NVIDIA
Nemotron Nano 12B v2 VL
Nemotron multimodal model for visual reasoning and agentic AI workflows
Model facts
- Context window
- 128K tokens
- Maximum output
- 131K tokens
- Cheapest paid input
- $0.2 per 1M tokens
- Cheapest paid output
- $0.6 per 1M tokens
- Open weights
- yes
- Providers
- 3
Capabilities and modalities
reasoning, tool calling, attachments, temperature control, open weights, text, image, video.
Artificial Analysis benchmarks
Compare this model on the full LLM benchmark leaderboard.
| Configuration | AAI | Coding | Math | Output tokens/s |
|---|---|---|---|---|
| Reasoning | 8.8 | not measured | 75.0 | 39.9 |
| Non-reasoning | 4.2 | not measured | 26.7 | 110.3 |
Observed price history
- 2026-08-24: $0.2 input / $0.6 output per 1M tokens
API providers
- Nvidia — model id nvidia/nemotron-nano-12b-v2-vl; free input / free output per 1M tokens; provider documentation
- DigitalOcean — model id nemotron-nano-12b-v2-vl; $0.2 input / $0.6 output per 1M tokens; provider documentation
- Vercel AI Gateway (Nvidia) — model id nvidia/nemotron-nano-12b-v2-vl; $0.2 input / $0.6 output per 1M tokens; provider documentation