Skip to main content
POST
/
api
/
v3
/
parse
Parse a document to Markdown
curl --request POST \
  --url https://api.lighton.ai/api/v3/parse \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: multipart/form-data' \
  --form 'file=(binary)'
{
  "id": "parse_0196e4b2a3c14d5e8f7a9b2c1d0e3f4a",
  "status": "completed",
  "created_at": "2026-03-31T10:00:00+00:00",
  "completed_at": "2026-03-31T10:00:03+00:00",
  "processing_time_ms": 2840,
  "document": {
    "filename": "invoice.pdf",
    "page_count": 3,
    "file_size_bytes": 245120,
    "mime_type": "application/pdf"
  },
  "result": {
    "content": "# Invoice\n\nInvoice Number: INV-2026-001\nDate: March 15, 2026\n..."
  },
  "usage": {
    "pages_processed": 3
  }
}

Documentation Index

Fetch the complete documentation index at: https://developers.lighton.ai/llms.txt

Use this file to discover all available pages before exploring further.

Authorizations

​
Authorization
string
header
required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Body

​
file
string<uri>

The document to parse. Use for multipart/form-data requests.

​
document
string<uri> | null

Publicly accessible URL of the document to parse. Use for JSON body requests.

Response

Document parsed successfully.

​
id
string
required
​
status
string
required
​
created_at
string<date-time>
required
​
completed_at
string<date-time>
required
​
processing_time_ms
integer
required
​
document
object
required
​
result
object
required
​
usage
object
required