by Nvidia

Nemotron-3-Nano-Omni-30B-A3B-Reasoning.

multimodal open weights laptop+ 30B params 262K ctx
Cheapest input
$0.2/M
on DeepInfra
Cheapest output
$0.8/M
on DeepInfra
Smallest GPU
1× Nvidia RTX 4000 Ada SFF
$0.17/hr

Nemotron 3 Nano Omni is an open multimodal model built on a hybrid Mixture-of-Experts (MoE) architecture, engineered for high efficiency and strong accuracy across image, video, audio, and text inputs. It powers always-o

Smallest GPU to run it See all quantisations →

1× Nvidia RTX 4000 Ada SFF · $0.17/hr.

Most-aggressive quantisation we have a working recommendation for. Lower precision = less VRAM = cheaper hardware, at a small accuracy cost.

Where to use it

Cheapest hosted endpoints.

Provider Access $/M in $/M out
DeepInfra hosted inference $0.2 $0.8 Launch ↗
FAQ

Frequently asked.

How do I run Nemotron-3-Nano-Omni-30B-A3B-Reasoning?
Nemotron-3-Nano-Omni-30B-A3B-Reasoning is open-weight, so you can self-host on rented GPUs. See the Run It Yourself tab for GPU configurations + cost estimates, or use one of the hosted inference providers listed on this page.
Where can I access Nemotron-3-Nano-Omni-30B-A3B-Reasoning?
Nemotron-3-Nano-Omni-30B-A3B-Reasoning is available via DeepInfra. Each access option lists its own pricing (per million tokens or hourly hosting).
How much does it cost to run Nemotron-3-Nano-Omni-30B-A3B-Reasoning?
API pricing starts at $0.2/M input tokens and $0.8/M output tokens. Self-hosting cost depends on the GPU you rent — see the Run It Yourself tab.
Is Nemotron-3-Nano-Omni-30B-A3B-Reasoning open-source or proprietary?
Nemotron-3-Nano-Omni-30B-A3B-Reasoning is open-weight under the license. You can download and self-host it.