File uploads (PDF, image, CSV, docx, code)

File uploads on claude.ai let you attach documents and media directly to your conversations so Claude can read, analyze, and reason about their contents. Supported formats include PDFs, images (PNG, JPG, GIF, WebP), plain text, Markdown, CSV, TSV, DOCX, XLSX, and code files. Claude can analyze both the text and visual elements—such as charts, diagrams, and embedded graphics—within uploaded files, making it useful for everything from quick document summaries to complex multi-file analysis. Files can be attached in two ways on claude.ai: directly to an individual chat (temporary, lasts only for that conversation) or uploaded to a Project's Files section (persistent across all conversations within that project). Via the API, developers can use the Files API beta to upload files up to 500 MB, store them server-side, and reference them by a unique file ID across multiple requests without re-uploading each time. File uploads are available across all plans—Free, Pro, Max, Team, and Enterprise—with some differences in limits and which file types require additional features like code execution. The core upload-and-analyze workflow works for most file types on all plans, while features like XLSX upload and file creation (generating output files) require code execution to be enabled, which is available on paid plans.