Model dossier

NVIDIA: Nemotron 3.5 Content Safety

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...

ProviderNVIDIA Start comparison

Context131,072

Max output117,964

Pricing viewTVP price

Identity

NVIDIA: Nemotron 3.5 Content Safety

Model ID: nvidia/nemotron-3.5-content-safety
Canonical slug: nvidia/nemotron-3.5-content-safety-20260604
Knowledge cutoff: n/a
Created: 6/4/2026

Capabilities

textimagestructured

Modalities

text+image->texttextimage

Capacity

Context131,072

Max output117,964

TokenizerOther