VISIONCommunity moderation that keeps up.
Forums, comment sections and social apps grow faster than their moderators. Detectivision checks every post, comment and avatar for the flags your rules name, and leaves the decisions to your team.
Each place, its flags
| Where | Type | Flags |
|---|---|---|
| Posts and comments | text_moderation | insult, hate, racism, sexism, sexual, self_harm |
| Usernames and bios | text_moderation | insult, hate, sexual |
| Avatars and images in posts | image_moderation | sexual, violence, hate |
Every account has these flags. GET /api/v1/flags lists the ones yours may send.
Check before it shows
Send each post or comment as it was written. A held comment can wait: with "async": true it costs half and its result comes by webhook.
Send self-harm to people
A post that raises self_harm needs someone who can help, not a silent removal. Route it to them.
Let moderators decide
Requests show in the dashboard’s Logs with your own actions, such as Approve, Hide or Ban, and your system gets each one by webhook.
A comment, held for review
curl https://api.detectivision.ai/api/v1/moderation \
-H "Api-Key: $DETECTIVISION_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"type": "text_moderation",
"input": "Great thread, but the guy above is an idiot.",
"async": true,
"metadata": { "commentId": "c_981", "threadId": 42 }
}'{
"id": 1043,
"type": "text_moderation",
"status": "queued",
"metadata": { "commentId": "c_981", "threadId": 42 }
}Without flags, every text flag of your account is checked. The result comes as a moderation.completed webhook, with your metadata in it.
Toxicity detection
Seven flags for toxic comments, instead of one score.
Hate speech detection
Hate, racism and sexism, each a flag of its own.
Self-harm detection
Posts where someone may need help.
Frequently asked
Which languages are supported?
Turkish and English. Text in other languages is checked, but the results are not reliable.
How do moderators work with it?
Every request shows in the dashboard’s Logs. You define your own actions, such as Approve or Ban; when a moderator takes one, your system gets a moderation.action webhook and carries it out. Detectivision never acts on your platform itself.
Can it handle a burst of comments?
Yes. Async requests wait their turn instead of being refused, so a burst of thousands of comments is checked shortly after it arrives.
What does a comment cost?
A text costs 1 credit per started 2,500 characters when the answer comes by webhook, and twice that when it comes at once. Asking for fewer flags never costs more.
Is there a free trial?
Yes. The plans, and the free trial, are on the pricing page.