Claude can work with various types of documents within chats and Project knowledge bases to help you analyze and understand their contents.
We currently support the following document types:
PDF
DOCX
CSV
TXT
HTML
ODT
RTF
EPUB
JSON
File Limits
Chat uploads:
File size: 30MB per file
Number of files: Up to 5 files per chat
Project knowledge bases:
File size: 30MB per file
Number of files: Unlimited, but total content must fit within Claude's context window.
Text extraction only, regardless of document type.
Note: Additional token limits apply to these limits based on the length of the extracted content
PDF Processing
Visual analysis:
Visual PDF analysis requires enabling the feature preview. Learn how to enable visual PDF analysis here.
When the feature preview is enabled, Claude 3.5 Sonnet can analyze both text and visual elements (like images, charts, and graphics) in PDFs that are:
Under 100 pages
Uploaded directly to a chat
Text-only analysis:
Claude will only process the text (not images) from PDFs when:
The PDF is over 100 pages
You're using a model other than Claude 3.5 Sonnet
The PDF is uploaded to a Project's knowledge base
Important Notes
When referring to specific pages of a PDF, use the PDF page numbers as shown in your PDF viewer, not the page numbers printed on the document itself.
For non-PDF documents, Claude will only extract text. If these files contain images, Claude won't be able to read or interpret them.
If you're working with larger documents, we recommend dividing your file into smaller sections to stay within these limits.