More filter options
OpenUpdated Sep 9, 20261 reply
More filter options for models (all of them) would be useful, such as "can be coaxed easily into NSFW", "does not guarantee privacy", etc...
NanoGPT teamSep 9, 2026
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.