NVIDIA: Nemotron 3 Super

Nvidia

NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute ef

1M+ contextUltra-low cost
Text
Visit official site →Compare →

Specifications

VendorNvidia
Familynvidia
Context1M · 750k words（≈ a novella）
Max output1M · 750k words（≈ a novella）
Released2026-06-19
Open sourceNo
Tool use—

Pricing across channels

per 1M tokens, USD

ChannelTypeInputOutput→
OpenRouter (auto)Aggregator$0.090$0.45visitAd
OpenRouter API (auto-fetched)· 2026-06-19

Related models

Similar tier, vendor or price range

NVIDIA: Llama 3.3 Nemotron Super 49B V1.5
Nvidia
Intel. —$0.40/$0.40
NVIDIA: Nemotron 3 Nano 30B A3B
Nvidia
Intel. —$0.050/$0.20
NVIDIA: Nemotron 3.5 Content Safety (free)
Nvidia
Intel. —$0/$0
NVIDIA: Nemotron 3 Ultra (free)
Nvidia
Intel. —$0/$0