AI Models Database
173 models across text, image, audio & embedding
2 models
DeepSeek V3.2
LatestText Local
DeepSeek V3.2 with 685B total parameters (37B active). Features Multi-Token Prediction and Sparse Attention for efficiency.
Context
128K
Params
685
Cutoff
-
License
MIT
Functions
13 in familyDeepSeek V3.2 Exp
LatestText API
DeepSeek Sparse Attention architecture
Context
128K
Params
-
Input
$0.2700
Output
$1.1000
Functions
13 in family