DeepSeek 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...
DeepSeek: DeepSeek V4 Flash 0423 — DeepSeek. Context window 1,048,576 tokens. API pricing (per 1M tokens): Input $0.0224, Output $1.28. License: Open-Weights.
| Provider | DeepSeek |
|---|---|
| API model ID | deepseek/deepseek-v4-flash |
| Tier | Frontier |
| Context window | 1,048,576 tokens |
| Max output | 943,718 tokens |
| License | Open-Weights |
| API pricing (per 1M tokens) · Input | $0.0224 |
| API pricing (per 1M tokens) · Output | $1.28 |