DEVONthink 4.0 Beta 3

New AI models are sprouting like mushrooms. Today’s DEVONthink 4.0 public beta 3 brings support for cutting-edge models such as Anthropic's Claude 4, Sonnet, and Opus, Perplexity's Sonar Reasoning models, and Mistral Medium 3.

Icons make it easier to see at a glance which AI provider you’re working with, separate AI > Summarization settings let you better control how DEVONthink summarizes documents, and you can exclude documents or whole groups from being ever accessed by AI. The chat assistant can draft an email for you, and it has more reliable rendering of lists, code blocks, and MathJax. Finally, we have made numerous under-the-hood changes to reduce costs, control the exchange of information, and filter irrelevant information to produce better responses.

AI aside, a new toolbar button simplifies creating compressed archives of databases, while improvements in metadata handling, Markdown editing, and PDF processing enhance usability and performance. In addition, DEVONthink sends us some anonymized data that can help us determine, e.g., if some features or actions are more popular than others. Of course, you can switch this off in the app’s settings. The update also includes numerous fixes addressing stability issues, UI inconsistencies, and script compatibility.

Another maintenance update for DEVONthink 3 brings some improvements over from version 4. Download version 3.9.11 from the Legacy Download page.