DeepSeek: DeepSeek V4 Flash 0423
deepseek/deepseek-v4-flash
DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window. It is designed for fast inference and...
Modalities
In / Out Price
$0.0075 / $1.28 per 1M
Context
1M
Released
Apr 24, 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.
| Provider | Context | Input /M | Output /M | Cache read /M | Latency | Throughput | Uptime |
|---|---|---|---|---|---|---|---|
 Relacefp4 | 1M | $0.0075 | $1.28 | $0.0075 | — | — | 100.00% |
 OpenInferencefp4 | 1M | $0.00792 | $0.604 | $0.00792 | — | — | 96.67% |
 Baidufp8 | 1M | $0.0182 | $0.0364 | $0.00364 | — | — | 80.00% |
 StreamLakefp8 | 1M | $0.07 | $0.14 | $0.014 | — | — | 100.00% |
 Wafer | 1M | $0.075 | $0.17 | $0.013 | — | — | 100.00% |
 DeepInfrafp8 | 1M | $0.09 | $0.18 | $0.018 | — | — | 100.00% |
 GMICloudfp8 | 1M | $0.091 | $0.182 | $0.0182 | — | — | 100.00% |
 Venice | 1M | $0.0966 | $0.193 | $0.0196 | — | — | 100.00% |
 DigitalOcean | 1M | $0.098 | $0.196 | $0.0196 | — | — | 100.00% |
 SiliconFlowfp8 | 1M | $0.13 | $0.28 | $0.028 | — | — | 100.00% |
 Alibabafp8 | 1M | $0.134 | $0.268 | $0.0268 | — | — | 100.00% |
 Novitafp8 | 1M | $0.14 | $0.28 | $0.028 | — | — | 100.00% |
 AtlasCloudfp4 | 1M | $0.14 | $0.28 | $0.028 | — | — | 100.00% |
 Parasailfp8 | 1M | $0.14 | $0.28 | $0.07 | — | — | 100.00% |
 Mancer 2fp8 | 1M | $0.19 | $0.50 | — | — | — | 89.66% |
 Azure | 1M | $0.21 | $0.56 | $0.031 | — | — | 100.00% |
 Cloudflare | 384K | $0.44 | $1.32 | $0.014 | — | — | 100.00% |