Show HN: We built open OpenRouter that turns usage into a better model

Areibman | 6 hours ago

Could you say more about how caching works? One major advantage of sticking with a single model is saving money on cached input tokens. I'd imagine if you swap between a bunch of models, you may improve performance but cost would would balloon out of control

purplecats | 6 hours ago

and caching is related to performance too ofc

[OP] SilenN | 6 hours ago

The trick is to rarely switch, or switch at task boundaries. Often the conclusion of routing is actually "this one model is actually at the pareto front for this task, just use it always".

cameronh90 | 4 hours ago

But then it's better to just not have a gateway switch models at all.

Just have the harness able to choose which model its sub-agents use, then tell it how to split up tasks and which models to use when doing so.

[OP] SilenN | 4 hours ago

That is another way to do. Or we can automatically figure out which models the subagents should be using for you. And update them as new models come out and the work your subagents do changes. More than one way to skin a cat.

ashermania | 6 hours ago

Finally an open source tool doing this!

23david | 6 hours ago

Super interesting and congrats on the release. Curious if you initially had this in Python and then rewrote in Rust?

[OP] SilenN | 6 hours ago

Yep! If you look at the commit history that's exactly what happened.

cheema33 | 5 hours ago

I have not tried it yet. Is it similar to LiteLLM? If so, what sets it apart?

kfallah15 | 4 hours ago

Router and model optimization from traffic is the main differentiator

[OP] SilenN | 4 hours ago

Also a hosted marketplace, not just BYOK

ceroxylon | 4 hours ago

>The gateway adds under 1 ms for BYOK requests

Amazing! Really brilliant idea, thank you for sharing this project. There is so much ground to cover in the LLM gateway / routing / reporting world, and this is a great start. The Tinker implementation is my favorite part, fine tuning is much better than a sea of context files.

kfallah15 | 3 hours ago

Thanks! We are going to add continual RL via Tinker soon too

akshay_akula | 4 hours ago

Open source and no markup is the right default for a gateway. The caching question above is the one I would want answered before swapping models though.

[OP] SilenN | 3 hours ago

Ans: we rarely switch, often times it's just a "switch to using this model for your agent"

0xbadcafebee | 3 hours ago

You started it a week ago? I look forward to checking back in 3 weeks when you've exited for $1B

[OP] SilenN | 3 hours ago

See you soon

swthbht | 2 hours ago

Very cool. Does your gateway decide effort levels as well? Or just models?

[OP] SilenN | an hour ago

Yep! One interesting example is often Opus 5 on low reasoning ~= Opus 5 on high reasoning.

sangwook | an hour ago

What online signal recalibrates simulated rankings against actual task success? Also do you have a plan to support semantic caching at the router level?

kfallah15 | an hour ago

For the online signal, we use a LLM judge with a rubric calibrated offline by the user via TUI. UX of the calibration is a major focus area. Semantic caching is interesting, open to supporting it but not currently planned.

forgetme2020 | an hour ago

what's the business model here. How does experiential labs make money

kakugawa | an hour ago

They make money on enterprise plans: https://www.experientiallabs.ai/pricing#enterprise

Look at the Intelligence features in the Enterprise plan:

* Per-prompt model optimization

* Caching

* A model you own, trained on your traffic

kfallah15 | an hour ago

yep, it will be through enterprise licenses and our own hosted platform built on the repo