Nemotron 3.5 Content Safety (free)

Name: Nemotron 3.5 Content Safety (free)
Brand: NVIDIA

byNVIDIA

NVIDIA Nemotron 3.5 Content Safety is a compact 4B-parameter multimodal guardrail model from NVIDIA, fine-tuned from Google Gemma-3-4B. It moderates both inputs to and responses from LLMs and VLMs, accepting...

Chat withNemotron 3.5 Content Safety (free)

Input PriceFree

Output PriceFree

Context Window128,000 tokens

Modalitiestext, image

Specifications

Technical details and pricing.

ProviderNVIDIA

Context Window128,000 tokens

Release DateJun 4, 2026

ModalitiesText, Image → Text

CapabilitiesVision

Frequently Asked Questions

What is Nemotron 3.5 Content Safety (free) good for?

Use Nemotron 3.5 Content Safety (free) for everyday tasks like writing, summarizing, brainstorming, and getting clear explanations.

How much does Nemotron 3.5 Content Safety (free) cost?

Pricing is based on usage. Current rates are Free for input and Free for output.

Can I try Nemotron 3.5 Content Safety (free) for free?

Yes. You can start a chat instantly and test the model before deciding on a plan.

Does Nemotron 3.5 Content Safety (free) support images or audio?

Nemotron 3.5 Content Safety (free) can understand images.

Similar Models

Other models you might want to explore.

Nemotron 3 Ultra (free)

NVIDIA

NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it...

Details →

Nemotron 3 Super (free)

NVIDIA

NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications. Built on a hybrid Mamba-Transformer...

Details →

Nemotron 3 Nano 30B A3B (free)

NVIDIA

NVIDIA Nemotron 3 Nano 30B A3B is a small language MoE model with highest compute efficiency and accuracy for developers to build specialized agentic AI systems. The model is fully...

Details →

Pricing, context, and capability data are based on the live model catalog.