Doc2X V3 PDF Conversion
- Doc2X V3 PDF document conversion model, converting PDF into Markdown / LaTeX / DOCX formats
- Supports formula recognition and cross-page table merging
- The result is a ZIP archive (containing the converted document and image assets), downloaded via
results[0].url - Asynchronous processing mode; use the returned task ID to query the result
- The result format is
{url}, where the URL points to a downloadable ZIP archive containing the converted document files (md / tex / docx) and image assets. See Task Query Special Format Notes - The ZIP link is valid for 24 hours; please download and save it promptly
Authorizations
All endpoints require Bearer Token authentication
Add the following to your request header:
Authorization: Bearer YOUR_API_KEY
Body
doc2x-v3: PDF → md / tex / docx conversion; the result is a downloadable ZIP archive
"doc2x-v3"
Download URL of the PDF file
"https://example.com/document.pdf"
Number of PDF pages, used for pre-authorization billing and runtime validation
x >= 110
Output format
md, tex, docx "md"
Formula processing mode
normal, dollar "normal"
Output file name (without extension; truncated at runtime if it exceeds 50 characters)
200"output"
Whether to merge cross-page tables
false
Response
Task created successfully
Task creation timestamp
1757165031
Task ID
"task-unified-1757165031-uyujaw3d"
The actual model name used
The specific type of the task
document.generation.task Task progress percentage (0-100)
0 <= x <= 1000
Task status
pending, processing, completed, failed "pending"
Asynchronous task information
The output type of the task
document "document"