Too bad they seem too busy to answer these questions, IMO that feels like a missed early leverage opportunity for them. We benchmarked a bit self hosted alternative, and nothing reach quite the cost/performance of Jev, yet.
Maybe it's possible via their Digital Ocean offering https://ideas.digitalocean.com/changelog/now-available-jev-f...
Why does this thing have to be another Web API?
The main benefit of Jev seems to be broader knowledge? But local models (especially the ones actually trained specifically for decisions, rather than ones that "support" it like embeddinggemma) are probably good enough for what most people use it for. They also seem to be quite easy to fine tune (I haven't tried, but seems to be what people say).
I mean, yes, that works at dev time; but going from zero to nonzero local inference components makes an agent implementation suddenly much more complex to ship to production / drastically narrows the set of hosts such an implementation can be deployed onto.
If you are sending data over the internet to someone else's computer, who you can't or won't audit, you should keep you expectations realistic.
You can be sure that comapnies will only do ZDR if your data is more expensive to keep than its utility to them, even if they claim something else.