# Nemotron Nano 12B 2 VL (free)

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.

## Model Information

- **Organization**: [Nvidia](/llm.txt)
- **Slug**: nemotron-nano-12b-v2-vl
- **Available at Providers**: 16
- **Release Date**: October 28, 2025

## Providers

| Provider | Name | $ Input (per 1M) | $ Output (per 1M) | Free | Link |
|----------|------|-----------------|------------------|------|------|
| [AIMLAPI](/llm/aimlapi.txt) | Nemotron Nano 12B V2 VL | 0.27 | 0.82 |  |  |
| [OpenRouter](/llm/openrouter.txt) | Nemotron Nano 12B 2 VL | 0.20 | 0.60 |  | [View](https://openrouter.ai/nvidia/nemotron-nano-12b-v2-vl) |
| [ValorGPT](/llm/valorgpt.txt) | Nemotron Nano 12B 2 VL |  |  |  | [View](https://www.valorgpt.com/models/nvidia-nemotron-nano-12b-v2-vl) |
| [ValorGPT](/llm/valorgpt.txt) | Nemotron Nano 12B 2 VL |  |  | Yes | [View](https://www.valorgpt.com/models/nvidia-nemotron-nano-12b-v2-vl-free) |
| [Vercel AI Gateway](/llm/vercel.txt) | Nvidia Nemotron Nano 12B V2 VL | 0.20 | 0.60 |  |  |
| [Yupp](/llm/yupp.txt) | Nemotron Nano 12B 2 VL (OpenRouter) |  |  |  |  |
| [Routeway](/llm/routeway.txt) | NVIDIA: Nemotron Nano 12B 2 VL | 0.02 | 0.06 |  | [View](https://routeway.ai/models) |
| [LangDB](/llm/langdb.txt) | nemotron-nano-12b-v2-vl |  |  |  | [View](https://langdb.ai/app/models) |
| [Kilo Code](/llm/kilocode.txt) | NVIDIA: Nemotron Nano 12B 2 VL | 0.20 | 0.60 |  | [View](https://kilo.ai/models/nvidia/nemotron-nano-12b-v2-vl) |
| [Nvidia](/llm/nvidia.txt) | nemotron-nano-12b-v2-vl |  |  |  | [View](https://build.nvidia.com/nvidia/nemotron-nano-12b-v2-vl) |
| [Kilo Code](/llm/kilocode.txt) | NVIDIA: Nemotron Nano 12B 2 VL (free) | 0.00 | 0.00 | Yes |  |
| [Chats-LLM](/llm/chatsllm.txt) | NVIDIA: Nemotron Nano 12B 2 VL | 0.20 | 0.60 |  |  |
| [WaveSpeed AI](/llm/wavespeed.txt) | nemotron-nano-12b-v2-vl | 0.22 | 0.66 |  |  |
| [OpenRouter](/llm/openrouter.txt) | Nemotron Nano 12B 2 VL (free) | 0.00 | 0.00 | Yes | [View](https://openrouter.ai/nvidia/nemotron-nano-12b-v2-vl:free) |
| [Writingmate](/llm/writingmate.txt) | NVIDIA: Nemotron Nano 12B 2 VL |  |  |  | [View](https://writingmate.ai/models/nvidia/nemotron-nano-12b-v2-vl) |
| [Blackbox AI](/llm/blackboxai.txt) | blackboxai/nvidia/nemotron-nano-12b-v2-vl:free |  |  |  |  |

---

[← Back to all providers](/llm.txt)