——100.00%
Decartfp41M$0.09$0.18$0.018——100.00%
InferenceNetfp81M$0.105$0.60$0.015——100.00%
DekaLLM1M$0.12$1.20$0.005——100.00%
DeepInfrafp81M$0.14$0.42$0.0042——100.00%
StreamLakefp81M$0.15$0.60$0.003——100.00%
Alibaba1M$0.15$0.60$0.015——100.00%
DeepSeek1M$0.15$0.60$0.003——100.00%
GMICloudfp81M$0.18$0.72$0.0036——100.00%
Novitafp81M$0.195$0.78$0.0039——100.00%
CoreWeavefp81M$0.20$0.65$0.03——100.00%
OpenInferencefp41M$0.20$1$0.20——66.67%
Phala1M$0.21$0.84$0.0042——100.00%
DigitalOcean1M$0.225$0.90$0.006——100.00%
Makorafp81M$0.27$1.15$0.009——100.00%
Crusoefp81M$0.29$1.20$0.007——100.00%
AtlasCloudfp81M$0.30$1.20$0.03——100.00%
BaseTenfp81M$0.30$1.20$0.007——100.00%
Together1M$0.30$1.20$0.006——100.00%
SiliconFlowfp81M$0.30$1.20$0.006——100.00%
Modal1M$0.30$1.20$0.03——100.00%
BaseTenfp81M$0.30$1.20$0.007——100.00%
Parasailfp81M$0.30$1.20$0.006——100.00%
Fireworks1M$0.30$1.20$0.006——100.00%
Venicefp81M$0.30$1.20$0.0075——100.00%
Fireworks1M$0.45$1.80$0.009——100.00%