I’m building several projects in confidential inference space (enclava.ai, Mango AI) so I tend to stay on top of providers in the space, what they offer and how the industry is developing. I’ve had many conversations with friend building AI things about inference providers, explaining them which providers to use or more frequently just letting them know that there are alternatives. So I decided to build a website - confidentialinference.net
Pricing in confidential inference space is very …. varied (to put it mildly). And to make things even more interesting the amount of companies that offer confidential models vs the amount of companies who actually run the infrastructure instead of just reselling other providers with a markup tends to be significantly different number. Not to mention the even lower number - companies who actually expose all the data needed to perform actual remote attestation so we can be sure the models are confidential and can verify there stack. That number is even smaller.
For now I’m primarily focusing on models offered and their pricing on the website but I’m planning to expand the data with mode details (anonymous payments, proper remote attestation capabilities etc). The providers listed are providers who have directly consumable api infrastructure, there are other providers which do have confidential inference offering but its hidden behind enterprise agreeements and “contact sales” forms which are a big anti pattern in my book so they don’t get to be on the list.
The data is somewhat automatically updated on weekly-ish basis (not all providers are very transparent with the pricing or make it easy to figure out what their prices actually are).