Parse

Document parsing (PDF, images, OCR)

Parse documents into structured markdown. Supports PDF, images, and scanned documents. Fast mode is synchronous (~15 pages/sec), HiRes mode is asynchronous with OCR (~16 pages/min).

post/api/parse

Request body

urlstring

Document URL

base64string

Base64-encoded file content

filenamestring

Filename hint (required with base64)

mode'fast' | 'hires' | 'auto'

fast: ~15 pages/sec, synchronous. hires: ~16 pages/min, asynchronous with OCR. auto: server chooses.

output'markdown' | 'json'

waitboolean

Wait for async result (block until complete)

imageMode'embedded' | 's3'

How to handle images in output

promptTypestring

Custom prompt type for OCR

callbackUrlstring uri

URL for async completion callback

includeDetectionboolean

Include detection data in response (bboxes, element types)

Response

Success (sync or async)

successboolean

requestIdstring

Unique request identifier

mode'fast' | 'hires'

asyncboolean

taskIdstring

Task ID for async polling

status'completed' | 'processing'

processingTimeinteger

Changes

No recorded changes to this endpoint across all 1 revision of this API.