← Back to Directory

NVIDIA: Nemotron Nano 12B 2 VL

NVIDIA Developer Architecture Profile

OpenRouter ↗HuggingFace ↗
Intelligence (ELO)1432Chatbot Arena Verified
Max Context131,072Tokens
API Cost / 1M$0.80Blended Prompt + Completion

Model Capabilities

  • Coding & Logic
  • Fictional
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 Mamba’s...

Granular Pricing Matrix

Input Tokens (Prompt)$0.20 / 1M
Output Tokens (Completion)$0.60 / 1M

Pricing data via OpenRouter. Sync: 4/30/2026

Evaluate Competitors

VS Engine MatchupNVIDIA: Nemotron Nano 12B 2 VL vs NVIDIA: Nemotron 3 SuperVS Engine MatchupNVIDIA: Nemotron Nano 12B 2 VL vs TheDrummer: Cydonia 24B V4.1VS Engine MatchupNVIDIA: Nemotron Nano 12B 2 VL vs Tencent: Hunyuan A13B InstructVS Engine MatchupNVIDIA: Nemotron Nano 12B 2 VL vs TNG: DeepSeek R1T2 ChimeraVS Engine MatchupNVIDIA: Nemotron Nano 12B 2 VL vs xAI: Grok 3 MiniVS Engine MatchupNVIDIA: Nemotron Nano 12B 2 VL vs Qwen: Qwen3 8B