GuardRails Content Safety API
GuardRails scans text for sensitive content before it reaches your users or leaves your system. It detects PII (Social Security numbers, phone numbers, email addresses, physical addresses, names) with confidence scoring, checks content against HIPAA, GDPR, and PCI-DSS compliance profiles, detects crisis signals like self-harm or violence language, and analyzes cultural sensitivity across…
1 subscribers
5 endpoints
The in-depth APIMemo review for this API hasn't been published yet —
the data below comes straight from the public marketplace listing.
GuardRails Content Safety API endpoints
| Method | Endpoint | Description |
|---|---|---|
| v1 | ||
| POST |
/v1/compliance/check /v1/compliance/check |
Check text against HIPAA, GDPR, SOX, PCI-DSS, FERPA, or COPPA compliance profiles. |
| POST |
/v1/redact /v1/redact |
Detect personally identifiable information and redact it using mask, replace, hash, or remove strategies. |
| POST |
/v1/cultural/analyze /v1/cultural/analyze |
Analyze text for cultural sensitivity issues relevant to specific target cultures. |
| POST |
/v1/crisis/detect /v1/crisis/detect |
Detect crisis signals including self-harm indicators, violence, and extreme distress. |
| POST |
/v1/scan /v1/scan |
Run comprehensive content safety scan covering PII, compliance, cultural sensitivity, toxicity, and crisis detection. |
GuardRails Content Safety API pricing
| Plan | Price | Rate limit | Quotas |
|---|---|---|---|
| BASIC | Free | — |
|
| PRO | $4.99 / month | 60 / minute |
|
| ULTRA | $49.99 / month | 120 / minute |
|
| MEGA | $99.99 / month | 200 / minute |
|
