NVIDIA: Nemotron 3 Nano Omni (free)
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...
Everything else
| Max output | 66K |
|---|---|
| Input / 1M | free |
| Output / 1M | free |
| Cache read / 1M | — |
| Cache write / 1M | — |
| 1M in + 1M out | free |
| Takes | text, audio, image, video |
| Returns | text |
| Tools | yes |
| Reasoning | optional |
| Open weights | yes |
| Released | 2026-04-28 |
| Knowledge cutoff | — |
| Retires | — |
| Catalog id | nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free |
Using it
In 00, this model is picked per agent — and per tier, so the model that answers your customers need not be the one that writes your code. Get 00.