Nemotron Nano 2 12B VL is
NVIDIA's language model with a 131K context window and up to 4K output tokens, available from 3 providers, starting at $0.100 / 1M input and $0.100 / 1M output. A 12B-parameter multimodal model from NVIDIA's Nemotron Nano 2 series using a hybrid Transformer-Mamba architecture for video and document understanding.
nvidia-nemotron-nano-2-12b-vl |
| Language |
| Active |
| 131K tokens |
| 4K tokens |
| ImageTextVideo |
| Text |
| default |
| 12B |
| · 6 months ago |
10.1#269 |
5.9#231 |
26.7#132 |
0.6#178 |
0.4#224 |
0.0#224 |
0.3#135 |
0.3#241 |
0.66s#212 |
0.2#242 |
0.3#132 |
0.2#165 |
0.0#261 |
0.2#194 |
151.8#44 |
Capabilities
Input3/5
✓
✓
·
✓
·
Output1/5
✓
·
·
·
·
Capabilities2/13
✓
·
✓
·
·
·
·
·
·
·
·
·
·
Pricing by Provider
| Provider | Standard | |
|---|---|---|
| Input $ / 1M | Output $ / 1M | |
Fireworks AI | $0.100 | $0.100 |
OpenRouter | $0.200 | $0.600 |
Vercel AI Gateway | $0.200 | $0.600 |
Cost Calculator
Preset:
Compares every provider & tier in USD