nvidia

NVIDIA: Nemotron Nano 12B 2 VL

NVIDIA Nemotron Nano 2 VL is a 12-billion-parameter open multimodal reasoning model designed for video understanding and document intelligence. It introduces a hybrid Transformer-Mamba architecture, combining transformer-level accuracy with Mamba’s...

Quality Score
91/100
composite of price, context, capability
Input Price
$0.20
per 1M tokens
Output Price
$0.60
per 1M tokens
Context Window
131,072
tokens
Model ID
nvidia/nemotron-nano-12b-v2-vl
Vendor
nvidia
Tokenizer
Other
Input Modalities
image, text, video
Output Modalities
text
Max Output
default
Tool Calling
not supported
Structured Output
✓ supported
Reasoning Mode
✓ supported
Vision
✓ accepts images
Audio
no
Moderated
no

Similar models