DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window. It is designed for fast inference and...
Rank
#6
Down 12% week over week
Tokens
4.63T
2026-09-11
Requests
497.3M
497,290,591
Tool calls
-
Input / M
$0.07
Output / M
$0.13
Cache / M
$0.01
Context
1.0M
1,048,576 tokens