DeepSeek V4 Flash 0423
DeepSeekDeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window. It is designed for fast inference and...
In
$0.09
Out
$0.18
Blended
$0.11
Where to buy this model
17 access routes| Route | In | Out | Blended | vs |
|---|---|---|---|---|
| ● StreamLake cheapestfp8 | $0.08 | $0.17 | $0.10 | - |
| $0.09 | $0.18 | $0.11 | +10% | |
| $0.09 | $0.18 | $0.11 | +10% | |
| ● Venice | $0.10 | $0.19 | $0.12 | +20% |
| $0.10 | $0.20 | $0.12 | +20% | |
| $0.10 | $0.21 | $0.13 | +30% | |
| ● Relace fp4 | $0.05 | $0.45 | $0.15 | +50% |
| ● SiliconFlow fp8 | $0.13 | $0.28 | $0.17 | +70% |
| ● Crusoe fp8 | $0.14 | $0.28 | $0.18 | +80% |
| ● Baidu fp8 | $0.14 | $0.28 | $0.18 | +80% |
| ● AtlasCloud fp4 | $0.14 | $0.28 | $0.18 | +80% |
| $0.14 | $0.28 | $0.18 | +80% | |
| ● Alibaba fp8 | $0.15 | $0.30 | $0.19 | +90% |
| ● Mancer 2 fp8 | $0.19 | $0.50 | $0.27 | +170% |
| $0.21 | $0.56 | $0.30 | +200% | |
| ● Wafer mxfp4 | $0.60 | $0.17 | $0.49 | +390% |
| ● Cloudflare | $0.44 | $1.32 | $0.66 | +560% |
● official API · ● cloud platform · ● inference host · USD per 1M tokens. Same model, different providers - price and quantization vary.
- Ctx
- 1.048576M
- max output
- 944K
- cache read /1M
- $0.02
- 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 V4 Flash 0423 · this model | $0.091 | $0.182 | 1.048576M |
| DeepSeek V4.1 Flash | $0.045 | $0.5 | 1.048576M |
| DeepSeek V3.2 | $0.26 | $0.38 | 164K |
| DeepSeek V3.2 Exp | $0.27 | $0.41 | 164K |
| DeepSeek V4 Flash Vision Exp | $0.216 | $0.647 | 1.048576M |
| DeepSeek V3.1 | $0.25 | $0.95 | 164K |