Build deterministic document workflows for AI

Parse PDFs, scans, images, and Office files into spatial JSON or Markdown with coordinates, confidence, and page context. Extract structured data for agents, RAG, search, automation, and human review.

Invoice document transforming into structured JSON output

Trusted by enterprises, governments, and AI-native teams building document workflows at scale.

Used by Lufthansa, Disney, Autodesk, UBS, Dropbox, IBM
Lufthansa
Disney
Autodesk
UBS
Dropbox
IBM

Capabilities

Parse PDFs. Extract structured data. Build deterministic workflows for AI.

Document being parsed into structured elements

Parse

Turn complex files into document structure


Detect every document element

Identify tables, forms, formulas, images, charts, handwriting, key-value regions, headings, lists, and reading order across complex files.


Preserve page context

Keep elements connected to page position, confidence, and reading order so teams can validate, highlight, and use results downstream.


Choose speed, cost, or depth

Select the processing mode that fits the document — from low-cost Markdown to AI-augmented parsing for complex visual layouts.


Handle real-world files

Process PDFs, images, Office files, scans, and multilingual documents through one API.


Invoice data being extracted into JSON

Extract

Extract data for systems, agents, and review


Map data to your schema

Use /parse output as source evidence for schema workflows. AI Document Processing supports templates and validation today; hosted schema extraction is coming soon.


Extract complex tables

Extract tables, forms, images, and handwriting with rows, columns, spans, captions, and footnotes preserved.


Trace every value

Keep values connected to page position, confidence scores, reading order, and source evidence for review.


Send downstream

Return output ready to map into databases, ERPs, CRMs, review queues, and document workflows.


Complex document structured into spatial JSON output

Structure

Return predictable output your systems can use


Spatial JSON for structured operations

Use spatial JSON for layout-aware elements, tables, key-value regions, coordinates, confidence scores, and page context.


Markdown for AI and search

Use Markdown for fast, cost-efficient content for RAG, search indexing, knowledge bases, and content migration.


Predictable output for the next step

Return results in predictable formats so downstream systems can validate, route, review, automate, or feed AI and search workflows.


Document workflow processing and routing

Process

Build governed document workflows, from extraction to downstream use


Validate before automating

Use confidence scores, coordinates, and word-level details to review the output before sending it downstream.


Route exceptions

Move clean results forward and hold low-confidence, incomplete, or mismatched files for review.


Reconcile and map

Compare extracted values against business rules, records, or downstream systems before posting.


Support review and recovery

Keep results tied to the source so teams can trace, fix, and recover issues.


Automate downstream workflows

Send typed JSON to business systems and review queues. Or, send Markdown to AI, search, knowledge bases, and content pipelines.


Start free

5,000 free Data Extraction API credits/month

No credit card required.

Your free plan includes:

    • 5,000 Data Extraction API credits each month
    • Parse and extract from PDFs, images, and Office files
    • Markdown or spatial JSON output
    • Available modes: text, structure, and understand

Processing modes

Pick the right path: one API, four modes

Choose speed, cost, or depth per workflow. Set mode per request.

Text

Available

Low-cost Markdown for born-digital PDFs and Office files

PDF to Markdown RAG Search

Structure

Available

Spatial JSON with OCR, tables, key-value regions, bounds, confidence, and page context

Scans Forms Tables

Understand

Available

AI-augmented parsing for complex layouts, handwriting, formulas, and OCR correction

Invoices KYC Legal

Agentic

Coming soon

Agent-guided extraction for documents that need deeper reasoning, review, and recovery

Complex layouts Schema workflows Agents

Output formats

Spatial JSON. Or Markdown. From the same API.

Elements, bounds, confidence, metadata, and usage. Choose
output: "json" or Markdown per request.

Spatial JSON

For extraction · validation · review

.json
{
"status": "processed",
"usage": {
"pages": 4,
"credits": 6
},
"pages": [
{
"index": 0,
"elements": [
{
"type": "key_value_pair",
"label": "Invoice number",
"value": "INV-20241108",
"confidence": 0.98,
"page": 1,
"bounds": [82, 128, 284, 152]
},
{
"type": "table",
"rows": 3,
"columns": 4,
"confidence": 0.96,
"bounds": [70, 320, 516, 482]
}
]
}
]
}

Markdown

For RAG · search · knowledge bases

.md
# Invoice INV-20241108
**From** Acme Studios LLC
**Issued** Nov 8, 2024
## Line items
| Item | Qty | Total |
| --- | ---: | ---: |
| Visual identity | 1 | $8,500 |
| Brand guidelines | 1 | $2,200 |
**Total · $13,500.00**

Built for production

Deterministic document infrastructure for trusted AI workflows

Handle messy real-world files

Process PDFs, photos, scans, Office files, and archives without building a separate parser for each format.

