nemotron-3.5-content-safety

nvidia/nemotron-3.5-content-safety

NVIDIA Build Card

Multilingual, multimodal model for detecting unsafe and toxic content.

Context Length

131,072 tokens

Input Pricing

Not published

Output Pricing

Not published

Recent Latency

No probes

Model Architecture & Limits

Canonical IDnvidia/nemotron-3.5-content-safety

Publisher / Originatornvidia

Model FamilyNemotron

ArchitectureTransformer (Decoder-only)

Context Window Limit131,072 tokens

Max Output Tokens4,096 tokens

Endpoint Protocolopenai-chat

Capabilities & Modal Surfaces

Chat Conversation✓ Yes

Tool / Function Calling✕ No

Reasoning / Thinking✕ No

Structured Output (JSON)✓ Yes

Vision / Multimodal✓ Yes

Audio Processing✕ No

License & Restrictions

**Governing Terms:** Use of the model is governed by the [OpenMDW License Agreement, version 1.1 (OpenMDW-1.1)](https://raw.githubusercontent.com/OpenMDW/OpenMDW/refs/heads/main/1.1/LICENSE.OpenMDW-1.1), [Gemma Terms of Use](https://ai.google.dev/gemma/terms) and [Gemma Prohibited Use Policy](https:

Commercial and research use permitted under governing model and API terms.