Profanity Filter and Moderation
**Profanity Moderation API** is a fast, deterministic text-moderation engine. Send a string and get back a structured decision: whether it's clean, an overall severity, the matched categories, the exact offending spans, and a censored copy of the text — with no AI, no database, and no data retention. ### Why this API - **Deterministic & auditable** — a rule-based engine, so the same input always…
1 subscribers
8.2/10 popularity
353 ms avg latency
100% success rate
4 endpoints
The in-depth APIMemo review for this API hasn't been published yet —
the data below comes straight from the public marketplace listing.
Profanity Filter and Moderation endpoints
| Method | Endpoint | Description |
|---|---|---|
| v1 | ||
| POST |
moderateTextV1 /v1/moderate |
|
| v2 | ||
| POST |
moderateTextV2 /v2/moderate |
|
| health | ||
| GET |
readiness /health/ready |
|
| GET |
health /health |
|
Profanity Filter and Moderation pricing
| Plan | Price | Rate limit | Quotas |
|---|---|---|---|
| BASIC | $5 / month | 10 / minute |
|
| PRO | $20 / month | 1000 / minute |
|
