DeepSeek: DeepSeek V4 Pro 0423
deepseek/deepseek-v4-pro
DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window. It is designed for advanced reasoning, coding,...
Modalities
In / Out Price
$0.287 / $0.575 per 1M
Context
1M
Released
Apr 24, 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
$0.287 / M
Output tokens
$0.575 / M
Cache read
$0.0239 / 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 |
|---|---|---|---|---|---|
 Relace | $0.284 | $4.20 | $0.21 | — | — |
 StreamLake | $0.287 | $0.575 | $0.0239 | — | 83% |
 Baidu | $0.289 | $0.578 | $0.0239 | — | 83% |
 Parasail | $0.45 | $3.48 | $0.10 | — | — |
 GMICloud | $0.957 | $1.91 | $0.0798 | — | 45% |
 DigitalOcean | $1.04 | $2.09 | $0.209 | — | — |
 Reka | $1.05 | $10.50 | $0.21 | — | 30% |
 Cloudflare | $1.15 | $2.55 | $0.20 | — | — |
 DeepInfra | $1.30 | $2.60 | $0.10 | — | — |
 Alibaba | $1.42 | $2.83 | $0.118 | — | — |
 SiliconFlow | $1.5 | $3.14 | $0.135 | — | — |
 Novita | $1.60 | $3.20 | $0.135 | — | — |
 Venice | $1.65 | $3.3 | $0.33 | — | — |
 AtlasCloud | $1.68 | $3.38 | $0.13 | — | — |
 Azure | $1.91 | $3.83 | $0.16 | — | — |