Context
262K
Input
$0.15/M
Output
$0.50/M
Aliases:nemotron-super-vlnemotron-3.5-super-vl-120b-a12bnvidia-nemotron-3.5-super-vlnvidia-nemotron-3.5-super-vl-120b-a12b
NVIDIA's open multimodal hybrid MoE model (120B total, 12B active) that reasons over text, images, documents and GUI screenshots, with built-in tool calling. Tuned for document understanding, OCR, charts and agentic workloads.
deepinfra/nemotron-3.5-super-vlQuantfp4
- Input
- $0.15/M
- Output
- $0.50/M
- Context
- 262K
- Max out
- 33K
- Cache read
- $0.02/M
- Cache write
- $0.15/M
- Thinking out
- $0.50/M