Prism vs PageExtract

Offline AI in your pocket. Prism is a native AI workspace for iPhone, iPad, and iPhone Duo. Run models on your own hardware with Apple Intelligence or Prism’s custom llama.cpp engine. Download models directly in Prism or import compatible GGUF files. Your conversations, model files, and settings stay on your device. No account, subscription, or cloud inference service required. Control your inference Use Metal GPU acceleration with supported models and configure how they run. Adjust context length, response limits, batch size, temperature, Top-P, Top-K, and repeat penalty. Define your own system prompt and inspect prompts in Developer Mode. Explore local models Browse a curated library of compact text, reasoning, and vision models. Download models in the background or import compatible GGUF files from Files and HTTPS URLs. Attach images with supported vision models. Measure performance Track generation speed in tokens per second, token counts, and generation duration. Review performance trends and compare runs across your local models. Keep your work close Search and reopen saved conversations, review formatted responses and inline reasoning, and export transcripts as Markdown or JSON. Thinking duration is shown for supported models. Built for Apple devices Work in a focused native interface with layouts adapted to iPhone, iPad, and iPhone Duo. Available in English, German, and Turkish. Once your chosen model is downloaded and ready, inference works offline. Internet access is required for model downloads and catalog updates. Prism does not collect analytics or telemetry. Requires iOS 26 or iPadOS 26 or later. Apple Intelligence requires a supported device and must be enabled. Model compatibility, image support, and performance depend on the selected model and available device memory.

PageExtract pulls apart any web page and shows you everything inside — article text, images, fonts, stylesheets, scripts, links, and metadata. Paste a URL and get a complete breakdown of the page. Read the article as clean plain text or Markdown. Browse every image with dimensions and alt text. Inspect linked stylesheets and JavaScript files. View web fonts, hyperlinks, meta tags, Open Graph data, and HTTP response headers. WHAT YOU CAN EXTRACT • Article text — clean plain text or Markdown, free of ads and clutter • Images — every image on the page with dimensions, alt text, and download • Links — all internal and external hyperlinks • Fonts — web font families, weights, styles, and font file sources • Source files — CSS stylesheets and JavaScript files with sizes • Metadata — meta tags, Open Graph data, and page properties • HTTP headers — full server response headers • Full HTML — the complete page source EXPORT & SHARE • Copy extracted text to the clipboard • Share as .txt, .md, or PDF file • Download images and source files for offline access • Open the original page in your browser BATCH PROCESSING Queue multiple URLs and extract them all at once. Ideal for research, site auditing, archiving, or content migration. SAVE TO YOUR LIBRARY Build a searchable library of your extractions. Each saved item preserves everything — the full article, all images, every link, fonts, metadata, and source files. SHARE FROM ANY APP Use the Share Sheet extension to extract page content directly from Safari, Chrome, or any app that shares URLs. SYNC WITH ICLOUD Enable iCloud sync to keep your library available on all your iPhone and iPad devices. PRIVACY BY DESIGN All extraction happens on your device using a local web engine. No server uploads, no account required, no tracking. Lock the app with Face ID or Touch ID for added security. MAKE IT YOURS • Light, dark, and system appearance • Custom accent colors • Alternate home screen icons Terms of Use (EULA): https://www.apple.com/legal/internet-services/itunes/dev/stdeula/