Nemotron 3.5 Content Safety: Customizable Multimodal Safety for Global Enterprise AI

Back to Articles

What's New in Nemotron 3.5 Content Safety 1. Unified Multimodal Evaluation 2. Global Language Coverage 3. Custom Policy Enforcement 4. Reasoning Traces (THINK Mode) 5. Safety Dataset Model Architecture Reasoning Training Data Benchmarking Latency Addressing the Benchmark Gap Getting Started The last two years have seen NVIDIA's content safety stack grow from a focused English text classifier into a family of specialized models—each extending coverage to new modalities, languages, and inference modes. Nemotron 3 Content Safety, released in March 2026, combined multimodal and multilingual capabilities for the first time in a single 4B-parameter model. Today, we are releasing Nemotron 3.5 Content Safety, which completes that arc: a single model that unifies multimodal input, multilingual reach, custom enterprise policy enforcement, and auditable reasoning into one inference call.

This post covers what changes in 3.5, the design decisions behind each new capability, and how to integrate the model into production safety pipelines.

What's New in Nemotron 3.5 Content Safety

1. Unified Multimodal Evaluation