NVIDIA Nemotron 3 Ultra (550B-A55B)
Knows up to September 2025Missing 1,990 events
nvidia/nemotron-3-ultra-550b-a55b
$0.60 in, $2.40 out per 1M tokens
NVIDIA Nemotron 3 Nano Omni (30B-A3B Reasoning)
Small open model for video/speech analysis, document intelligence and GUI agents.
Model idnvidia/nemotron-3-nano-omni-30b-a3b-reasoning
PricePrice not published
Checked29 September 2026
No published training cutoff
At least1,864events since its release on 28 April 2026
83 historic, 426 major. 199 days of news.
NVIDIA doesn’t publish a training cutoff, so we count from its release date. The real gap is larger.
How to call it
3 ways to use NVIDIA Nemotron 3 Nano Omni (30B-A3B Reasoning), with the model id each provider expects.
| Provider | Model id | Endpoint | Docs |
|---|---|---|---|
| NVIDIA API (build.nvidia.com) | nvidia/nemotron-3-nano-omni-30b-a3b-reasoning |
https://integrate.api.nvidia.com/v1/chat/completions |
build.nvidia.com |
| OpenRouter | nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free |
openrouter.ai | |
| Hugging Face | huggingface.co |
Pricing
Price not published.
No price source linked. Checked 29 September 2026.
Specs
- Input
- Text, images, audio and video
- Output
- Text
- Context window
- 256,000 tokens
- Max output
- Not published
- Open weights
- Yes
- Licence
- NVIDIA Open Model Agreement
- Training cutoff
- Not published
- Released
- 28 April 2026
- Status
- Current
- Type
- Multimodal model
What stands out
What its maker marketed at launch, and what people found later, each with its source.
Open omni-modal reasoning (video + audio + image)
Single 3B-active open model reasoning over video (up to ~2 min), audio, images and text with chain-of-thought on by default.
ASR with word timestamps, OCR, GUI automation
Targets transcription with word-level timestamps, document intelligence/OCR and GUI agent workflows.
Notes
Also FP8/NVFP4 repos. Knowledge cutoff not published.
curl https://integrate.api.nvidia.com/v1/chat/completions -H "Authorization: Bearer $NVIDIA_API_KEY" -H "Content-Type: application/json" \
-d '{"model":"nvidia/nemotron-3-nano-omni-30b-a3b-reasoning","messages":[{"role":"user","content":"Describe this image"}]}'
Sources: https://huggingface.co/nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16 , https://integrate.api.nvidia.com/v1/models
Not yet checked against an official source: Only free OpenRouter variant seen; paid pricing not verified.