Choosing a model

Updated Jul 12, 2026 · 1 min read

Pick any model from the OpenRouter catalog, and optionally include thumbnails in prompts if the model can see images.

The AI settings include a model picker fed by the live OpenRouter catalog, with a solid default already selected. Out of the box, tagging works from text: the model reads a file's name, folder path, and existing tags, and writes tags plus a searchable description from those.

There's also an optional “Include thumbnails in AI prompts” switch. Turn it on and Meshory attaches a small copy of each model's rendered thumbnail, which sharpens tags considerably for cryptically-named files. It requires a vision-capable model: the switch only activates when the model you've picked accepts images.

Beyond that it's a trade-off you control: stronger models produce better tags and descriptions but cost more per model; lighter models are cheaper for tagging a huge library. Settings shows a cost estimate for the model you've picked, and because you're billed by OpenRouter per use, you decide where to land.