Models
Max pages per request100 pages
Supported character setsA · 가 · あ · ア · 漢
OutputsClassification Result
Price
$0.004/pageStandard
The universal product for identifying document types across any format, including mixed-document files. It delivers consistent, template-free classification ready for enterprise workflows.
Format-agnostic classification
No templates or training required
Flexible labels for any workflow
Supported file formats
JPEGSupported
PNGSupported
BMPSupported
TIFFSupported
HEICSupported
PDFSupported
DOCXSupported
PPTXSupported
XLSXSupported
HWPSupported
HWPXSupported
Maximum file size
50MB
Maximum number of pages per file
Synchronous API: 100 pages (For files exceeding 100 pages, the first 100 pages are processed)
Maximum pixels per page
200,000,000 pixels
(For non-image files, the pixel count is determined after converting to images at a standard of 150 DPI.)
(For non-image files, the pixel count is determined after converting to images at a standard of 150 DPI.)
Supported character sets (if using OCR)
AlphanumericInput and output
HangulInput and output
HiraganaInput and output
KatakanaInput and output
HanjaInput and output
Hanzi (Beta)Not fully supported
Kanji (Beta)Not fully supported
Hanja, Hanzi, and Kanji are writing systems based on Chinese characters used in Korean, Chinese, and Japanese writing systems. Despite sharing similarities, they possess distinct visual representations, pronunciations, meanings, and usage conventions within their respective linguistic contexts. For more information, see this article.
Available Platforms
Upstage Console
API privacy
Data not collectedUpstage does not collect any data from this API
- API input data is not used for model training.
- API input data is not stored, unless required for service delivery and explicitly stated.