Compare Models
Created by
nvidia
nvidiaReleasedOct 28, 2025
The model is an auto-regressive vision language model that uses an optimized transformer architecture. The model enables multi-image reasoning and video understanding, along with strong document intelligence, visual Q&A and summarization capabilities.
Limits
Context Length131.1K
Max Output Tokens131.1K
Pricing
Pricing (Input)$0.20/M
Pricing (Output)$0.60/M
Caching
Input Modalities
Text
Image
PDF
Audio
Output Modalities
Text
Image
Audio
Features
Reasoning
Tools
Temperature
No model selected
Use the selector above to choose a model.