Close Menu
MyAppsPlus

    Subscribe to Updates

    Get the latest creative news from FooBar about art, design and business.

    What's Hot

    Durham Box Takes Gluing to a New Level with the Latest Technology from Baumer hhs

    November 19, 2026

    Battle of the small(er) phones vs Pixel 11 Pro

    November 19, 2026

    Samsung is bringing a lighter version of Galaxy S26’s Horizontal Lock to selfie cameras

    November 19, 2026
    Facebook X (Twitter) Instagram
    Facebook X (Twitter) Instagram
    MyAppsPlusMyAppsPlus
    Thursday, November 19
    • Home
    • Breaking Tech
    • Apps & Software
    • AI & Automation
    • Android
    • iPhone & iOS
    • More
      • Reviews
      • How-To Guides
      • Deals & Discounts
      • Shop
    MyAppsPlus
    Home»AI & Automation»Nutrient Data Extraction API: JSON Matching Your Schema With Per-Field Citations and Confidence
    AI & Automation

    Nutrient Data Extraction API: JSON Matching Your Schema With Per-Field Citations and Confidence

    myappsplusBy myappsplusNovember 19, 2026005 Mins Read
    Share Facebook Twitter Pinterest Copy Link LinkedIn Tumblr Email Telegram WhatsApp
    Follow Us
    Google News Flipboard
    Nutrient Data Extraction API: JSON Matching Your Schema With Per-Field Citations and Confidence
    Share
    Facebook Twitter LinkedIn Pinterest Email Copy Link

    An LLM presents you a wrong value extracted from a document as fact. That error is costly, especially when basing decisions on it. The Nutrient Data Extraction API targets that problem. It parses PDFs, scans, images and Office files into spatial JSON or Markdown. Extract maps fields from a document onto your JSON schema, and split, classify and form endpoints provide useful primitives for your document pipelines. Each extracted value is anchored to a page via a bounding box, a match label and a confidence score. Nutrient (formerly PSPDFKit) runs the same engine behind an MCP server, agent skill, Mac app and SDK.

    TL;DR

    • Size: A hosted API with 4 parse modes plus auto routing.
    • Runs on: Nutrient cloud, your own servers via SDK, or an Apple silicon Mac.
    • Where to try it:Studio, a browser workspace to configure and test parsing, extraction,classification, splitting, and form filling.
    • Performance:86.2 overall on Nutrient’s WholeDoc Bench, top of 19 settings (live API, Agentic).
    • Best: 86.2 at 1.8¢ per page, versus 67.1 at 17.8¢ for the best frontier-model setting.

    How do you test it in Studio before writing code?

    Studio is Nutrient’s browser workspace for configuring and testing the API before integrating it in your application. It enables you to test parsing, extraction, classification, splitting, and form filling on your own files. A typical loop:

    1. Upload a sample document and set the parameters you plan to send.
    2. Draft a schema in the UI, or generate one based on your own documents.
    3. Run it on a fresh document, then inspect values and citations.
    4. Save the setup as a versioned preset. The API calls it a processor, with a proc_ ID.
    5. Score preset versions against up to 25 reviewed documents in an evaluation set.

    Processors saved in Studio can then be called from the API by ID.

    Which mode should you pick?

    Auto routes each page to structure, understand or agentic. If the mode is omitted, the API defaults to understand.

    *WholeDoc Bench parsing score, 5 November 2026; not extraction accuracy. Extract adds $0.006 per page. **API docs list text-mode extract; the agent skill starts at structure.

    Pricing is in dollars, from 1 balance shared across Nutrient’s cloud APIs, so teams can mix and match. The free plan gives you $5 monthly usage that covers about 330 understand-mode extractions. Starter costs $75 a month for $90 of usage; Growth costs $275 for $345.

    How does grounded confidence work?

    In Nutrient’s confidence post, a field scored 0.97 but came from the wrong column.

    The current score is a composite of optional signals: token probability, candidate margin, grounding and format. Nutrient’s NLI grounding model is open under Apache-2.0. A grounded value can still answer the wrong field. When no score exists, confidence is omitted, not low.

    Each field also gets a match label: id_match, id_match_multiblock, id_match_partial, fuzzy_match or not_found. Gate on the label first, then confidence.

    import json, requests
    
    API_KEY = "your_api_key"
    schema = {
        "type": "object",
        "properties": {
            "invoice_number": {"type": "string", "description": "Invoice number below the supplier details."},
            "total_amount": {"type": "number", "description": "Printed final total including tax. Not the subtotal."},
        },
        "required": ["invoice_number", "total_amount"],
    }
    instructions = {"schema": schema, "parseConfig": {"mode": "understand"},
                    "options": {"includeCitations": True}}
    
    with open("invoice.pdf", "rb") as f:
        r = requests.post(
            "https://api.nutrient.io/extraction/extract",
            headers={"Authorization": f"Bearer {API_KEY}"},
            files={"file": ("invoice.pdf", f, "application/pdf"),
                   "instructions": (None, json.dumps(instructions), "application/json")},
            timeout=300,
        )
    r.raise_for_status()
    out = r.json()["output"]
    data, metadata = out.get("data") or {}, out.get("metadata") or {}
    
    EXACT = {"id_match", "id_match_multiblock"}
    THRESHOLD = 0.97  # illustrative only; evaluate on representative documents
    
    for field in schema["properties"]:  # loop over expected fields so none skip review
        value = data.get(field)
        meta = metadata.get(field) or {}
        match, conf = meta.get("match"), meta.get("confidence")  # None = no score
        passes = (value is not None and match in EXACT
                  and conf is not None and conf >= THRESHOLD)
        print(field, value, match, conf, "page", meta.get("pageNumber"),
              "PASSES_BASIC_CHECKS" if passes else "REVIEW")

    This demo covers flat schemas only; production needs type and business-rule checks. The 0.97 bar mirrors money fields in Nutrient’s mortgage tutorial.

