AI Observatory / Model Radar
Nvidia / nvidia/nemotron-nano-12b-v2-vl:free
NVIDIA: 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...
128,000
Context
128,000
Max output
<$0.01 / 1M
Prompt price
2025-10-28
Created
01 / Snapshot
Pricing, context, modalities, and parameters.
Model Radar detail pages stay neutral and operator-readable: core metadata first, then workflow fit.
| Provider | Nvidia | Input modalities | image, text, video |
|---|---|---|---|
| Output modalities | text | Prompt price | <$0.01 / 1M |
| Completion price | <$0.01 / 1M | Request price | N/A |
| Context length | 128,000 | Max completion tokens | 128,000 |
| Supported parameters | include_reasoning, max_tokens, reasoning, seed, temperature, tool_choice, tools, top_p | ||
Best for
nvidia/nemotron-nano-12b-v2-vl:free
NVIDIA: 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...
Deep analysis
Cross-modal work
High-volume usage
Coding workflows
vision
tool-capable
low-cost
03 / Colophon
Routes and exits.
Each model page stays simple: overview, compare, related models, then back to the public hub.