Nemotron 3 Nano Omni

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

Inference$ Commercial use

About Nemotron 3 Nano Omni

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

nemotronnvidiavideo-to-textvideo-understandingvideo-reasoningreasoning

Pricing

Coming soon. You can still browse this model's inputs below.

Inputs

prompttextarearequired

Text prompt to send to the model. English only.

system_prompttextarea

Optional system prompt to steer the model. Reasoning behavior is controlled by the separate `reasoning_mode` field.

reasoning_modeselectdefault: "no_think"

Whether the model should emit an explicit reasoning trace. `no_think` returns a direct answer; `think` returns chain-of-thought followed by the final answer.

Options: think, no_think

max_tokensintegerdefault: 1024

Maximum number of tokens to generate.

temperaturenumberdefault: 0.7

Sampling temperature. Lower is more deterministic.

top_pnumberdefault: 0.95

Nucleus sampling probability mass.

enable_safety_checkerbooleandefault: true

Whether to enable the safety checker.

video_urlfilerequired

URL of the video to reason about. mp4, up to 1080p, max 2 minutes.

More from Nemotron 3 Nano

Nemotron 3 Nano Omni

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

nemotronnvidia

audio-to-text

Nemotron 3 Nano Omni

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

nemotronnvidia

image-to-text

Nemotron 3 Nano Omni

Open, efficient reasoning model from NVIDIA. 30B A3B hybrid Transformer-Mamba MoE, built for enterprise agentic workflows.

nemotronnvidia

large-language-models

Related video to text models

OpenRouter [Video]

Run any video-capable LLM with fal. Analyze, summarize, and understand video files using Gemini (Google) models. Supports mp4, mpeg, mov, webm, and YouTube links. Powered by OpenRouter.

video-to-text

OpenRouter [Video][Enterprise]

Run any VLM (Video Language Model) with fal, powered by OpenRouter.

video-to-text

✦ new

NVIDIA Nemotron 3.5 Super Video

Ask NVIDIA Nemotron 3.5 Super about a video clip: summarize what happens, find moments and reason across frames.

video-understandingmultimodal

video-to-text