Nemotron-nano 12b v2-vl
Input, lowest
$0.2
Output, lowest
$0.6
Providers
1
Providers & prices
| Provider | Input | Output | Context | Last sync | |
|---|---|---|---|---|---|
D
DigitalOcean
|
$0.2 | $0.6 | 128,000 |
About this model
A 12B vision-language model built on a hybrid Mamba-Transformer architecture with C-RADIOv2-H vision encoder. choose this when you need document intelligence, multi-image Reason'g, or video understanding at high throughput. Context up to 128K tokens, supports image summarization, OCR, visual Q&A, and chain-of-thought Reason'g across 10 languages.