DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. This re-post-trained revision is suited for coding, reasoning, and agent workflows....
| Field | Per token (USD) | Per million |
|---|---|---|
| prompt | 0.0000000434 | $0.043 |
| completion | 0.0000003 | $0.300 |
| input_cache_read | 0.000000035 | $0.035 |
2 answersin this database. A round opens every model's answer to the same prompt.