reroute

DeepSeek: DeepSeek V4 Flash 0731

deepseek/deepseek-v4-flash-0731
Compare API Try this model

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....

Modalities
In / Out Price
$0.018 / $1.28 per 1M
Context
1M
Released
Jul 31, 2026
Knowledge Cutoff
—

Activity

Tokens processed for this model through Reroute, per day, over the last 30 days.

No usage through Reroute yet

Daily token volume shows up here as soon as the first request for this model completes.