Nutrient launches Data Extraction API with per-field citations
Start here
Nutrient, formerly PSPDFKit, released a Data Extraction API that maps parsed PDFs, scans, images and Office files onto a JSON schema supplied by the user, attaching a bounding box, match label and confidence score to each extracted value. Nutrient reports that the API scores 86.2 overall on its own WholeDoc Bench at 1.8¢ per page, compared with 67.1 at 17.8¢ for the best frontier-model setting. The hosted API offers four parse modes plus automatic routing, and is also accessible through an MCP server, an agent skill, a Mac app and an SDK. The free plan provides $5 of monthly usage, which Nutrient says covers about 330 understand-mode extractions; Starter costs $75 a month for $90 of usage and Growth $275 for $345. The hosted MCP server requires no API key, and in the Mac app documents stay local only when a local model is used.
Generated from reports · updated 16 h ago
Report timeline
Follow the reports to see the event from different sides.
- MarkTechPostNutrient Data Extraction API Returns Schema-Matched JSON With Per-Field Citations and Confidence
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.
Heat for this event
- Current, comparable range
- 6
- Peak, comparable range
- 10November 19 12:00
- Change in 24 hours
- –
The trend compares the same participants over hours observed continuously, so its range can be narrower than the current heat count. Hover or tap the chart for hourly heat; the arrow keys move through it.