NVIDIA: Nemotron 3 Super

NVIDIA Developer Architecture Profile

Intelligence (ELO)1432Chatbot Arena Verified

Max Context1,000,000Tokens

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: 6/17/2026

Evaluate Competitors

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 Qwen: Qwen3 8B VS Engine MatchupNVIDIA: Nemotron 3 Super vs Reka Flash 3 VS Engine MatchupNVIDIA: Nemotron 3 Super vs MoonshotAI: Kimi K2.7 Code VS Engine MatchupNVIDIA: Nemotron 3 Super vs Qwen: Qwen3.7 Max