N
NVIDIA

Nemotron 3 Super pricing & price history

reasoningtoolsnvidia/nemotron-3-super-120b-a12b

Nemotron 3 Super by NVIDIA costs $0.08 per 1M input tokens and $0.45 per 1M output tokens, with a 262K token context window.

$0.08Input / 1M tokens
$0.45Output / 1M tokens
262KContext window
12.8Intelligence index · coding 37.7

Price history

$0.000$0.259$0.517 2026-09-24today input /1M output /1M

No price changes since tracking began on 2026-09-24. We check hourly.

Cost calculator

Cheaper alternatives to Nemotron 3 Super

ModelInputOutputContextIntel.
$0.018$0.09131K9compare
$0.05$0.15131K3.8compare
$0.05$0.20262K8.9compare
I
$0.06$0.18262K24.6compare
I
$0.06$0.18262K22.6compare
$0.10$0.10131K4.8compare
I
Granite 4.2 8B
IBM Granite
$0.06$0.25131K11.1compare
$0.08$0.20262K12.9compare

About Nemotron 3 Super

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...

FAQ

How much does Nemotron 3 Super cost?

Nemotron 3 Super by NVIDIA costs $0.08 per 1M input tokens and $0.45 per 1M output tokens, with a 262K token context window. A typical request with 2,000 input and 500 output tokens costs about $0.0004.

What is the context window of Nemotron 3 Super?

Nemotron 3 Super supports up to 262,144 tokens of context and up to 235,929 output tokens per request.

Has Nemotron 3 Super’s price changed?

No price changes recorded since ModelBank started tracking it on 2026-09-24.

Is Nemotron 3 Super being deprecated?

No retirement date has been announced for Nemotron 3 Super as of 2026-09-24.

What are cheaper alternatives to Nemotron 3 Super?

Cheaper options include gpt-oss-20b ($0.018/$0.09), Gemma 3 12B ($0.05/$0.15), Nemotron 3 Nano 30B A3B ($0.05/$0.20), Ling 3.0 Flash VL ($0.06/$0.18).