AI model · NVIDIA

nemotron-3-super-120b-a12b

NVIDIA: Nemotron 3 Super

Input costs $0.08 per million tokens and output costs $0.45. It takes up to 262,144 tokens of context at once. At 10 million tokens a month that works out to about $1.72. Listed in the catalogue on 3/12/2026.

Input$0.08
Output$0.45
Context262,144
Listed3/12/2026
OutputText
AcceptsText

You will only get news about this version (nemotron-3-super-120b-a12b).

What it costs a month

Token prices translated into real usage.

  • Light1M tokens a month — a personal tool or trial
    ₩235$0.17
  • Steady10M tokens a month — one small service
    ₩2,347$1.72
  • Heavy100M tokens a month — a service with real users
    ₩23,466$17.25

Mixed 75% input, 25% output — a common ratio for chat usage, though real cost depends on how you use it. Exchange rate is from the last collection.

Report card

What this model is good at, by subject.

This model has not been evaluated yet.

Community

Share what using it is actually like — the part the metrics do not show.

Would you recommend this model?
No links, 500 characters max. Reported notes are hidden automatically.Sign in
  • No notes yet. Be the first to share.

Buzz trend

How much this model was talked about over the past week.

Not enough observations yet. Collection runs hourly.

News about this model

No news about this model yet.

Other models from this vendor

Jump straight to where the conversation is.

ModelPerformanceInputOutputContext
nemotron-3.5-lightning13.6$0.08$0.20262K
nemotron-3-nano-30b-a3b$0.05$0.20262K

Compare with others

Pricing and scores side by side. Blank cells mean the price is undisclosed or the model did not take that test.