MarkTechPost· Asif Razzaq·· 16 h agoAI score40
Nutrient Data Extraction API Returns Schema-Matched JSON With Per-Field Citations and Confidence
Nutrient Data Extraction API: JSON Matching Your Schema With Per-Field Citations and Confidence
AI summary
Nutrient (formerly PSPDFKit) launched a Data Extraction API that maps parsed PDFs, scans, images and Office files onto a user-supplied JSON schema, attaching a bounding box, match label and confidence score to each value. It scores 86.2 overall on Nutrient's WholeDoc Bench at 1.8¢ per page, versus 67.1 at 17.8¢ for the best frontier-model setting. The hosted API offers four parse modes plus auto routing, and is also reachable through an MCP server, agent skill, Mac app and SDK.
Source:MarkTechPost · marktechpost.com