Content Moderation

Content Moderation API

Vettly is decision infrastructure for text, images, and video.

One request, consistent decisions, and policy control you can version in code.

What it detects

  • • Hate & harassment
  • • Sexual content
  • • Violence & self-harm
  • • Spam & bots
  • • Scams & fraud
  • • Custom rules

Why developers choose Vettly

  • • One endpoint for text, image, and video
  • • App Store compliant - meets Guideline 1.2
  • • Policies in YAML with versioning
  • • Webhooks, dashboards, and evidence trails
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 generic NLP APIs

Vettly returns clear decisions, categories, and actions without extra classification glue code.

Keep exploring

OpenAI Moderation Alternative

Keep OpenAI speed while adding workflows, images, and video.

UGC Moderation API

Moderate posts, comments, profiles, and media at scale.

React Native Moderation API

Add moderation to React Native apps without custom backend glue.

Swift Moderation API

Moderation infrastructure for native Swift and iOS teams.

Get an API key

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

Get an API key