Model Terminal

NVIDIA Nemotron 3.5 Content Safety

Nemotron 3.5 Content Safety is a compact 4B-class multimodal guardrail model from NVIDIA that classifies text and image inputs as safe or unsafe, supports custom safety policy enforcement, and returns optional reasoning traces for auditable moderation of AI pipelines. Source: supabase.

Value score
Not scored
Context
tokens
Max output
tokens
Price

Capability radar

Peer value bars

Identity

Developer
NVIDIA
Openness
Modalities
Release
Knowledge cutoff
Deprecation
API docs

Benchmarks

No benchmark scores yet.

Compare nearby

Pricing

Input / 1M
Output / 1M
Speed