DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B parameters on input and 16B on...
Rank
#2
Down 2% week over week
Tokens
15.3T
2026-11-21
Requests
487.4M
487,385,407
Tool calls
-
Input / M
$0.05
Output / M
$0.20
Cache / M
$0.001
Context
1.0M
1,048,576 tokens