Claude Fable 5.1
Provider status: active; identity checked 2026-10-08. Documented support: Work with long documents; Call tools and functions; Understand images.
$10 input / $50 output per million tokens
Atlas / Find your approach
Get a useful summary and a way to check where the answer came from.
Your situation
Choose a priority above, or start with these questions.
Open questions will travel with your prompt. Nothing is assumed on your behalf.
The practical differences
Keep the wider workflow in view as you decide.
The Gemini Notebook mobile app may have limitations to chat features; Live Voice Chat is currently available only to users ages 18+ on the mobile app.
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).
You can upload sources and ask the model questions, give instructions, or select which sources the model should use. Agentic capabilities allow searching the web, running code, and creating downloadable files, charts, and images with or without sources.
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.
Gemini Notebook uses direct quotes, text, and images from your sources as citations to help check response accuracy. Hovering over a citation shows the full quoted text; selecting it navigates to the quote in context.
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.
Latest source check: 2026-10-15. These are product offerings, not individual model benchmarks. Plans and availability can change.
Candidates reflect current provider identities and documented capability coverage. A newer release is not evidence of better output quality.
Model and API access can differ from the models available in your chosen app.
Provider status: active; identity checked 2026-10-08. Documented support: Work with long documents; Call tools and functions; Understand images.
$10 input / $50 output per million tokens
Provider status: active; identity checked 2026-10-08. Documented support: Work with long documents; Call tools and functions; Understand images.
$4 input / $20 output per million tokens
Provider status: active; identity checked 2026-10-08. Documented support: Work with long documents; Call tools and functions; Understand images.
$2 input / $10 output per million tokens
When the next step gets complicated
Take the prompt and keep building. If you hit a roadblock, we can help with the architecture, integrations, or an AI-built app that needs experienced hands.