nemotron-nano-12b-v2-vl
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.
| Provider | Source | Input Price ($/1M) | Output Price ($/1M) | Description | Free |
|---|---|---|---|---|---|
| vercel | vercel | Input: $0.20 | Output: $0.60 | 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. | |
| openrouter | openrouter | Input: $0.20 | Output: $0.60 | 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 memory-efficient sequence modeling for significantly higher throughput and lower latency. The model supports inputs of text and multi-image documents, producing natural-language outputs. It is trained on high-quality NVIDIA-curated synthetic datasets optimized for optical-character recognition, chart reasoning, and multimodal comprehension. Nemotron Nano 2 VL achieves leading results on OCRBench v2 and scores ≈ 74 average across MMMU, MathVista, AI2D, OCRBench, OCR-Reasoning, ChartQA, DocVQA, and Video-MME—surpassing prior open VL baselines. With Efficient Video Sampling (EVS), it handles long-form videos while reducing inference cost. Open-weights, training data, and fine-tuning recipes are released under a permissive NVIDIA open license, with deployment supported across NeMo, NIM, and major inference runtimes. Context: 131072 |