AI Safety

How to Moderate AI-Generated Images

Block unsafe generations before users see them.

CSAM signals, NSFW, deepfakes, and policy violations - all in one image check.

What it detects

• CSAM signals
• NSFW & nudity
• Violence & gore
• Deepfake patterns
• Hate symbols
• Custom rules

Why developers choose Vettly

• Same API for upload and generation flows
• CSAM signal detection included
• Sub-500ms image decisions
• Audit trails for compliance

Example request

bash

curl -X POST https://api.vettly.dev/v1/check \
  -H "Authorization: Bearer YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{"content": "https://example.com/image.jpg", "contentType": "image"}'

Example response

json

{
  "flagged": true,
  "action": "review",
  "categories": {
    "sexual": 0.88,
    "violence": 0.04
  },
  "policy": "marketplace-safe",
  "latency_ms": 318
}

Compared to model-side safety filters

Model-side filters are evaded routinely. Vettly runs as an independent check after generation, before display.

Keep exploring

Content Moderation API

One endpoint for text, image, and video moderation.

Image Moderation API

Policy-driven image checks with clear allow, review, and block actions.

Video Moderation API

Async video moderation without stitching together multiple vendors.

Content Moderation in Next.js

Add content moderation to a Next.js App Router project in minutes. Server-side API routes, React Server Components, and edge runtime examples.

Get an API key

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