NVIDIA: Nemotron 3 Super (free)
NVIDIA Developer Architecture Profile
Intelligence (ELO)1037Chatbot Arena Verified
Max Context Limit262,144Max Out: 235,929 tokens
Prompt CachingStandardNo Cache Discount
Standard API / 1MFREEBlended Standard Rate
Model Capabilities & Contract SLAs
- Free Tier
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)Free / 1M
Output Tokens (Completion)Free / 1M
Pricing data via OpenRouter. Sync: 10/2/2026
Evaluate Competitors
VS Engine MatchupNVIDIA: Nemotron 3 Super (free) vs TypeSafe: Jev RouterVS Engine MatchupNVIDIA: Nemotron 3 Super (free) vs Mistral: Mistral Small 4 (batch)VS Engine MatchupNVIDIA: Nemotron 3 Super (free) vs Dots Studio: Dots3-Note Preview (free)VS Engine MatchupNVIDIA: Nemotron 3 Super (free) vs Inference.net: Schematron V2 TurboVS Engine MatchupNVIDIA: Nemotron 3 Super (free) vs OpenRouter: FusionVS Engine MatchupNVIDIA: Nemotron 3 Super (free) vs OpenAI: gpt-oss-20b