Document Parsing

The Parsing Model extracts and parses structured data from IDs and documents — names, dates, addresses, amounts, and more.

Available Models

Model	Use Case	Supported File Types
`light`	Parsing light model. Data extraction is aimed at Driver License, State ID, Residency Permit, Social Security Card, Military ID	jpg, jpeg, png, webp, pdf
`performance`	Parsing performance model. Data extraction is aimed at bank statements, US pay stubs, and common government-issued IDs (for example driver licenses)	jpg, jpeg, png, webp, pdf

Retrieve the full list of models programmatically:

curl https://api.deepxl.ai/v1/parsing-models \
  -H "x-api-key: YOUR_API_KEY"

Parsing a Document

Submit a file for parsing via POST /v1/parse:

curl -X POST https://api.deepxl.ai/v1/parse \
  -H "x-api-key: YOUR_API_KEY" \
  -F "model=light" \
  -F "file=@drivers_license.jpg" \
  -F 'tags={"customerId":"9999","customerName":"Acme Corp","documentId":"DOC-001","companyName":"DeepXL","companyId":"COMP-001"}'

Parameters

Parameter	Type	Required	Description
`model`	string	Yes	`light` or `performance`
`file`	file	Yes	The document to parse (max 50MB)
`tags`	string	No	JSON object with metadata key-value pairs
`country`	string	No	Optional country hint. Supported values: `us`, `mx`, `br`. Missing, empty, or invalid values default to `us`.

Country Hint Behavior

Use the optional country parameter when you want to steer parsing toward a specific supported market.

Supported values: us, mx, br
Matching is case-insensitive
Leading and trailing whitespace is ignored
Missing, empty, or invalid values fall back to us

The request value is treated as a routing hint. It is normalized before the request is forwarded downstream, and the normalized value is returned as country in the parse response metadata. Example:

curl -X POST https://api.deepxl.ai/v1/parse \
  -H "x-api-key: YOUR_API_KEY" \
  -F "model=performance" \
  -F "file=@bank_statement.pdf" \
  -F "country=br" \
  -F 'tags={"customerId":"9999","customerName":"Acme Corp","documentId":"DOC-2024-042","companyName":"DeepXL","companyId":"COMP-001"}'

Response Structure

{
  "result": {
    "parseId": 123,
    "mediaType": "image",
    "fileType": "jpeg",
    "fileName": "drivers_license.jpg",
    "fileSize": 231433,
    "timestamp": 1770984134,
    "timestampISO": "2026-02-13T13:02:14.833162",
    "model": "light",
    "modelVersion": "1.2.0",
    "documentType": "idDocument",
    "parsedData": {
      "firstName": "JOHN",
      "lastName": "DOE",
      "dateOfBirth": "1990-05-15",
      "licenseNumber": "D1234567",
      "expirationDate": "2028-05-15",
      "address": "123 MAIN ST ANYTOWN, CA 90210"
    },
    "tags": [
      { "name": "customerId", "value": "9999" },
      { "name": "customerName", "value": "Acme Corp" },
      { "name": "documentId", "value": "DOC-001" },
      { "name": "companyName", "value": "DeepXL" },
      { "name": "companyId", "value": "COMP-001" }
    ],
    "files": [
      {
        "category": "original_file",
        "fileName": "drivers_license.jpg",
        "fileSize": 231433,
        "contentType": "image/jpeg",
        "timestamp": 1770984134,
        "timestampISO": "2026-02-13T13:02:14.833162",
        "url": "https://api.deepxl.ai/v1/files/parse_123_drivers_license.jpg"
      }
    ]
  }
}

Field Reference

Field	Type	Description
`parseId`	integer	Unique identifier for the parse record
`mediaType`	string	Media type category (`image` or `document`)
`fileType`	string	File extension (`jpeg`, `png`, `pdf`, `webp`)
`fileName`	string	Original uploaded file name
`fileSize`	integer	File size in bytes
`timestamp`	integer	Unix timestamp of the analysis
`timestampISO`	string	ISO 8601 timestamp of the analysis
`model`	string	Model used (`light` or `performance`)
`modelVersion`	string	Version of the model used for analysis
`documentType`	string	Identified document type (e.g. `idDocument`, `bankStatement.us`, `payStub.us`)
`parsedData`	object	Extracted key-value pairs (fields vary by document type)
`tags`	object[]	Metadata tags attached to this parse
`files`	object[]	Associated files (original upload)

Understanding Results

Document Type

The documentType field identifies the parsed document type (for example idDocument, bankStatement.us, or payStub.us).

Parsed Data

The parsedData object contains the extracted key-value pairs. The fields depend on the document type. ID Documents (light model):

Field	Description
`firstName`	First name
`lastName`	Last name
`dateOfBirth`	Date of birth (YYYY-MM-DD)
`licenseNumber`	License or document number
`expirationDate`	Document expiration date (YYYY-MM-DD)
`address`	Full address

performance model document types: The extracted fields vary by document type. The current set is idDocument, bankStatement.us, and payStub.us.

Tags and Filtering

Attach metadata to organize your parsing results:

curl -X POST https://api.deepxl.ai/v1/parse \
  -H "x-api-key: YOUR_API_KEY" \
  -F "model=performance" \
  -F "file=@bank_statement.pdf" \
  -F 'tags={"customerId":"9999","customerName":"Acme Corp","documentId":"DOC-2024-042","companyName":"DeepXL","companyId":"COMP-001"}'

Filter your parse history:

curl "https://api.deepxl.ai/v1/parse?tagFilter=customerId=9999" \
  -H "x-api-key: YOUR_API_KEY"

Browsing History

Retrieve paginated parsing results:

curl "https://api.deepxl.ai/v1/parse?limit=25&offset=0&sortBy=parseId&direction=desc" \
  -H "x-api-key: YOUR_API_KEY"

Sort Options

parseId, mediaType, fileType, fileName, fileSize, confidence, documentType, timestamp

Getting Started

Guides

Integrations

Document Parsing

Available Models

Parsing a Document

Parameters

Country Hint Behavior

Response Structure

Field Reference

Understanding Results

Document Type

Parsed Data

Tags and Filtering

Browsing History

Sort Options

​Available Models

​Parsing a Document

​Parameters

​Country Hint Behavior

​Response Structure

​Field Reference

​Understanding Results

​Document Type

​Parsed Data

​Tags and Filtering

​Browsing History

​Sort Options

Available Models

Parsing a Document

Parameters

Country Hint Behavior

Response Structure

Field Reference

Understanding Results

Document Type

Parsed Data

Tags and Filtering

Browsing History

Sort Options