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
$0.0104 / $1.28 per 1M
Context
1M
Released
Jul 31, 2026
Knowledge Cutoff
—
Pricing
What Reroute charges per unit. No markup on inference — you pay the carrier's price, metered from the carrier's own usage numbers.
Input tokens
$0.0104 / M
Output tokens
$1.28 / M
Cache read
$0.0104 / M
By provider
Each carrier sets its own price. The router weighs these against uptime when it picks one.
| Provider | Input /M | Output /M | Cache read /M | Cache write /M | Discount |
|---|---|---|---|---|---|
 OpenInference | $0.00632 | $0.484 | $0.00632 | — | — |
 Relace | $0.0079 | $1.28 | $0.0079 | — | — |
 Sail Research | $0.019 | $0.42 | $0.012 | — | — |
 Reka | $0.021 | $0.528 | $0.0056 | — | — |
 StreamLake | $0.044 | $0.132 | $0.0014 | — | 90% |
 Inceptron | $0.05 | $0.65 | $0.027 | — | — |
 DeepInfra | $0.06 | $0.18 | $0.015 | — | — |
| Sail Research | $0.10 | $0.30 | $0.03 | — | — |
 DigitalOcean | $0.119 | $0.238 | $0.0238 | — | — |
 Wafer | $0.13 | $0.23 | $0.12 | — | — |
 BaseTen | $0.13 | $0.26 | $0.028 | — | — |
| BaseTen | $0.13 | $0.26 | $0.028 | — | — |
 Venice | $0.13 | $0.26 | $0.028 | — | — |
 CoreWeave | $0.13 | $0.28 | $0.07 | — | — |
 Cohere | $0.14 | $0.28 | $0.07 | — | — |
 Together | $0.14 | $0.28 | $0.03 | — | — |
 Parasail | $0.14 | $0.28 | $0.05 | — | — |
 Alibaba | $0.176 | $0.528 | $0.0176 | — | — |
 Mancer 2 | $0.20 | $0.60 | — | — | — |
 SiliconFlow | $0.22 | $0.66 | $0.028 | — | — |
 GMICloud | $0.286 | $0.858 | $0.0091 | — | 35% |
 Phala | $0.308 | $0.924 | $0.0196 | — | 30% |
 Novita | $0.409 | $1.23 | $0.026 | — | 7% |
 Baidu | $0.44 | $1.32 | $0.014 | — | — |
 AtlasCloud | $0.44 | $1.32 | $0.028 | — | — |
 Cloudflare | $0.44 | $1.32 | $0.014 | — | — |