Statement extraction

Every transaction.Reconciled in real time.

Account holder, period, opening and closing balance, every transaction with description, amount, and balance — from any bank, in any format.

Start extracting See the API

100 pages free No card SOC 2 in progress

app.docparse.io / extractions / chase-march-2026.pdf

Live

CHASE BUSINESS COMPLETE BANKING

Statement Period · Mar 1–31, 2026

Account**** 4892

HolderNorthwind Logistics LLC

Open balance$84,231.04

Deposits+$142,800.00

Withdrawals−$98,420.16

Close balance$128,610.88

JSONCSVWebhook98.6% confidence

{
  "account_no_last4": "4892",
  "holder": "Northwind Logistics LLC",
  "period_start": "2026-03-01",
  "period_end": "2026-03-31",
  "opening_balance": 84231.04,
  "closing_balance": 128610.88,
  "transactions": [ 47 entries ]
}

Extracted in 2.4s · 7 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

Every bank, every layout

4,200+ banks tested. Personal, business, brokerage, foreign-currency. Multi-page statements stitched automatically.

4,200+banks tested in benchmark

Transactions with categories

Each transaction returned with merchant, MCC code, and category. Maps to your chart of accounts or to a global taxonomy.

99.7%transaction extraction accuracy

Lender-grade output

Used by 30+ lenders for underwriting. Returns cash-flow summaries, NSF flags, and average daily balance ready for risk models.

30+lenders in production

How it works

From raw bank statements
to structured data, in four steps.

Drop document, paste URL, or POST file

PDFPNGJPGTIFFDOCXHEICHTMLEMLXLSX

The schema

Starter schema for bank statements.
Tweakable in seconds.

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

Bank statements · default schema

bankstringrequired99.9%

account_no_last4stringrequired99.7%

holderstringrequired99.4%

period_startstringrequired99.8%

period_endstringrequired99.8%

opening_balancenumberrequired99.6%

closing_balancenumberrequired99.6%

transactionsarrayrequired99.7%

avg_daily_balancenumberoptional98.9%

nsf_countintegeroptional99.2%

JSON SchemaTypeScriptPython

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "title": "Bankstatements",
  "type": "object",
  "required": [
    "bank",
    "account_no_last4",
    "holder",
    "period_start",
    "period_end",
    "opening_balance",
    "closing_balance",
    "transactions"
  ],
  "properties": {
    "bank": {
      "type": "string"
    },
    "account_no_last4": {
      "type": "string"
    },
    "holder": {
      "type": "string"
    },
    "period_start": {
      "type": "string"
    },
    "period_end": {
      "type": "string"
    },
    "opening_balance": {
      "type": "number"
    },
    "closing_balance": {
      "type": "number"
    },
    "transactions": {
      "type": "array"
    },
    "avg_daily_balance": {
      "type": "number"
    },
    "nsf_count": {
      "type": "integer"
    }
  }
}

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 bank statements — run your own documents and compare against a small ground-truth set before you scale.

99.3%

illustrative field-level
accuracy ceiling

10starter fields

Anylanguage supported

25 MBmax file size

FieldAccuracy

opening_balance

99.6%

closing_balance

99.6%

transactions

99.7%

period_start

99.8%

holder

99.4%

avg_daily_balance

98.9%

nsf_count

99.2%

account_no_last4

99.7%

The API

One endpoint.
Every output you need.

# Extract with one POST
curl -X POST "https://api.docparse.io/v1/statements" \
  -H "Authorization: Bearer $DOCPARSE_KEY" \
  -F file=@"chase-march-2026.pdf" \
  -F schema="bank-statement" \
  -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)

Ocrolus / Plaid

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 bank statements.

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

“

We underwrite small-business loans on PDFs. Ocrolus was 96%, DocParse is 99.3% — that 3-point difference is hundreds of approvals a month.

Felix Tran

VP Risk · Lattice Bank

+3ptsunderwriting accuracy

“

Statements from credit unions used to crash our pipeline. DocParse parses every regional bank we throw at it. Coverage is the killer feature.

Wren Chen

Eng Lead · Northwave

4,200banks tested

“

The cash-flow summary fields meant our risk models worked on day one. We didn't need to derive anything ourselves.

Lucia Romano

Head of Underwriting · Tidemark

1 dayto model integration

Frequently asked

The questions teams ask before they sign up.

Which banks are supported?

4,200+ banks tested in benchmark including all top-200 US banks, all major UK/EU/AU banks, and most credit unions. Coverage adds 30-50 institutions per month based on customer demand.

Are transactions categorized?

Yes. Each transaction returns merchant name, MCC, and a category. Categories map to common chart-of-accounts schemes or you can supply your own taxonomy.

What about multi-statement reconciliation?

Send multiple periods for the same account; DocParse stitches them and returns continuous transaction history with running balance.

Is this used for underwriting?

Yes — 30+ lenders use DocParse for SMB underwriting. Returns the cash-flow summary fields lenders need: average daily balance, deposit count, NSF count, debt-service ratio.

Bank statements as a structured feed.

Every transaction, every bank, with categorization and lender-grade summaries.

Start extracting Talk to sales

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

Every transaction.Reconciled in real time.

Three reasons teams switch to us

Every bank, every layout

Transactions with categories

Lender-grade output

From raw bank statements
to structured data, in four steps.

Define the fields

Upload the file

Multi-modal AI reads it

Get structured data back

Starter schema for bank statements.
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 bank statements.

The questions teams ask before they sign up.

Bank statements as a structured feed.

Every transaction.Reconciled in real time.

Three reasons teams switch to us

Every bank, every layout

Transactions with categories

Lender-grade output

From raw bank statementsto structured data, in four steps.

Define the fields

Upload the file

Multi-modal AI reads it

Get structured data back

Starter schema for bank statements.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 bank statements.

The questions teams ask before they sign up.

Bank statements as a structured feed.

From raw bank statements
to structured data, in four steps.

Starter schema for bank statements.
Tweakable in seconds.

One endpoint.
Every output you need.