Marketplace moderation for every listing.

Each place, its flags

bad_habits finds drug use, drinking, smoking or gambling talked up. Every account has these flags; GET /api/v1/flags lists the ones yours may send.

1. 01

   Before a listing goes live

   Check its photos and its text together, and hold it when anything is flagged.

2. 02

   In bulk

   Send imports and the listings already online with "async": true: they cost half, and each result comes by webhook.

3. 03

   Tied to the listing

   metadata carries your listing and seller ids into the answer, Logs and every webhook, so an action lands on the right listing.

Check a listing photo

curl https://api.detectivision.ai/api/v1/moderation \
  -H "Api-Key: $DETECTIVISION_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "type": "image_moderation",
    "input": "https://example.com/listings/7731/1.jpg",
    "mode": "detect",
    "metadata": { "listingId": 7731, "sellerId": "s_204" }
  }'

{
  "id": 7120,
  "type": "image_moderation",
  "mode": "detect",
  "status": "completed",
  "flagged": true,
  "flags": [{ "flag": "scam", "confidence": 0.83 }],
  "checked": ["hate", "scam", "sexual", "violence"],
  "unchecked": [],
  "tookMs": 1310,
  "usage": { "charged": 2, "remaining": 9998 },
  "metadata": { "listingId": 7731, "sellerId": "s_204" }
}

Without flags, every image flag of your account is checked, for the price of one image.

• NSFW detection →

  Nudity and sexual content in listing photos.

• Violence detection →

  Violent images, before they are posted.

• Hate speech detection →

  Hate, racism and sexism in reviews and messages.