AI Moderation

AI Content Moderation API

Use AI to evaluate content with clear, deterministic actions.

Deploy policies once and apply them across every content type.

What it detects

  • • Text, images, and video
  • • Hate & harassment
  • • Sexual content
  • • Violence & self-harm
  • • Spam & scams
  • • Custom rules

Why developers choose Vettly

  • • Consistent action schema
  • • Policy thresholds you control
  • • Audit-friendly decision logs
  • • Developer plan to start and scale
Example request
bash
curl -X POST https://api.vettly.dev/v1/check \
  -H "Authorization: Bearer YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{"content": "You are terrible.", "contentType": "text"}'
Example response
json
{
  "flagged": true,
  "action": "block",
  "categories": {
    "harassment": 0.93,
    "hate": 0.02
  },
  "policy": "default",
  "latency_ms": 142
}

Compared to LLM-only checks

Vettly is purpose-built for decision workflows with clear actions and policy control.

Keep exploring

Vettly Guardian

Focused safety moments, Conversation Coach, and visible Companion pairing for teen families.

Vettly Bridge for Mac

Optional Mac-assisted iPhone safety signals from a visible Finder backup.

Bark Alternative

An honest Vettly-vs-Bark comparison: visible safety, calm moments, and a free forever tier.

Get an API key

Start making decisions in minutes with a Developer plan and clear upgrade paths.

Get an API key