Extracting data from crypto account statements
Exchanges, custodians and block explorers each produce cryptocurrency account statements in their own layout, listing an account's transactions for a period. Mortgage lenders collect them from every applicant whose down payment comes from selling crypto, as PDFs exported from the platform and uploaded to the loan portal.
Underwriting needs the balances, the totals received and sent, and each transaction's date, direction and USD value. The lender traces the funds from the account to a deposit in the borrower's bank account before they count toward closing.
What makes crypto account statements hard
Amounts to eight decimals
Bitcoin amounts run to eight decimal places, and each sits beside a USD value at the price when the transaction settled.
Long identifiers that wrap
A 64-character transaction hash or a wallet address often wraps across two lines inside one narrow table cell.
Every platform has its own layout
An exchange statement, a custodian report and a block explorer export differ in their columns and in how they mark a send or a receipt.
Parse, extract, verify
Parse
Parse turns the document into reading-order Markdown and a hierarchy of blocks (text, tables, figures), and grounds each block to its exact location on the page.
Extract
You define the fields in a JSON schema, and Extract returns their values in a consistent, structured format, each linked back to where it appears in the Markdown.
Verify
Each value links back to where it appears, down to the character range in the Markdown, and the page and bounding box in the source document, so every result can be verified.
One cryptocurrency account statement, end to end
About this document: A Bitcoin wallet statement generated by Blockchair, a block explorer. Two portrait pages: a header with the wallet address and statement period, a balance summary, then a 16-row transaction history that runs onto page 2. Page 1 is featured. The wallet address and every transaction hash were replaced with stand-ins.
Processing objective: The objective is to read one transaction whole. A send of bitcoin carries its time, its direction, the amount in BTC to eight decimal places and its USD value when it settled. Each value grounds to its own cell in that transaction's row.
Demonstration fields: Transaction time, Direction, Amount (BTC), Amount (USD)
The document
2 of 2 pages
Page 1shown below
Page 2
Where each value came from
transactions[2].time
{
"value": "11:12:12",
"page": 1,
"range": {
"end": 4177,
"start": 4155
},
"box": {
"xmin": 0.07327,
"ymin": 0.57897,
"xmax": 0.20631,
"ymax": 0.62221
}
}transactions[2].direction
{
"value": "Sent",
"page": 1,
"range": {
"end": 4190,
"start": 4186
},
"box": {
"xmin": 0.20631,
"ymin": 0.57896,
"xmax": 0.3203,
"ymax": 0.62222
}
}transactions[2].amount_crypto
{
"value": 0.02314739,
"page": 1,
"range": {
"end": 4209,
"start": 4199
},
"box": {
"xmin": 0.32025,
"ymin": 0.57895,
"xmax": 0.50566,
"ymax": 0.62222
}
}transactions[2].amount_usd
{
"value": 1134.36,
"page": 1,
"range": {
"end": 4226,
"start": 4218
},
"box": {
"xmin": 0.5056,
"ymin": 0.57894,
"xmax": 0.63915,
"ymax": 0.62222
}
}How to try it yourself
Everything on this page is reproducible. The sample, its schema, and the Parse and Extract API outputs are published. You can repeat the same two calls from whichever surface you already build on.
- Claude Skilldescribe the job; the agent writes it
- CLIno code at all
- MCPexpose ADE docs as an agent tool
- REST APIany language
- Pythonlandingai-ade
- TypeScriptlandingai-ade
Documents into data
Accurate
The best accuracy on the difficult documents other tools get wrong, such as messy scans, complicated tables, checkboxes and handwriting.
Auditable
Every answer cites its sources. Values come back with an audit trail (page, bounding box, character range) so a human can review them.
Agentic
Applies multi-step reasoning, and plans before it acts. Handles documents it has never seen before and adapts to variations.
API-first
Composable APIs that drop into any tech stack and can be called from anywhere. Easy to build on and embed in your pipelines and products.
Affordable
Cost-competitive rates with complete price transparency. Spend controls before you run, and every job reports its exact cost.
Enterprise-grade
Built for production and scale from day one. Fully observable and monitored, running securely in our cloud or yours.
Built for high-volume, high-throughput production
- Zero data retention
- Priority rate limits
- Enhanced support
- VPC and on-prem deployment
Available on Team and Enterprise plans.
