Home/Models/Nemotron 3.5 Content Safety
NVIDIA logo

Nemotron 3.5 Content Safety

by NVIDIA · Released Jun 2026

Multimodal
Compare
Context
131K tokens (~66 books)
Input $/1M
$0.20
Output $/1M
$0.20
Type
multimodal
License
Proprietary
Benchmarks
0 tested
Data updated today
About

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...

No benchmark data available yet.

Links
Documentation
Community
BenchGecko API
nemotron-3-5-content-safety
Specifications
  • Typemultimodal
  • Context131K tokens (~66 books)
  • ReleasedJun 2026
  • LicenseProprietary
  • StatusActive
  • Cost / Message~$0.001
Available On
NVIDIA logoNVIDIA$0.20
Share & Export
Tweet
Nemotron 3.5 Content Safety is a proprietary multimodal AI model by NVIDIA, released in June 2026. Context window: 131K tokens.