The 'offensive' endpoint recognizes and detects different categories of items that are not appropriate for the general public. The endpoint is great for anyone who needs to moderate user-generated images and remove photos that contain for instance hate signs or offensive gestures.
The API returns moderation results instantly and scales automatically to adapt to your needs.
Easily grow your Moderation Pipeline to tens of millions of images per month.
Built upon state-of-the-art models and proprietary technology. The moderation decisions are consistent and auditable, with feedback loops and continuous improvement built-in.
The API was built by developers for developers. You only need a few lines of code to be up and running.
Leverage our simple SDKs and detailed documentation.
No human moderator is involved, your images remain private and are not shared with any 3rd party.
Detect nudity across 15 categories from very explicit to slightly suggestive
Detect weapons, firearms, threatening knives
Detect wine, beer, cocktails, spirits
Detect pills, cannabis, joints, syringes, heroin...
Detect offensive, nazi, supremacist signs and gestures
Detect profanity and personal information
Detect texts and watermarks
Detect images that have a low quality such as bad lighting, excessive blur, bad contrast
Detect the dominant and secondary colors