AI Content Moderator
AI Content Moderator API provides comprehensive text moderation with 6 endpoints. Features include: profanity detection with leetspeak and obfuscation handling, toxicity scoring across 5 categories (hate speech, threats, insults, sexual content, self-harm), spam detection with 17 heuristic indicators and combo multiplier scoring, PII detection (email, phone, credit card with Luhn validation,…
AI Content Moderator endpoints
| Method | Endpoint | Description |
|---|---|---|
| POST |
Full Content Moderation /api/moderate |
Analyze text for profanity, toxicity, spam, PII, and sentiment in a single request. Returns detailed scores and matches for each category. |
| POST |
Profanity Detection /api/profanity |
Quick profanity check. Detects swear words, leetspeak variants, obfuscated profanity, and stretched characters with severity scoring. |
| POST |
Toxicity Analysis /api/toxicity |
Analyze text for toxic content across 5 categories: hate speech, threats, insults, sexual content, and self-harm references. |
| POST |
Spam Detection /api/spam |
Detect spam content using 12 heuristic indicators including excessive caps, URL density, urgency language, scam patterns, and more. |
| POST |
PII Detection /api/pii |
Detect personally identifiable information (PII) including emails, phone numbers, credit cards (with Luhn validation), SSNs, and IP addresses. Returns masked values. |
| POST |
Sentiment Analysis /api/sentiment |
Analyze text sentiment with AFINN-based lexicon scoring. Returns positive, negative, or neutral label with confidence score. Supports negation and intensifier handling. |
AI Content Moderator pricing
| Plan | Price | Rate limit | Quotas |
|---|---|---|---|
| BASIC | Free | — |
|
| PRO Recommended | $10 / month | 5 / second |
|
| ULTRA | $50 / month | 10 / second |
|
| MEGA | $100 / month | 20 / second |
|