RentGPU RentGPU
寻找 GPU →
by Nvidia

Nemotron-Content-Safety-3.5.

multimodal open weights 131K ctx
Cheapest input
$0.2/M
on DeepInfra
Cheapest output
$0.2/M
on DeepInfra
Hosted equiv.
~$0.07/hr
@ 100 tok/s on DeepInfra

Nemotron Content Safety 3.5 is a multimodal safety classifier developed by NVIDIA. A compact safety model that handles text, images, and custom policies. It outputs a safe/unsafe classification plus a reasoning trace, a

Where to use it

Cheapest hosted endpoints.

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

Frequently asked.

How do I run Nemotron-Content-Safety-3.5?
Nemotron-Content-Safety-3.5 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-Content-Safety-3.5?
Nemotron-Content-Safety-3.5 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-Content-Safety-3.5?
API pricing starts at $0.2/M input tokens and $0.2/M output tokens. Self-hosting cost depends on the GPU you rent — see the Run It Yourself tab.
Is Nemotron-Content-Safety-3.5 open-source or proprietary?
Nemotron-Content-Safety-3.5 is open-weight under the license. You can download and self-host it.