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...
| Field | Per token (USD) | Per million |
|---|---|---|
| prompt | 0.00000009 | $0.090 |
| completion | 0.00000018 | $0.180 |
| input_cache_read | 0.000000018 | $0.018 |