DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B parameters on input and 16B on...
What Reroute charges per unit. No markup on inference — you pay the carrier's price, metered from the carrier's own usage numbers.
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 |
|---|---|---|---|---|---|
| $0.0168 | $0.80 | $0.008 | — | — | |
| $0.0354 | $0.142 | $0.000708 | — | 88% | |
| $0.045 | $0.60 | $0.01 | — | — | |
| $0.05 | $1.15 | $0.006 | — | — | |
| $0.055 | $1.20 | $0.044 | — | — | |
| $0.08 | $0.40 | $0.01 | — | — | |
| $0.09 | $0.18 | $0.018 | — | — | |
| $0.105 | $0.60 | $0.015 | — | — | |
| $0.12 | $1.20 | $0.005 | — | — | |
| $0.14 | $0.42 | $0.0042 | — | 30% | |
| $0.15 | $0.60 | $0.003 | — | 50% | |
| $0.15 | $0.60 | $0.015 | — | — | |
| $0.15 | $0.60 | $0.003 | — | — | |
| $0.18 | $0.72 | $0.0036 | — | 40% | |
| $0.195 | $0.78 | $0.0039 | — | 35% | |
| $0.20 | $0.65 | $0.03 | — | — | |
| $0.21 | $0.84 | $0.0042 | — | 30% | |
| $0.225 | $0.90 | $0.006 | — | — | |
| $0.27 | $1.15 | $0.009 | — | — | |
| $0.29 | $1.20 | $0.007 | — | — | |
| $0.30 | $1.20 | $0.03 | — | — | |
| $0.30 | $1.20 | $0.007 | — | — | |
| $0.30 | $1.20 | $0.006 | — | — | |
| $0.30 | $1.20 | $0.006 | — | — | |
| $0.30 | $1.20 | $0.03 | — | — | |
| $0.30 | $1.20 | $0.007 | — | — | |
| $0.30 | $1.20 | $0.006 | — | — | |
| $0.30 | $1.20 | $0.006 | — | — | |
| $0.30 | $1.20 | $0.0075 | — | — | |
| $0.45 | $1.80 | $0.009 | — | — |