AI Content Moderator
### 🛡️ Protect Your Platform - 80% of Features are FREE The most **cost-effective content moderation API** on the market. Detect toxicity, spam, profanity, and PII with industry-leading accuracy. Most features use efficient pattern matching - **no AI cost** for basic moderation. ### Why 500+ Developers Choose Us | Feature | Speed | Cost | |---------|-------|------| | PII Detection | <100ms |…
6 subscribers
12 endpoints
The in-depth APIMemo review for this API hasn't been published yet —
the data below comes straight from the public marketplace listing.
AI Content Moderator endpoints
| Method | Endpoint | Description |
|---|---|---|
| Info | ||
| GET |
root__get / |
Get API information and available endpoints. |
| Health | ||
| GET |
health_check_healthz_get /healthz |
Check if the API is healthy and running. |
| Moderation | ||
| GET |
list_languages_v1_languages_get /v1/languages |
List supported languages. |
| POST |
moderate_batch_v1_moderate_batch_post /v1/moderate/batch |
Analyze multiple pieces of content in a single request. Maximum 100 items per batch. |
| POST |
filter_profanity_v1_profanity_filter_post /v1/profanity/filter |
Filter profanity from content. **100% FREE - No AI cost!** Detects and optionally replaces profane words with asterisks or clean alternatives. |
| POST |
analyze_toxicity_v1_toxicity_analyze_post /v1/toxicity/analyze |
Analyze content for toxicity using AI. **Uses Gemini AI - Premium feature** Detects harassment, hate speech, threats, insults, and more. |
| POST |
analyze_spam_v1_spam_analyze_post /v1/spam/analyze |
Analyze content for spam indicators. **FREE with pattern matching!** Detects promotional language, solicitation, urgency, money mentions, etc. |
| POST |
detect_pii_v1_pii_detect_post /v1/pii/detect |
Detect and mask personally identifiable information. **100% FREE - No AI cost!** Detects: emails, phone numbers, SSN, credit cards, IP addresses, etc. |
| POST |
moderate_content_v1_moderate_post /v1/moderate |
Analyze content for toxicity, spam, profanity, PII, and more. This endpoint combines multiple moderation checks. Use the `checks` parameter to specify which checks to run.… |
| GET |
list_pii_types_v1_pii_types_get /v1/pii/types |
List all supported PII types. |
| POST |
analyze_sentiment_v1_sentiment_analyze_post /v1/sentiment/analyze |
Analyze content sentiment using AI. **Uses Gemini AI - Premium feature** Returns sentiment (positive/negative/neutral/mixed), emotions, and aspects. |
| POST |
check_policy_v1_policy_check_post /v1/policy/check |
Check content against custom policy rules. **100% FREE - No AI cost!** Define your own rules using regex patterns or keyword lists. |
AI Content Moderator pricing
| Plan | Price | Rate limit | Quotas |
|---|---|---|---|
| BASIC | Free | — |
|
| PRO | $9.99 / month | — |
|
| ULTRA | $29.99 / month | — |
|
| MEGA | $59.99 / month | — |
|
