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 Mam

Creator: NVIDIA
Lifecycle: Active
Context: 262.1K
Max output: —
Released: Mar 11, 2026
Status: unknown

Input: $0.10 / 1M tokens
Output: $0.50 / 1M tokens
Cached read: $0.10 / 1M tokens
Cached write: — / 1M tokens
Batch discount: —%
Source: OpenRouter
Verified: Apr 5, 2026 (High)

Capabilities

Modalities: text→text
Capabilities: reasoningpromptCachingfunctionCallingstructuredOutputs

Official Links

Intro

https://openrouter.ai/nvidia/nemotron-3-super-120b-a12b

Docs

https://openrouter.ai/nvidia/nemotron-3-super-120b-a12b

Pricing

https://openrouter.ai/models

Benchmark Coverage

Benchmark	Version	Score	Date	Source	Notes

Release History

Release	Alias	Lifecycle	Release Date	Deprecation	Shutdown	Summary
Nemotron 3 Super	nvidia-nemotron-3-super-120b-a12b	Active	Mar 11, 2026	—	—	Model available via OpenRouter.

Host Coverage

Host	Type	Context	Pricing Note	Differences
OpenRouter	aggregator	262.1K	$0.10/1M in · $0.50/1M out via OpenRouter	—

Migration Guidance

Change Events

Date	Type	Title	Description	Source
Mar 11, 2026	family_added	Nemotron 3 Super published	Model made available via OpenRouter.	OpenRouter

Other models from NVIDIA

Llama 3.1 Nemotron 70B Instruct, Llama 3.1 Nemotron Ultra 253B v1, Llama 3.3 Nemotron Super 49B V1.5, Llama Nemotron Super 49B, Llama Nemotron Ultra 253B, Nemotron 3 Nano 30B A3B, Nemotron 3 Nano 30B A3B, Nemotron 3 Super, Nemotron Nano 12B 2 VL, Nemotron Nano 12B 2 VL, Nemotron Nano 9B V2, Nemotron Nano 9B V2