nvidia/nemotron-3-nano-omni/video

Video reasoning variant of NVIDIA's Nemotron 3 Nano Omni. 30B A3B hybrid Transformer-Mamba MoE - accepts video plus a prompt and returns text.

Learn more about Nemotron

Inference

Commercial use

Schema

LLMs

Playground API Examples

Input

Prompt*

Video URL*

Hint: Drag and drop video files from your computer, video from web pages, paste from clipboard (Ctrl/Cmd+V), or provide a URL. Accepted file types: mp4, mov, webm, m4v, gif

Additional Settings

Customize your input with more control.

Result

Idle

A woman dressed in a navy blue blazer and white blouse stands in a studio setting with large softbox lights visible on either side of her. She begins by spreading her arms wide with palms facing up, then brings her hands together in front of her waist. As she speaks, she gestures with her hands, at one point raising her index finger to emphasize a point before clasping her hands again and smiling at the camera.

What would you like to do next?

{
  "output": "A woman dressed in a navy blue blazer and white blouse stands in a studio setting with large softbox lights visible on either side of her. She begins by spreading her arms wide with palms facing up, then brings her hands together in front of her waist. As she speaks, she gestures with her hands, at one point raising her index finger to emphasize a point before clasping her hands again and smiling at the camera.",
  "finish_reason": "stop",
  "usage": {
    "input_tokens": 4540,
    "output_tokens": 569
  }
}

Your request will cost $0.006 per 1000 token.

nvidia/nemotron-3-nano-omni/video

Input

Result

What would you like to do next?

Logs