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
#218
Up 55% week over week
Tokens
4.3B
2026-10-15
Requests
907.1K
907,074
Tool calls
-
Input / M
$0.11
Output / M
$0.34
Cache / M
$0.0034
Context
1.0M
1,048,576 tokens