Atlas / AI assistant app
Upload a document and work through a summary in a conversation.
By Anthropic · This record describes the product and its workflow, not a benchmark of an individual model.
Files can be uploaded to individual chats or to a project's Files section for persistent reference across conversations. Supported document types include PDF, DOCX, CSV, TXT, HTML, ODT, RTF, EPUB, JSON, and XLSX (XLSX requires code execution and file creation enabled). Supported image formats are JPEG, PNG, GIF, and WebP.
Claude analyzes both text and visual elements (images, charts, graphics) in PDFs of 100 pages or fewer. For PDFs from 101 to 1000 pages, Claude processes text only and does not analyze visual elements. For non-PDF documents, Claude extracts text only and cannot read embedded images.
Chat uploads allow up to 20 files per chat, 500MB per file, up to 8000x8000 pixels for images, and PDFs up to 1000 pages. Project files are limited to 30MB per file with unlimited file count, but total content must fit within Claude's context window and supports text extraction only (except multimodal PDFs).
Latest source check: 2026-10-11. Confirm current plans and terms before committing.
Explore the category’s model records, capabilities and billing units. These are separate records; this page does not establish which models power this product.