EN Submit a tool

Nemotron 3 Nano Omni

Rank #103 free nvidia

nvidia/nemotron-3-nano-omni-30b-a3b-reasoning-20260428

Usage data date 2026-07-26 · updated daily

Usage and specs

Daily rank#103
Daily tokens27.3B
Daily requests1.3M
Daily change +18.4%
Context window256K
Released

What is Nemotron 3 Nano Omni

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 audio inputs and produces text output, enabling agents to perceive and reason across modalities in a single inference loop. Built on a hybrid MoE Transformer-Mamba architecture with Conv3D video layers and Efficient Video Sampling (EVS), it delivers approximately 2× higher throughput and 2.5× lower compute for video reasoning versus separate vision + speech pipelines. It supports up to 300K context length and a 16,384 reasoning budget, with extended thinking enabled via reasoning.enabled on OpenRouter.

Nemotron 3 Nano Omni capabilities

Input: Text、Audio、Image、Video   Output: Text

Reasoning output Reasoning Tool choice Tool use

Nemotron 3 Nano Omni API pricing

Free tier · Rate limits may apply — see provider termsFree

List prices in USD; see each provider’s site for current terms.