NVIDIA Nemotron 3 Nano 30B A3B | LLM Models | HyperAI

NVIDIA Nemotron 3 Nano 30B A3B

NVIDIA2025-12-15

Model variants

At a glance:

Intelligence Index: —
Cost per task: —
Time per task: —
Output tokens per task: —
Input / output price per 1M tokens: $0.05 / $0.20
Cached input per 1M tokens: $0.05

Model variants

Reasoning effort	Intelligence	Cost per task	Time per task	Price / 1M tokens
Non-reasoning	—	—	—	$0.05 / $0.20
Reasoning	—	—	—	$0.05 / $0.20

Humanity's Last Exam
4.6%
CritPt
0.0%
AA-LCR v1.1: Long Context Reasoning
10.7%