NVIDIA: Nemotron 3 Super

NVIDIA Developer Architecture Profile

Intelligence (ELO)1432Chatbot Arena Verified

Max Context262,144Tokens

API Cost / 1M$0.54Blended Prompt + Completion

Model Capabilities

Coding & Logic
Fictional

NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications. Built on a hybrid Mamba-Transformer...

Granular Pricing Matrix

Input Tokens (Prompt)$0.09 / 1M

Output Tokens (Completion)$0.45 / 1M

Pricing data via OpenRouter. Sync: 5/3/2026

Evaluate Competitors

VS Engine MatchupNVIDIA: Nemotron 3 Super vs NVIDIA: Nemotron Nano 12B 2 VL VS Engine MatchupNVIDIA: Nemotron 3 Super vs TheDrummer: Cydonia 24B V4.1 VS Engine MatchupNVIDIA: Nemotron 3 Super vs Tencent: Hunyuan A13B Instruct VS Engine MatchupNVIDIA: Nemotron 3 Super vs TNG: DeepSeek R1T2 Chimera VS Engine MatchupNVIDIA: Nemotron 3 Super vs xAI: Grok 3 Mini VS Engine MatchupNVIDIA: Nemotron 3 Super vs Qwen: Qwen3 8B