PO extraction

Every PO.Three-way matched.

PO number, line items with SKUs, delivery terms, ship-to, bill-to. Wires into your ERP and matches against invoices and goods receipts automatically.

Start extracting See the API

100 pages free No card SOC 2 in progress

app.docparse.io / extractions / po-acme-77840.pdf

Live

PURCHASE ORDER #PO-77840

Acme Industries → Northwind Logistics

BuyerAcme Industries

SupplierNorthwind Logistics

PO dateApril 12, 2026

DeliveryMay 3, 2026

Total$48,720.00

IncotermsFOB Long Beach

JSONCSVWebhook98.6% confidence

{
  "po_no": "PO-77840",
  "buyer": "Acme Industries",
  "supplier": "Northwind Logistics",
  "po_date": "2026-04-12",
  "delivery_date": "2026-05-03",
  "total": 48720.00,
  "line_items": [ 12 SKUs ],
  "incoterms": "FOB"
}

Extracted in 2.4s · 8 fields

Scroll

Pipe extracted data into any of these — via Zapier or signed webhooks

Zapier

Google Drive

Gmail

Slack

Sheets

Notion

Airtable

Webhook

Zapier

Google Drive

Gmail

Slack

Sheets

Notion

Airtable

Webhook

Why DocParse

Three reasons teams switch to us

Line-level extraction

Every SKU with description, quantity, unit price, line total, GL code, and ship-to. Captures price-list mismatches at intake.

12.4avg line items per PO

Auto-3-way match

PO ↔ invoice ↔ goods receipt matched automatically. Exceptions flagged with the discrepant fields and reasons.

94%auto-matched without review

ERP-ready output

Native integrations with NetSuite, SAP, Dynamics, Oracle, Coupa. Output already coded to your GL and cost centers.

6 ERPsnative integrations

How it works

From raw purchase orders
to structured data, in four steps.

Drop document, paste URL, or POST file

PDFPNGJPGTIFFDOCXHEICHTMLEMLXLSX

The schema

Starter schema for purchase orders.
Tweakable in seconds.

The purchase orders template comes with a 10-field starter schema based on the most common fields teams pull from purchase orders. Add your own fields, mark which are required, and change types in the dashboard or via the REST API.

Purchase orders · default schema

po_nostringrequired99.7%

buyerstringrequired99.4%

supplierstringrequired99.5%

po_datestringrequired99.6%

delivery_datestringoptional98.4%

ship_tostringrequired98.9%

bill_tostringrequired98.7%

currencystringrequired99.9%

totalnumberrequired99.6%

line_itemsarrayrequired97.6%

JSON SchemaTypeScriptPython

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "title": "Purchaseorders",
  "type": "object",
  "required": [
    "po_no",
    "buyer",
    "supplier",
    "po_date",
    "ship_to",
    "bill_to",
    "currency",
    "total",
    "line_items"
  ],
  "properties": {
    "po_no": {
      "type": "string"
    },
    "buyer": {
      "type": "string"
    },
    "supplier": {
      "type": "string"
    },
    "po_date": {
      "type": "string"
    },
    "delivery_date": {
      "type": "string"
    },
    "ship_to": {
      "type": "string"
    },
    "bill_to": {
      "type": "string"
    },
    "currency": {
      "type": "string"
    },
    "total": {
      "type": "number"
    },
    "line_items": {
      "type": "array"
    }
  }
}

What to expect

Field-level accuracy per field.

Multi-modal models do the reading, and accuracy depends on document quality. The numbers below are illustrative ranges we've seen on purchase orders — run your own documents and compare against a small ground-truth set before you scale.

98.7%

illustrative field-level
accuracy ceiling

10starter fields

Anylanguage supported

25 MBmax file size

FieldAccuracy

po_no

99.7%

buyer

99.4%

supplier

99.5%

total

99.6%

line_items

97.6%

delivery_date

98.4%

ship_to

98.9%

currency

99.9%

The API

One endpoint.
Every output you need.

# Extract with one POST
curl -X POST "https://api.docparse.io/v1/purchase-orders" \
  -H "Authorization: Bearer $DOCPARSE_KEY" \
  -F file=@"po-acme-77840.pdf" \
  -F schema="po" \
  -F webhook="https://api.acme.co/incoming"

# Returns:
{
  "status": "complete",
  "confidence": 0.987,
  "latency_ms": 2412,
  "data": { ... }
}

Plain HTTP, no SDK lock-in

Bearer-token auth with revocable, SHA-256-hashed API keys. Call it from any language that can hit a REST endpoint — we publish docs and copy-pasteable snippets, not opinionated wrappers.

cURLPythonNode.jsGoRubyPHPJava.NET

Signed webhooks for async

Register an endpoint, set the events, and we POST signed deliveries (HMAC-SHA256, Standard Webhooks spec) as extractions finish. Every attempt is logged in the dashboard with response code, body, and timing.