Return source-grounded outputs

Return coordinates, confidence, page context, and review paths so AI outputs stay tied to source evidence.

Flag uncertainty before automation

Use confidence scores and page context to catch extraction issues before agents or automations rely on them.

Choose speed, cost, or depth

Pick the cheapest mode that meets your accuracy bar. Then increase depth only when documents require it.

Prepare schema-ready data

Use /parse output with AI Document Processing templates today. Hosted schema extraction is coming soon.

Connect the full workflow

Parse first. Then convert, redact, generate, sign, view, edit, or approve across Nutrient DWS and SDKs.

SOC 2 Type 2

Audited annually. Reports available under NDA.

Regional processing options

Choose supported processing regions for enterprise deployments.

Trust and compliance

Built for enterprise
workflows

Secure document handling

Files are discarded once their data is extracted.

HTTPS/TLS encryption

API communication is encrypted by default, and unencrypted requests are rejected.


Data Extraction API questions

What file formats can this document parsing API process?

Data Extraction API processes PDFs, images, Word, Excel, PowerPoint, and other common document formats. Upload files directly, send raw binary content, or point the API at a hosted document URL. It handles scanned PDFs, fillable forms, and mixed digital/image-based documents without requiring a separate OCR pipeline.

Can I extract JSON from PDFs, scans, and forms?

Yes. The hosted /parse API returns spatial JSON with typed document elements, tables, key-value regions, coordinates, confidence scores, page context, and optional word-level bounds. For target-schema extraction, templates, classification, and validation today, use AI Document Processing. Hosted schema-driven extraction for Data Extraction API is coming soon.

How is this different from using a general LLM for document extraction?

A general LLM can reason over document text, but it doesn’t give you a document processing layer by itself. Data Extraction API returns layout-grounded elements with reading order, coordinates, confidence scores, and page references, so teams can validate, route, highlight, and automate with traceability.

Can I get spatial JSON and Markdown in the same request?

Spatial JSON and Markdown are separate output formats on the same API. Choose spatial JSON when your workflow needs structured elements with layout context, or Markdown when you need clean structured content for RAG, search, or document Q&A. Send two requests if your pipeline needs both.

How do I validate and review extracted data before sending it downstream?

Every extracted element comes back with confidence scores, page references, coordinates, and word-level details, so you can compare outputs across sample documents, flag low-confidence fields for human review, highlight results on the original document, and route exceptions to a review queue. Because results stay connected to the source document, teams can trace outputs back to the original page and correct downstream records when needed.

Can Data Extraction API support full document workflows?

Yes. Use Data Extraction API as the parsing layer. Then connect the output to AI Document Processing for templates and validation; DWS Processor for conversion, redaction, generation, and signing; and Nutrient SDKs when humans need to review, edit, annotate, or approve documents in your application.

Does Nutrient store my documents or use them to train models?

No. Uploaded files are processed and discarded — extracted content is returned in the API response and not retained. All API communication uses HTTPS with TLS encryption, and unencrypted HTTP requests are rejected.

Is the Data Extraction API SOC 2 compliant?

Yes. The API is backed by Nutrient’s broader security practices, including SOC 2 Type 2 compliance, with no persistent document storage and TLS-encrypted transport — built for use in business-critical and regulated workflows.

How does pricing work, and what’s included in the free tier?

New accounts get 5,000 free Data Extraction API credits per month with no credit card required. Beyond the free tier, you control cost by choosing the processing mode that fits each workflow: text for low-cost Markdown extraction, structure for spatial JSON, understand for AI-augmented parsing, and agentic for advanced extraction workflows when it becomes available.

What is understand mode?

Understand mode uses an AI-augmented extraction pipeline for complex documents that need richer layout understanding, OCR correction, handwriting support, formulas, and structure-aware output.

Documents in, structured data out

5,000 free Data Extraction API credits per month — no credit card required. Parse PDFs, images, scans, and Office files into spatial JSON or Markdown for AI workflows, automation, and human review.