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,...
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 |
|---|---|---|---|---|---|---|---|
| 1M | $0.284 | $4.20 | $0.21 | — | — | 100.00% | |
| 1M | $0.287 | $0.575 | $0.0239 | — | — | 100.00% | |
| 1M | $0.289 | $0.578 | $0.0239 | — | — | 39.29% | |
| 1M | $0.45 | $3.48 | $0.10 | — | — | 100.00% | |
| 1M | $0.957 | $1.91 | $0.0798 | — | — | 100.00% | |
| 1M | $1.04 | $2.09 | $0.209 | — | — | 100.00% | |
| 1M | $1.05 | $10.50 | $0.21 | — | — | 82.14% | |
| 1M | $1.15 | $2.55 | $0.20 | — | — | 100.00% | |
| 1M | $1.30 | $2.60 | $0.10 | — | — | 100.00% | |
| 1M | $1.42 | $2.83 | $0.118 | — | — | 100.00% | |
| 1M | $1.5 | $3.14 | $0.135 | — | — | 100.00% | |
| 1M | $1.60 | $3.20 | $0.135 | — | — | 100.00% | |
| 1M | $1.65 | $3.3 | $0.33 | — | — | 96.67% | |
| 1M | $1.68 | $3.38 | $0.13 | — | — | 77.27% | |
| 1M | $1.91 | $3.83 | $0.16 | — | — | 100.00% |