All AI models · LLM benchmarks · Methodology

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.

ConfigurationAAICodingMathOutput tokens/s
Reasoning8.8not measured75.039.9
Non-reasoning4.2not measured26.7110.3

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