← All models
N
NVIDIA: Nemotron 3 Nano Omni (free)
nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free
VisionTool useReasoningStreaming
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...
Specs
Context
256,000 tokens
Input
text, audio, image, video
Output
text
Released: 2026-04
Supported parameters
include_reasoningmax_tokensreasoningseedtemperaturetool_choicetoolstop_p