DeepSeek V4 Pro 0423
DeepSeekdeprecatedDeepSeek 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,...
In
$1.60
Out
$3.20
Blended
$2.00
Where to buy this model
14 access routes| Route | In | Out | Blended | vs |
|---|---|---|---|---|
| ● Relace cheapestfp4 | $0.90 | $1.50 | $1.05 | - |
| ● StreamLake fp8 | $0.96 | $1.91 | $1.19 | +13% |
| $0.96 | $1.91 | $1.20 | +14% | |
| $1.04 | $2.09 | $1.31 | +25% | |
| ● Cloudflare | $1.15 | $2.55 | $1.50 | +43% |
| ● SiliconFlow fp8 | $1.00 | $3.13 | $1.53 | +46% |
| $1.30 | $2.60 | $1.63 | +55% | |
| ● Alibaba fp8 | $1.42 | $2.83 | $1.77 | +69% |
| $1.60 | $3.20 | $2.00 | +90% | |
| ● Venice | $1.65 | $3.30 | $2.06 | +96% |
| ● AtlasCloud fp4 | $1.68 | $3.38 | $2.11 | +101% |
| ● Baidu fp8 | $1.69 | $3.38 | $2.11 | +101% |
| ● Crusoe fp8 | $1.74 | $3.48 | $2.17 | +107% |
| $1.91 | $3.83 | $2.39 | +128% |
● official API · ● cloud platform · ● inference host · USD per 1M tokens. Same model, different providers - price and quantization vary.
- Ctx
- 1.048576M
- max output
- 393K
- cache read /1M
- $0.14
- Family
- deepseek
- Modalities
- text
- Features
- json · reasoning · tools
Live pricing, updated 2026-11-03.
DeepSeek models at a similar price
| Model | In | Out | Ctx |
|---|---|---|---|
| DeepSeek V3 | $0.257 | $1.03 | 164K |
| DeepSeek V3.1 Terminus | $0.27 | $1 | 164K |
| DeepSeek V3 0324 | $0.29 | $1.14 | 164K |
| R1 0528 | $0.5 | $2.15 | 164K |
| DeepSeek V4 Pro 0813 | $0.115 | $4 | 1.048576M |
| DeepSeek V4 Pro 0423 · this model | $1.6 | $3.2 | 1.048576M |