token.app › NVIDIA › Nemotron Nano 12B 2 VL (free)

Nemotron Nano 12B 2 VL (free) pricing & benchmarks

Nemotron Nano 12B 2 VL (free) is available from NVIDIA at Free per million input tokens and Free per million output tokens (Free blended at 3:1). It accepts up to 128,000 tokens of context. 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…

Pricing
Per million tokens · OpenRouter
InputFree
OutputFree
Blended (3:1)Free
Specification
nvidia/nemotron-nano-12b-v2-vl:free
Context window128K
Max output128K
ReleasedOct 2025
LicenceOpen weights
Modalitiesin:text, in:image, in:video, out:text
No independently-run benchmark scores are published for Nemotron Nano 12B 2 VL (free) yet. We show nothing rather than reprinting an unverified figure.
Compare Nemotron Nano 12B 2 VL (free)
Nemotron Nano 12B 2 VL (free) vs Qwen3.8 Max Nemotron Nano 12B 2 VL (free) vs DeepSeek V4 Flash 0731 Nemotron Nano 12B 2 VL (free) vs Claude Opus 5 Nemotron Nano 12B 2 VL (free) vs Gemini 3.6 Flash Nemotron Nano 12B 2 VL (free) vs Kimi K3 Nemotron Nano 12B 2 VL (free) vs GPT-5.6 Luna Nemotron Nano 12B 2 VL (free) vs GPT-5.6 Terra Nemotron Nano 12B 2 VL (free) vs GPT-5.6 Sol
FAQ
How much does Nemotron Nano 12B 2 VL (free) cost?
Nemotron Nano 12B 2 VL (free) costs Free per million input tokens and Free per million output tokens on OpenRouter. At a 3:1 input:output mix that blends to Free per million tokens.
What is Nemotron Nano 12B 2 VL (free)'s context window?
Nemotron Nano 12B 2 VL (free) accepts up to 128,000 tokens of context, and can generate up to 128,000 output tokens.