← All models
DeepSeek: DeepSeek V4 Flash 0731 logo

Deepseek · Text

DeepSeek: DeepSeek V4 Flash 0731

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....

Open-weightIn: TextOut: Text

Input / M

$0.06 / M

Output / M

$0.18 / M

Cache read / M

$0.01 / M

Context

1M

Released

Jul 31, 2026