    How do classify and split work?

    A document decision model powers classify and split. Nutrient reports 96.2% split F1 against 63.7% for Typesafe AI’s Jev.

    How do agents use it?

    The hosted MCP server needs no API key. Claude Code connects with 1 command:

    claude mcp add --transport http --scope user nutrient https://mcp.nutrient.io/mcp

    Coding agents can install the document-extraction-api skill with npx skills add pspdfkit-labs/nutrient-skills –skill document-extraction-api.

    Can it run locally?

    On the Mac app, documents stay local only with a local model. Fully offline production needs the SDK.

    How does it score on WholeDoc Bench?

    Nutrient’s new WholeDoc Bench scores whole documents, not single pages: 480 documents, 30+ languages, 7 areas.

    Selected rows, WholeDoc leaderboard, 5 November 2026, list prices. *Score still under review.

    Cross-page continuity is the biggest gap. On 44 documents with page-spanning tables, 15 of 19 settings rarely kept them whole.

    Nutrient built and ran it, and the main test set is private. The code is Apache-2.0, with a 10-document public sample. 

    Key Takeaways

    • Fields carry pages, regions, match labels and, when available, confidence.
    • Configure and test in Studio before writing any API code.
    • Understand-mode extraction costs $15 per 1,000 pages.
    • Agentic tops Nutrient’s WholeDoc Bench at 86.2 for 1.8¢ per page.
    • Charts remain hard: 64.5 is the best WholeDoc chart score.

    Thanks to the Nutrient AI team for the thought leadership / resources for this article. This article is sponsored.

    The post Nutrient Data Extraction API: JSON Matching Your Schema With Per-Field Citations and Confidence appeared first on MarkTechPost.

    agentic ai AI Shorts applications Artificial intelligence Computer Vision Editors Pick Embedding Model Enterprise AI For Devs Generative AI Language Model New Releases OCR Promote Sponsored staff technology Uncategorized Vision Language Model
    Follow on Google News Follow on Flipboard
    Share. Facebook Twitter Pinterest LinkedIn Tumblr Email Copy Link
    myappsplus
    • Website

    Related Posts

    74% of shoppers trust AI agents for buying advice – but checkout is another story

    November 19, 2026

    You can use Google’s Spark AI agent, renamed Tasks, for free now – with limits

    November 19, 2026

    From early adopter to Fisher’s premier AI thought leader

    November 19, 2026
    Add A Comment
    Leave A Reply Cancel Reply

    Top Posts

    UiPath Launches AI Coding Agent, Integrates Claude Code and Codex to Target Development Automation

    November 16, 202642 Views

    The pros and cons of using your phone as a mobile hotspot

    November 16, 202641 Views

    Save on your groceries, gas, and holiday shopping with this $15 BJ’s membership (Reg. $60) 

    November 4, 202632 Views
    Latest Reviews

    Google Pixel Tablet has been discontinued, out of stock everywhere

    myappsplusSeptember 9, 2026

    iPhone price hikes —here’s the full list of every price increase from the iPhone 18 Pro to a 21% rise for one iPhone Air model

    myappsplusSeptember 9, 2026

    Apple launches iPhone Duo developer resources ahead of October release

    myappsplusSeptember 9, 2026
    Stay In Touch
    • Facebook
    • YouTube
    • TikTok
    • WhatsApp
    • Twitter
    • Instagram

    Subscribe to Updates

    Get the latest tech news from FooBar about tech, design and biz.

    Most Popular

    AI data centers have a hidden cost few highlighted: A $200 billion insurance price tag that consumers will end up paying

    September 9, 20260 Views

    Despite spending billions on data centers and AI, US government report finds Amazon workers are using food stamps more than ever

    September 10, 20260 Views

    How to watch Patriots vs Seahawks: Free Streams & TV Channels for 2026 NFL Kickoff Game

    September 10, 20260 Views
    Our Picks

    Durham Box Takes Gluing to a New Level with the Latest Technology from Baumer hhs

    November 19, 2026

    Battle of the small(er) phones vs Pixel 11 Pro

    November 19, 2026

    Samsung is bringing a lighter version of Galaxy S26’s Horizontal Lock to selfie cameras

    November 19, 2026

    Subscribe to Updates

    Subscribe to our newsletter and get the latest tech news, app updates, AI trends, smartphone reviews, and exclusive deals delivered straight to your inbox.

    Facebook X (Twitter) Instagram Pinterest
    • About Us
    • Get In Touch
    • Disclaimer
    • Privacy Policy
    • Terms & Conditions
    © 2026 MyAppsPlus. All Rights Reserved.

    Type above and press Enter to search. Press Esc to cancel.