Skip to content

Cost to run

Nemotron-3 Super 120B

nvidia/nemotron-super-120b

Family
Nemotron
Context
131,072 tokens

Nemotron-3 Super 120B can be run self-hosted (rent a GPU + run vLLM/TGI) or through a serverless API (pay per token). Live pricing comparisons:

Need to benchmark this model against another? Try the calculator or see where it ranks on the InferenceScore leaderboard.