docs
UAEN
API Reference

Convert Document

Convert a PDF, image, or document to markdown, HTML, JSON, or chunks. Use save_checkpoint=true to save parsed state for later /extract or /segment calls.

POST/api/v1/convert

Authorizations

X-API-Keystringheaderrequired
Your API key for authentication

Body Parameters

file_urlstringbody
Optional file URL (http/https). If provided, the server will download and process it.
modestringbody
Output mode: 'fast' (lowest latency), 'balanced', 'accurate' (highest accuracy).
max_pagesintegerbody
Maximum number of pages to convert.
page_rangestringbody
Page range to convert, comma separated like 0,5-10,20. Overrides max_pages.
paginatebooleanbody
Paginate the output. Pages separated by horizontal rule with page number.
add_block_idsbooleanbody
Add data-block-id attributes to HTML elements for citation tracking.
include_markdown_in_chunksbooleanbody
Include markdown field in chunks and JSON output.
disable_image_extractionbooleanbody
Disable image extraction from the document.
disable_image_captionsbooleanbody
Disable synthetic image captions/descriptions in output.
fence_synthetic_captionsbooleanbody
Wrap synthetic image captions with HTML comment markers.
output_formatstringbody
Output format: 'markdown', 'html', 'json', 'chunks'.
token_efficient_markdownbooleanbody
Use token-efficient markdown output.
skip_cachebooleanbody
Skip the cache and re-run.
save_checkpointbooleanbody
Save a checkpoint after processing for future /extract or /segment calls.
additional_configstringbody
Additional configuration as JSON string.
webhook_urlstringbody
Optional webhook URL to call when complete.
force_newbooleanbody
Force a new conversion even if cached.
filefilebody
Input PDF, Word, PowerPoint, or image file. Images must be png, jpg, or webp.

Cookies

wos-sessionstringcookie
Session cookie
access_tokenstringcookie
Access token cookie
datalab_active_teamstringcookie
Active team cookie

Response

Successful Response
Convert Document
import requests

url = "https://www.datalab.to/api/v1/convert"
files = {
    "file.0": ("example-file", open("example-file", "rb"))
}
payload = {
    "file_url": "<string>",
    "mode": "fast",
    "max_pages": "123",
    "page_range": "<string>",
    "output_format": "<string>",
    "skip_cache": "false",
    "save_checkpoint": "false"
}
headers = {"X-API-Key": "<api-key>"}
response = requests.post(url, data=payload, files=files, headers=headers)
print(response.text)
200Success
{
  "request_id": "<string>",
  "request_check_url": "<string>",
  "success": true,
  "error": "<string>",
  "versions": {}
}
← PreviousCreate DocumentNext →Extract Structured Data