More filter options
More filter options for models (all of them) would be useful, such as "can be coaxed easily into NSFW", "does not guarantee privacy", etc...
We’ve added privacy information to the model browser, including a “ZDR available” filter and provider badges covering retention and training policies. The filter shows models with a zero-data-retention provider available; it doesn’t itself change routing. This covers the privacy part of your suggestion, although we don’t currently offer a filter rating how easily a model can be prompted into NSFW responses.
We’ve added more filters to the text models page (nano-gpt.com/models/text), under More filters: "Open source only", a price ceiling ($1, $5 or $15 or less per 1M tokens), and a Creators filter to show only, or hide, models from chosen companies. They also work with search and are saved in the page link. We still don’t have a filter for how easily a model goes NSFW.