Nemotron 3 Nano Omni 30B A3B Reasoning · deepinfra

Nemotron 3 Nano Omni is an open multimodal model built on a hybrid Mixture-of-Experts (MoE) architecture, engineered for high efficiency and strong accuracy across image, video, audio, and text inputs. It powers always-on sub-agents for computer use, document intelligence, and audio-video understanding—replacing fragmented vision, speech, and language pipelines with a single unified inference pass.

Base modelAll models on this baseAll models of the providerto the provider

All NVIDIA models at every provider

Input, $/1M $0.20

Output, $/1M $0.80

Context 262 144

Accepts audio, images, text, video

Last checked 04.11.2026 12:00:14 UTC

Source —