View the input types supported by Parse and Extract, the playground upload limits, and the boundaries of reusable results.
Parse supports document/image content, audio, and video; Extract only supports document/image input. Before submitting, confirm that the capability matches the file type.
Extract supports the document/image files listed above and does not support audio or video. Input can be:
Reusing a ParseResult avoids parsing the same file again. Audio or video ParseResults cannot be used for Extract.
Capability scope
| Input type | Parse | Extract |
|---|---|---|
| Documents, images, scans, spreadsheets, and text | Supported | Supported |
| Audio | Supported | Not supported |
| Video | Supported | Not supported |
| Valid document/image ParseResult | — | Supported for reuse |
Formats supported by Parse
Document/image files
| Category | Formats |
|---|---|
| Documents | .pdf、 .doc、.docx、.rtf、.pages 、.ppt、.pptx、.key 、.xls、.xlsx、.xlsm、.csv、.numbers |
| Images | .png、.jpg、.jpeg、.bmp、.gif |
| Text | .md、.markdown、.txt |
| Web pages | .html、.htm |
| E-books | .epub、.mobi |
Audio and video
| Category | Formats |
|---|---|
| Audio | .mp3、.wav、.aac、.amr、.flac、.ogg、.opus、.wma |
| Video | .mp4、.mkv、.avi、.mov、.wmv、.flv、.mpeg、.webm |
Formats supported by Extract
Extract supports the document/image files listed above and does not support audio or video. Input can be:
| Category | Formats |
|---|---|
| Documents | .pdf、.doc、.docx、.rtf、.ppt、.pptx、.xls、.xlsx、.xlsm、iWork（Keynote、Numbers、Pages） |
| Images | .png、.jpg、.jpeg、.bmp、.gif |
| Text | .md、.markdown、.txt |
| Web pages | .html、.htm |
| E-books | .epub、.mobi |
Maximum size per file
| Input type | API | Console upload |
|---|---|---|
| Documents, text, web pages, e-books | 1 GB | 200 MB |
| Images | 20 MB | 20 MB |
| Audio | 2 GB | 200 MB |
| Video | 10 GB | 200 MB |