One OpenAI-compatible API for hundreds of models on attested infrastructure, end to end encryption, with Confidential routes, ZDR routes, provider failover, BYOK, and no prompt or output logs.
hey everybody, I started trustedrouter.com, which is a really simple way to use AI without needing to give your data to a third party like a close source router
It’s been really fun to build this because I got to know the CEOs and founders of so many different providers. We now have more providers than open router and more models as well. More on that soon
We are doing a lot of innovations in security and skills that advise you on which LLM to use and also we created a new site called anyeval.com that I expect to be a critical part of the open-source infrastructure for AI on the Internet. Other companies like AAII postbenchmarks, but you’d have no idea about what they’re really doing and how they’re really measuring, and they have a ton of gaps about which models they’re doing their tests on because it’s so expensive. The idea behind any eval is so that you can pay the few pennies it costs to run an individual problem in an eval, and then as a together as a collective, we can crowdsource paying for a whole eval for any model that we want, or you can just pay for a random sample of the problems to get a an and some Arab artists on what you think that the quality of that model is. You can do head-to-head comparisons. You can also create whole new evals.
For example, I created this new eval called honey pot bench or honey bench, which recreates the some of the facts of the hugging face incident to measure whether a particular AI is prone to wanting to escape, and I found that Fable in particular, unlike the other Claude’s, is very unaligned in comparison
I also created freedom bench, which measures the amount of censorship related to Chinese censorship that a model has, and found that it’s mostly the provider level monitor provided at the providers in China, but not the US providers that does the censitions. I don’t see as much censorship in the model weights
Report
@_joseph_perla_ Really like the idea of having one interface across models without giving up control of the data. How does the routing work in practice, can I set rules for which model handles which type of request, or does TrustedRouter automatically choose the model based on the task?
@saksham_shukla3 you have full control. you set the model and provider.
Report
@_joseph_perla_ Got it, that makes sense. I actually prefer having explicit control over the model/provider for different workloads. Congrats on the launch Joseph!
Report
What happens when a Confidential route fails over? Does it stay attested, or can it land on a normal provider? Nice launch by the way.
@niveditha_patluri1 nope it goes to another attested provider until one answers and only if they’re all down does it fail. you have full control over which providers you trust
I've been hearing the privacy/confidentiality/anonymity pitch a lot in this space and I'm a little confused what different platforms mean by it. Can you help me understand how y'all compare vs OpenRouter & Venice? Seems like pricing is the same, but how you talk about privacy isn't.
@gasiorekm privacy and security is paramount and we take it very seriously. ask your claude to do remote attestations end to end with trustedrouter and see that it works fully: not the case with any others.
Report
Competition is always, mostly, good for the consumer. I'm a happy openrouter customer and I get the switch the base URL one line temptation. What's not clear to me is the APIs available to get the logs, routing, etc. for my auditing. I may have missed it in the documentation. I applaud this effort. Well done.
TrustedRouter
@_joseph_perla_ Really like the idea of having one interface across models without giving up control of the data. How does the routing work in practice, can I set rules for which model handles which type of request, or does TrustedRouter automatically choose the model based on the task?
TrustedRouter
@saksham_shukla3 you have full control. you set the model and provider.
@_joseph_perla_ Got it, that makes sense. I actually prefer having explicit control over the model/provider for different workloads. Congrats on the launch Joseph!
What happens when a Confidential route fails over? Does it stay attested, or can it land on a normal provider?
Nice launch by the way.
TrustedRouter
@niveditha_patluri1 nope it goes to another attested provider until one answers and only if they’re all down does it fail. you have full control over which providers you trust
TrustedRouter
I've been hearing the privacy/confidentiality/anonymity pitch a lot in this space and I'm a little confused what different platforms mean by it. Can you help me understand how y'all compare vs OpenRouter & Venice? Seems like pricing is the same, but how you talk about privacy isn't.
TrustedRouter
@gasiorekm privacy and security is paramount and we take it very seriously. ask your claude to do remote attestations end to end with trustedrouter and see that it works fully: not the case with any others.
Competition is always, mostly, good for the consumer. I'm a happy openrouter customer and I get the switch the base URL one line temptation. What's not clear to me is the APIs available to get the logs, routing, etc. for my auditing. I may have missed it in the documentation. I applaud this effort. Well done.
TrustedRouter
@rick_segal1 plz point your agent at TrustedRouter.com/docs
@_joseph_perla_ Well, yeah, there's that, sure. I was doing that weird thing. Reading them manually. :-)
But if Mark Heynen, sez yer good, yer good.
Great platform, pricing and people! Been using it for the past month after moving over from openrouter 👍🏻
Tiny Notes
let's gooooo joseph! fresh approach
Jammy Chat
Congrats on the launch, Joseph! 🚀