Nutrient launches data extraction API with per-field citations and confidence scores
Understand this story
Nutrient (formerly PSPDFKit) has released the Data Extraction API, which parses PDFs, scans, images, and Office files into spatial JSON or Markdown, and extracts fields according to a user-supplied JSON Schema. Each extracted value comes with a bounding box page location, a match label, and a confidence score. On pricing, the free plan provides $5 of usage per month, enough for roughly 330 understand-mode extractions; Starter at $75 per month corresponds to $90 of usage, and Growth at $275 per month corresponds to $345 of usage. The hosted MCP server requires no API key; in the Mac app, documents stay local only when using local models.
AI overview based on source reports · Updated 1 days ago
Coverage timeline
Follow the coverage to explore different perspectives.
- MarkTechPostNutrient Data Extraction API: JSON Matching Your Schema With Per-Field Citations and Confidence
Nutrient (formerly PSPDFKit) launched a hosted Data Extraction API that parses PDFs, scans, images and Office files and maps fields onto a user's JSON schema, anchoring each value to a page via bounding box, match label and confidence score. It offers four parse modes plus auto routing, with pricing from $0.001 per page for text parsing to $0.018 for agentic parsing, and scored 86.2 overall on Nutrient's own WholeDoc Bench. The API is also available through an MCP server, agent skill, Mac app and SDK, and can be configured and tested in the browser-based Studio before integration.
Activity for this story
- Current comparable activity
- 4
- Peak comparable activity
- 10Nov 19 13:00
- Change in the past 24 hours
- -50%
Trends compare the same fully observed participants, which may cover fewer participants than current activity. Move the pointer or tap the chart to inspect hourly activity; use the left and right arrow keys with a keyboard.