Integrate AI safety testing with simple REST APIs. All endpoints accept prompt + response, return consensus-based analysis in <4s.
All APIs use the same format: send prompt + response, receive consensus score.
Detect demographic and contextual bias
POST /v1/evaluate/biasIdentify harmful or offensive content
POST /v1/evaluate/toxicityDetect AI-generated false information
POST /v1/evaluate/hallucinationDetect security bypass attempts
POST /v1/evaluate/jailbreakDetect personally identifiable information
POST /v1/evaluate/piiDetect content unsafe for children
POST /v1/evaluate/child_safetyDetect copyrighted content reproduction
POST /v1/evaluate/copyrightDetect false or misleading information
POST /v1/evaluate/misinformationDetect GDPR violations
POST /v1/evaluate/gdprDetect PHI and HIPAA violations
POST /v1/evaluate/hipaaDetect prompt injection attempts
POST /v1/evaluate/injectionTest reliability and error handling
POST /v1/evaluate/robustnessIntegrate AI safety testing in minutes with our simple REST APIs.