DeepSeek V3, a 685B-parameter, mixture-of-experts model, is the latest iteration of the flagship chat model family from the DeepSeek team. It succeeds the DeepSeek V3 model and performs really well...
| Field | Per token (USD) | Per million |
|---|---|---|
| prompt | 0.00000029 | $0.290 |
| completion | 0.00000114 | $1.14 |
| input_cache_read | 0.00000011 | $0.110 |