All AI models · LLM benchmarks · Methodology

nemotron-nano-v2-12b

NVIDIA Nemotron Nano v2 12B is a 12-billion-parameter multimodal reasoning model designed for advanced video understanding, document intelligence, and visual reasoning, built with a hybrid Transformer-Mamba architecture for high efficiency and low latency.

Model facts

Context window
128K tokens
Maximum output
128K tokens
Cheapest paid input
$0.24 per 1M tokens
Cheapest paid output
$0.707 per 1M tokens
Open weights
no
Providers
1

Capabilities and modalities

reasoning, tool calling, structured output, attachments, text, image.

Observed price history

  • 2026-08-24: $0.24 input / $0.707 output per 1M tokens

API providers