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
#5
No change
Tokens
5.19T
2026-09-06
Requests
524.2M
524,158,525
Tool calls
-
Input / M
$0.09
Output / M
$0.18
Cache / M
$0.02
Context
1.0M
1,048,576 tokens