How do I get an API key?

Sign up for a free Airparser account at app.airparser.com. Your API key is available immediately in Settings → API. The free trial includes 30 documents — no credit card required.

What does the API response look like?

The API returns a JSON object with a 'doc_id', 'status', metadata fields (name, content_type, created_at, processed_at), and a 'json' object containing your extracted fields. The exact structure of 'json' matches the schema you defined for your inbox — field names, types, and nesting are consistent across all documents.

How do webhooks work?

Configure a webhook URL in your inbox settings. When a document finishes parsing, Airparser sends a POST request to your URL with the full JSON payload. Failed deliveries are retried automatically with exponential backoff. You can view delivery history and retry manually from the dashboard.

Can I parse scanned or image-based PDFs?

Yes. Airparser automatically detects whether a PDF contains selectable text or is image-based. For image-based documents, it routes to the Vision LLM or AI OCR engine automatically — no configuration required on your end.

Is there a rate limit?

Rate limits depend on your plan. All plans support batch document uploads. For high-volume use cases (thousands of documents per day), contact us at support@airparser.com to discuss dedicated capacity.

Can I use the API for an agentic AI workflow?

Yes — two ways. First, the REST API is straightforward to call from any code. Second, Airparser has an MCP (Model Context Protocol) server, so Claude, Cursor, and other AI agents can call it directly as a tool without you writing integration code.

Where is my data stored? Is it GDPR compliant?

Airparser stores data on secure cloud infrastructure with AES-256 encryption at rest and TLS in transit. We never use your documents or extracted data to train AI models. Data retention is configurable per inbox — documents are permanently deleted after your chosen period. We are GDPR compliant.

REST API · Webhooks · JSON

Document Extraction API

A reliable REST API for extracting structured data from PDFs, emails, and documents. Define your schema once, get consistent JSON output every time — with webhooks, retries, and GDPR compliance built in.

Get API key free → View API docs

Upload a document, get structured JSON

Request

BASH

curl -X POST https://api.airparser.com/inboxes/INBOX_ID/upload-sync \
  -H "X-API-Key: YOUR_API_KEY" \
  -F "[email protected]"

Response

JSON

{
  "doc_id": "64abc123def456...",
  "parsing_in_progress": false,
  "status": "parsed",
  "name": "invoice.pdf",
  "content_type": "application/pdf",
  "created_at": "2026-03-10T12:00:00.000Z",
  "processed_at": "2026-03-10T12:00:04.321Z",
  "json": {
    "invoice_number": "INV-2024-0042",
    "invoice_date": "2024-03-15",
    "vendor_name": "Acme Supplies Ltd",
    "total_amount": 1284.50,
    "currency": "USD",
    "due_date": "2024-04-14",
    "line_items": [
      {
        "description": "Office supplies",
        "quantity": 3,
        "unit_price": 428.17,
        "total": 1284.50
      }
    ]
  }
}

Built for production, not prototyping

Guaranteed schema

Define your output schema once. Every document returns the exact same JSON structure — no format variations, no parsing surprises in production.

Webhook delivery

Results are pushed to your endpoint the moment extraction completes. Automatic retries with exponential backoff — no polling required.

Multi-engine fallback

Text LLM → Vision LLM → AI OCR. Scanned documents, image-based PDFs, and handwritten text are handled automatically without extra configuration.

GDPR by default

AES-256 encryption, configurable data retention, no training on your data, EU-based processing available. Compliance built in, not bolted on.

Python post-processing

Run custom Python code on extracted data before it's delivered — normalize values, apply business rules, enrich fields, or filter results.

60+ languages

Extract data from documents in any language. The AI understands context and field meaning — not just character patterns — so accuracy holds across languages.

How the API works

Define your extraction schema

Describe the fields you want to extract in plain English — field name, type, and a brief description. No templates, no training data. Airparser uses this to instruct the AI on what to extract and how to format it.

Upload documents via API or email

POST documents to /api/v1/inboxes/:id/documents via multipart upload or base64. Or forward emails to your Airparser inbox address — attachments are parsed automatically.

Receive structured JSON

Results are delivered to your webhook URL as a JSON payload matching your schema. Or poll the document endpoint. Or export to Google Sheets, Airtable, HubSpot, or any Zapier-connected app.

Supported document types

Every format, automatic engine selection

PDF

Native & scanned

Body & attachments

Images

JPG, PNG, TIFF

Word / DOCX

All versions

CSV / Excel

Tables & sheets

HTML

Web pages & emails

Handwritten

Via Vision LLM

Plain text

TXT, RTF, MD

Common API use cases

Invoice processing pipeline

Forward vendor invoices to your Airparser inbox or POST them via API. Extract invoice number, date, vendor, line items, and totals as structured JSON. Deliver to your accounting software via webhook or direct integration with QuickBooks, Xero, or Google Sheets.

Resume / CV screening

Parse incoming CVs and extract candidate name, contact details, skills, work history, and education as structured data. Push to your ATS or CRM via webhook. Works with PDF, DOCX, and plain text resumes in any language.

Lead capture from forms and emails

Extract lead information from inquiry emails, contact form notifications, or uploaded documents. Normalize the data and push structured leads to HubSpot, Salesforce, or your CRM of choice via webhook.

Shipping & logistics documents

Parse bills of lading, packing slips, customs declarations, and delivery confirmations. Extract shipment IDs, origins, destinations, item counts, and status into structured JSON for your logistics platform.

AI agent document tool (via MCP)

Connect Airparser to Claude, Cursor, or any MCP-compatible AI agent as a document extraction tool. Your agent can upload documents and receive structured data without building custom parsing logic — fully GDPR-compliant extraction inside any agentic workflow.

Start extracting in minutes

Free trial — 30 documents included. No credit card required.

API keys available immediately after signup.

Get API key → Read the docs