curl -X POST 'https://api.va.landing.ai/v2/ade/parse' \
-H 'Authorization: Bearer YOUR_API_KEY' \
-F 'document=@document.pdf' \
-F 'model=dpt-3-pro-latest'{
"markdown": "<string>",
"metadata": {
"job_id": "<string>",
"filename": "<string>",
"version": "<string>",
"page_count": 123,
"duration_ms": 123,
"failed_pages": [
123
],
"markdown_chars": 0,
"credit_usage": 0
},
"structure": {
"type": "document",
"children": [
{
"page": 123,
"span": [
123,
123
],
"type": "page",
"width": 123,
"height": 123,
"dpi": 123,
"status": "ok",
"reason": "<string>",
"children": [
{
"id": "<string>",
"span": [
123,
123
],
"children": [
"<unknown>"
],
"row": 123,
"col": 123,
"colspan": 123,
"rowspan": 123
}
]
}
]
},
"grounding": {}
}Parse
Parse a PDF or image into structured data using DPT-3, a document parsing model from LandingAI.
Use the response to power retrieval-augmented generation (RAG), intelligent search, key information extraction, and automated document workflows.
Each call returns a reading-order Markdown rendering of the document, a hierarchical structure of its pages and elements, per-element grounding back to the source, and metadata about the request (such as model version, duration, page count, and credit usage).
curl -X POST 'https://api.va.landing.ai/v2/ade/parse' \
-H 'Authorization: Bearer YOUR_API_KEY' \
-F 'document=@document.pdf' \
-F 'model=dpt-3-pro-latest'{
"markdown": "<string>",
"metadata": {
"job_id": "<string>",
"filename": "<string>",
"version": "<string>",
"page_count": 123,
"duration_ms": 123,
"failed_pages": [
123
],
"markdown_chars": 0,
"credit_usage": 0
},
"structure": {
"type": "document",
"children": [
{
"page": 123,
"span": [
123,
123
],
"type": "page",
"width": 123,
"height": 123,
"dpi": 123,
"status": "ok",
"reason": "<string>",
"children": [
{
"id": "<string>",
"span": [
123,
123
],
"children": [
"<unknown>"
],
"row": 123,
"col": 123,
"colspan": 123,
"rowspan": 123
}
]
}
]
},
"grounding": {}
}Documentation Index
Fetch the complete documentation index at: https://docs.landing.ai/llms.txt
Use this file to discover all available pages before exploring further.
Body
The file to parse. The file must be a PDF or image; see the list of supported file types. Provide either document or document_url, not both.
A publicly accessible URL to the file to parse. The file must be a PDF or image; see the list of supported file types. Provide either document or document_url, not both.
The DPT-3 model snapshot to use for this request. Accepts a dated snapshot (for example, dpt-3-pro-20250101) or the dpt-3-pro-latest alias. Defaults to the latest DPT-3 Pro snapshot.
Optional JSON object that customizes the parse. Use it to select which pages to process, adjust how content appears in the Markdown, or control how much detail the response includes.
Response
Successful Response
The full document as a single Markdown string, in reading order.
Information about the request: model version, page count, duration, credit usage, and more.
Show child attributes
Show child attributes
The document's hierarchical structure: pages and the elements detected on each page. Spatial information for each element is in grounding.
Show child attributes
Show child attributes
A map keyed by element ID. Each entry carries the element's page, bounding box, Markdown span, and finer-grained parts.
Show child attributes
Show child attributes
Was this page helpful?