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
#15
Down 12% week over week
Tokens
2.77T
2026-10-21
Requests
329.8M
329,822,161
Tool calls
-
Input / M
$0.09
Output / M
$0.18
Cache / M
$0.02
Context
1.0M
1,048,576 tokens