Content Moderation API
Keep toxic content out of your product before your users (or app store reviewers) ever see it. One call moderates any text — and tells you exactly what to do with it. Moderation is a feature you can't ship "later": one slur in a public comment section, one abusive username on a leaderboard, and you're dealing with churn, reports and store rejections. This API gives you a verdict in milliseconds,…
1 subscribers
2 endpoints
The in-depth APIMemo review for this API hasn't been published yet —
the data below comes straight from the public marketplace listing.
Content Moderation API endpoints
| Method | Endpoint | Description |
|---|---|---|
| Moderation | ||
| POST |
moderateUsername /moderate/username |
Validates a username (1-50 characters) against rule-based profanity matching and a curated list of reserved/staff terms per language (admin, moderator, support, official, root,… |
| POST |
moderateText /moderate/text |
Runs profanity detection (with leetspeak/homoglyph/spacing obfuscation normalization), ML-based toxicity scoring, and PII detection (email, phone, credit card, SSN, IP) over a… |
Content Moderation API pricing
| Plan | Price | Rate limit | Quotas |
|---|---|---|---|
| BASIC | Free | — |
|
| PRO Recommended | $15 / month | — |
|
| ULTRA | $49 / month | — |
|
| MEGA | $119 / month | — |
|
