Nemotron 3.5 Content Safety (free)
Nvidia · text, image → text
NVIDIA Nemotron 3.5 Content Safety is a compact 4B-parameter multimodal guardrail model fine-tuned from Google Gemma-3-4B. Featuring a 128,000 token context length, it is designed to moderate both inputs to and responses from LLMs and VLMs. This model provides an efficient safety layer to filter content and secure interactions across multiple modalities.
Input$0 /M
Output$0 /M