Skip to content
AnyRouter

Nemotron 3.5 Content Safety

Free
nvidia/nemotron-3.5-content-safety

128K context · Jun 2026 · 4 upstreams

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.

context
128K
input / 1M
$0
output / 1M
$0
routes
4
speed, 24h
—

Upstreams

4
  1. 1NVIDIAPlatform · freeFreeTPS —TTFT ——
  2. 2AIHubMixYour key · not addedyour planTPS —TTFT ——
  3. 3NVIDIAYour key · not addedyour planTPS —TTFT ——
  4. 4OpenRouterYour key · not addedyour planTPS —TTFT ——
  • Up
  • No traffic
  • Down

Try it

Send a prompt

Details

Owner
NVIDIA
Kind
Vision
Released
Jun 2026
Context
128K
Data policy
Provider retention
Endpoint
/api/v1/chat/completions

Quick start

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."
    }
  ]
}'