NVIDIA

Nemotron 3 Nano Omni (free)

by NVIDIAtext+image+audio+video->text1 endpoint

Overview

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...

Capabilities

Text generation
Image understanding
Audio processing
Video understanding
Tool use / Function calling
Extended reasoning
Long context
Top-P sampling
Deterministic seed

Modalities

Input
TextAudioImageVideo
Output
Text

Technical Specifications

Context Window
256K tokens
Max Output
65.5K tokens
Tokenizer
Other
Uptime (24h)
8913.7%

Supported Parameters

include_reasoningmax_tokensreasoningseedtemperaturetool_choicetoolstop_p

Pricing

Per 1M tokens
Free
Added
April 28, 2026
Last synced 9/16/2026