Moderation API Reference

Detect AI-generated images from Midjourney, DALL-E, Stable Diffusion and 100+ generators. 98.3% accuracy with source attribution. Stop synthetic fraud.

Detect face-swapped deepfakes and manipulated portraits with state-of-the-art AI. Identify GAN-generated faces and digital face alterations.

Detect face occlusions from masks, sunglasses, hands, and objects. Ensure clear facial visibility for identity verification and biometric systems.

Detect minors and children in images with AI age estimation. Protect child safety, enforce age restrictions, and ensure platform compliance.

Estimate age of individuals in images with AI facial analysis. Detect minors for age verification, content moderation, and regulatory compliance.

Automatically blur all faces in images for privacy protection. Uses AI face detection to identify and anonymize faces.

Count people in images with AI-powered detection and segmentation. Monitor crowd density, occupancy limits, and capacity for safety compliance.

Automatically blur young faces (under 23) in images. Uses a safety margin to ensure minors are protected even with age estimation uncertainty.

Screen faces against Interpol, Europol, FBI and 52+ law enforcement databases. Real-time wanted person detection for security and compliance.

Detect nudity and adult content with granular classification: mild, partial, explicit. AI-powered NSFW moderation with 94% accuracy for platforms.

Detect violence in images with severity classification: mild, moderate, graphic. AI content moderation for platforms requiring safety compliance.

Detect firearms, knives, and weapons in images automatically. AI-powered threat detection for platform safety, security screening, and compliance.

Detect drugs and paraphernalia in images: cannabis, pills, syringes, and controlled substances. Enforce platform policies and marketplace compliance.

Detect alcoholic beverages in images including wine, beer, spirits, and cocktails. Enforce advertising compliance and content policies automatically.

Detect cigarettes, vaping, and tobacco products in images. Enforce advertising bans, platform policies, and regulatory compliance automatically.

Detect gambling content in images: casinos, slot machines, poker, and betting. Enforce advertising regulations and protect underage users automatically.

Detect cash, banknotes, and currency displays in images. Enforce financial advertising compliance and content moderation policies automatically.

Detect fire, explosions, building damage, and destruction in images. Monitor insurance claims, news content, and safety incidents automatically.

Detect military content: weapons, vehicles, personnel, and combat scenes. Moderate sensitive imagery and enforce content policies on global platforms.

Detect offensive text, slurs, and hate speech embedded in images. OCR-powered content moderation for memes, screenshots, and user-generated content.

Extract text from images with customizable prompts. Supports OCR, formula extraction (LaTeX), table parsing (HTML/Markdown), and structured data extraction (JSON).

Classify 76+ document types automatically: passports, IDs, invoices, bank statements. Streamline KYC/KYB onboarding with AI document recognition.

Automatically rate images as G, PG-13, R, or Adult based on nudity, violence, and language. Ensure age-appropriate content across your platform.

Detect and classify vehicles in images: cars, trucks, motorcycles, buses. AI-powered vehicle recognition for traffic analysis and fleet management.

Detect document forgery and digital manipulation in IDs, invoices, and certificates. AI-powered fraud detection for KYC and document verification.

Detect screen capture fraud and document replay attacks. Verify if ID photos are captured live or photographed from screens. Prevent identity fraud.