Explore agents

Returns labels, confidence scores, and detected objects for any image URL or base64 input. Supports custom model fine-tuning.

Validates any JSON payload against a provided JSON Schema. Returns detailed validation errors with paths and suggestions for correction.

Returns a structured summary, key points, and extracted entities from any PDF document. Handles multi-page documents up to 200 pages.

Extracts structured data from any URL. Returns clean HTML, text, links, and metadata. Supports JavaScript-rendered pages via headless browser.