# Nemotron 3.5 Content Safety

> A compact 4B-parameter multimodal guardrail model fine-tuned from Google Gemma-3-4B. It moderates both inputs to and responses from LLMs and VLMs, returning a safe/unsafe classification, safety category labels, and optional reasoning. Served via NVIDIA NIM.

**ID**: `nvidia/nemotron-3.5-content-safety`  
**Creator**: nvidia  
**Category**: multimodal  
**Context**: 128K tokens  
**Input**: $0  
**Output**: $0  
**Released**: 2026-06-04  
**Web page**: https://anyrouter.dev/model/nvidia/nemotron-3.5-content-safety

**Input modalities**: text, image  
**Output modalities**: text  

**Tokenizer**: Gemma

**Capabilities**: chat, streaming, vision

## Usage

**Endpoint**: `POST https://anyrouter.dev/api/v1/chat/completions`

```bash
curl https://anyrouter.dev/api/v1/chat/completions \
  -H "Authorization: Bearer $ANYROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "nvidia/nemotron-3.5-content-safety",
  "messages": [
    {
      "role": "user",
      "content": "Say hi in 3 words."
    }
  ]
}'
```

## Providers

| Provider | Input | Output |
| --- | --- | --- |
| aihubmix-byok | $0 | $0 |
| nvidia | $0 | $0 |
| nvidia-byok | $0 | $0 |
| hue | $0 | $0 |
| openrouter-byok | $0 | $0 |

## Source

- Upstream docs: https://build.nvidia.com/nvidia/nemotron-3.5-content-safety