DeepSeek: DeepSeek V4 Flash 0731
Input per million tokens
$0.098
Unchanged since November 16, 2026
- November 16, 2026: $0.098
Output per million tokens
$0.196
Unchanged since November 16, 2026
- November 16, 2026: $0.196
Alias deepseek-v4-flash-0731 > deepseek-v4-flash-0731-1
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.
We are inviting early-access interest while we develop the platform.
| Model version | Status | Released | Retires | Hugging Face revision |
|---|---|---|---|---|
| deepseek-v4-flash-0731-1CURRENT | Live |
Per million tokens
Batch is not offered for this model.
| Input | Cached input | Output | |
|---|---|---|---|
| On demand | $0.098 | Billed as input | $0.196 |
| Batch | Batch is not offered for this model. | ||
In every pool, every input token is billed at the input rate today.
Input per million tokens
$0.098
Unchanged since November 16, 2026
Output per million tokens
$0.196
Unchanged since November 16, 2026