ModelWatch
← Catalog

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....

long-contextopen-weightslow-cost
Input price
$0.04 / 1M tokens
Output price
$0.30 / 1M tokens
Context window
1.05M tokens
Max output
944K tokens
Output speed
127 tokens/s
Time to first token
1.66s
Inputs
text
Open weights
Yes
OpenRouter id
deepseek/deepseek-v4-flash-0731
Listed
Jul 31, 2026

Benchmarks

Intelligence Index
n/a
Engineering Index
n/a

Speed and benchmarks for “DeepSeek V4 Flash 0731 (Max)” from Artificial Analysis. Prices, context window and listing date are live from OpenRouter.

Compare with others