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
#4
Down 20% week over week
Tokens
4.90T
2026-08-14
Requests
505.0M
504,989,757
Tool calls
-
Input / M
$0.06
Output / M
$0.13
Cache / M
$0.01
Context
1.0M
1,048,576 tokens