All models
nvidiaContext 1M

NVIDIA: Nemotron 3 Ultra (free)

Current listing unconfirmed

The latest catalog could not be confirmed. These are previously recorded details, not a guarantee that this model is currently available.

Input
Text
Output
Text
Served by
OpenRouter
Last observed
Oct 26, 2026, 8:33 AM UTC

NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it...

More from nvidia

NVIDIA Nemotron™ 3 Nano Omni is a 30B-A3B open multimodal model designed to function as a perception and context sub-agent in enterprise agent systems. It accepts text, image, video, and...

VisionAudioOpenRouter
Chat

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...

OpenRouter
Chat

NVIDIA Nemotron 3.5 Content Safety is a compact 4B-parameter multimodal guardrail model from NVIDIA, fine-tuned from Google Gemma-3-4B. It moderates both inputs to and responses from LLMs and VLMs, accepting...

VisionOpenRouter
Chat