AI model · NVIDIA
Nemotron 3 Nano Omni (free)
Model ID: nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free
- Input
- Free per 1M tokens
- Output
- Free per 1M tokens
- Context
- 256K tokens at once
- Max output
- 66K tokens per reply
- Released
- 28 Apr 2026 NVIDIA
What it can do
- YesReasoning
- YesTool calling
- YesImage input
- YesOpen weights
- YesFree to use
Takes text, audio, image, video; gives text.
How its listing describes it
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...
Sources
- NVIDIA: Nemotron 3 Nano Omni (free) on OpenRouter — read 2 Oct 2026