reroute

DeepSeek: DeepSeek V4 Flash 0731

deepseek/deepseek-v4-flash-0731

DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. This re-post-trained revision is suited for coding, reasoning, and agent workflows....

Modalities
In / Out Price
$0.0079 / $1.28 per 1M
Context
1M
Released
Jul 31, 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
Relacefp41M$0.006$1.28$0.006——100.00%
OpenInferencefp41M$0.00632$0.549$0.00632——100.00%
Sail Researchfp41M$0.019$0.42$0.012——100.00%
Reka262K$0.021$0.528$0.0056——100.00%
StreamLakefp81M$0.044$0.132$0.0014——100.00%
Inceptronfp41M$0.05$0.65$0.027——100.00%
DeepInfrafp81M$0.06$0.18$0.015——100.00%
Sail Researchfp41M$0.10$0.30$0.03——100.00%
DigitalOcean1M$0.119$0.238$0.0238——100.00%
Wafer1M$0.13$0.23$0.12——100.00%
BaseTenfp81M$0.13$0.26$0.028——100.00%
BaseTenfp81M$0.13$0.26$0.028——100.00%
Venice1M$0.13$0.26$0.028——96.67%
CoreWeavefp8262K$0.13$0.28$0.07——100.00%
Cohere1M$0.14$0.28$0.07——100.00%
Together1M$0.14$0.28$0.03——100.00%
Parasailfp81M$0.14$0.28$0.05——100.00%
Alibaba1M$0.176$0.528$0.0176——100.00%
Mancer 2fp81M$0.20$0.60———100.00%
SiliconFlowfp81M$0.22$0.66$0.028——100.00%
GMICloudfp81M$0.286$0.858$0.0091——100.00%
Phala1M$0.308$0.924$0.0196——100.00%
Novitafp81M$0.409$1.23$0.026——100.00%
Baidufp81M$0.44$1.32$0.014——100.00%
AtlasCloudfp41M$0.44$1.32$0.028——93.33%
Cloudflare1M$0.44$1.32$0.014——100.00%