Nemotron 3 Super

NVIDIA · nvidia/nemotron-3-super-120b-a12b

← Back to leaderboard

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...

Nemotron 3 Super ranks #108 of 348 models in the default AI Benchmark Hub order (quality first, then cost). At $0.24 blended per million tokens, it is cheaper than 79% of models with published API pricing. Its 262,144-token context window is about the catalog median (262,144 tokens).

open weightstexttext->text

Context

Max context: 262144
Max output: 16384

Pricing

Input / 1M: 0.08
Output / 1M: 0.40
Blend / 1M: 0.24

Quality

Quality index:

Provider

Provider: NVIDIA
Moderated: no

Monthly cost at this blended rate

Estimated API spend if every token is billed at $0.24per million (the blend of this model's input and output prices). Real bills depend on the input/output mix.

Tokens / monthEst. cost (USD)
1,000,000$0.24
10,000,000$2.42
100,000,000$24.25

Related models

Same lab, similar price, or similar quality — useful next comparisons.

Closest API price