Webhook delivery log · per-endpoint retries

The alternatives

Why teams switch from regex.

A look at how DocParse compares to the three things you've probably already tried.

Regex + scripts

Manual review (BPO)

Tradeshift / Coupa

DocParse

Works on a layout it has never seen

partial

Handles handwriting and scans

partial

Custom fields without per-vendor setup

Multi-lingual out of the box

partial

REST API + signed webhooks + Zapier

partial

Pricing scales with pages, not seats

partial

Free tier, every month, forever

partial

Time-to-first-extraction

Days

Weeks

5 minutes

Where the data goes

Reach the tools you already run.

DocParse ships two integration surfaces directly — REST API and signed webhooks — plus a native Zapier app that opens up everything else.

Zapier

Automation

Webhooks

API

REST API

API

JSON export

Export

CSV export

Export

Google Drive

via Zapier

Google Sheets

via Zapier

Gmail

via Zapier

Outlook

via Zapier

Slack

via Zapier

Dropbox

via Zapier

Airtable

via Zapier

Notion

via Zapier

HubSpot

via Zapier

Salesforce

via Zapier

Make.com

via Webhooks

n8n

via Webhooks

Postgres

via Webhooks

REST API · Signed webhooks (HMAC-SHA256) · Zapier to 6,000+ apps · JSON / CSV export

Common patterns

How teams use DocParse for purchase orders.

Illustrative scenarios drawn from teams piloting DocParse — names and figures are examples, not customer quotes.

“

Three-way matching used to be one full-time AP analyst. DocParse handles 94% of matches automatically and our analyst now does anomaly review.

Marcus Patel

Procurement Director · Tarn

−1 FTEAP headcount needed

“

Our suppliers send POs in 18 different formats. DocParse normalizes them all into NetSuite. Zero supplier complaints about format requirements.

Lin Park

Supplier Relations · Folium

18 fmtsall to one schema

“

The price-list-mismatch detection caught $1.2M in supplier overcharges in the first six months. The product paid for itself in two weeks.

Tobias Hill

CFO · Northwave

$1.2Movercharges caught

Frequently asked

The questions teams ask before they sign up.

Does it match against invoices?

Yes — three-way match with invoice and goods receipt. Push your data via API; DocParse returns matched / partial / exception with reasons.

How does line-item extraction work?

Every line returned with SKU, description, quantity, unit price, line total, and ship-to. Maps to your master SKU catalog if you provide one.

Which ERPs are supported?

NetSuite, SAP S/4 HANA, Microsoft Dynamics, Oracle, Coupa, and Workday natively. Plus generic webhook + flat-file output for everything else.

Does it catch price-list mismatches?

If you upload a price list, DocParse flags any line that deviates beyond your tolerance. Common configurations: ±2% absolute, ±5% volume-tiered.

POs into your ERP. Today.

Three-way matching, line-level extraction, ERP-coded output. Live by tomorrow.

Start extracting Talk to sales

Free for first 100 pages 5-minute setup No credit card

Every PO.Three-way matched.

Three reasons teams switch to us

Line-level extraction

Auto-3-way match

ERP-ready output

From raw purchase orders
to structured data, in four steps.

Define the fields

Upload the file

Multi-modal AI reads it

Get structured data back

Starter schema for purchase orders.
Tweakable in seconds.

Field-level accuracy per field.

One endpoint.
Every output you need.

Plain HTTP, no SDK lock-in

Signed webhooks for async

Why teams switch from regex.

Reach the tools you already run.

How teams use DocParse for purchase orders.

The questions teams ask before they sign up.

POs into your ERP. Today.

Every PO.Three-way matched.

Three reasons teams switch to us

Line-level extraction

Auto-3-way match

ERP-ready output

From raw purchase ordersto structured data, in four steps.

Define the fields

Upload the file

Multi-modal AI reads it

Get structured data back

Starter schema for purchase orders.Tweakable in seconds.

Field-level accuracy per field.

One endpoint.Every output you need.

Plain HTTP, no SDK lock-in

Signed webhooks for async

Why teams switch from regex.

Reach the tools you already run.

How teams use DocParse for purchase orders.

The questions teams ask before they sign up.

POs into your ERP. Today.

From raw purchase orders
to structured data, in four steps.

Starter schema for purchase orders.
Tweakable in seconds.

One endpoint.
Every output you need.