NVIDIA: Nemotron 3 Super
NVIDIA Developer Architecture Profile
Intelligence (ELO)1432Aider: 36.8%
Max Context Limit262,144Max Out: 235,929 tokens
Prompt CachingStandardNo Cache Discount
Standard API / 1M$0.53Blended Standard Rate
Model Capabilities & Contract SLAs
- 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 (Standard Prompt)$0.08 / 1M
Output Tokens (Completion)$0.45 / 1M
Pricing data via OpenRouter. Sync: 10/2/2026
Evaluate Competitors
VS Engine MatchupNVIDIA: Nemotron 3 Super vs Tencent: Hy3 previewVS Engine MatchupNVIDIA: Nemotron 3 Super vs TheDrummer: Cydonia 24B V4.1VS Engine MatchupNVIDIA: Nemotron 3 Super vs Tencent: Hunyuan A13B InstructVS Engine MatchupNVIDIA: Nemotron 3 Super vs Qwen: Qwen3 8BVS Engine MatchupNVIDIA: Nemotron 3 Super vs Reka Flash 3VS Engine MatchupNVIDIA: Nemotron 3 Super vs OpenAI: GPT-6 Luna