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
SilenN 7 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.
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.
purplecats 7 hours ago [-]
and caching is related to performance too ofc
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.
SilenN 4 hours ago [-]
Ans: we rarely switch, often times it's just a "switch to using this model for your agent"
sangwook 1 hours 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 54 minutes 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.
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 4 hours ago [-]
Thanks! We are going to add continual RL via Tinker soon too
swthbht 2 hours ago [-]
Very cool. Does your gateway decide effort levels as well? Or just models?
SilenN 2 hours ago [-]
Yep! One interesting example is often Opus 5 on low reasoning ~= Opus 5 on high reasoning.
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
SilenN 3 hours ago [-]
See you soon
forgetme2020 1 hours ago [-]
what's the business model here. How does experiential labs make money
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.
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.
Look at the Intelligence features in the Enterprise plan:
* Per-prompt model optimization
* Caching
* A model you own, trained on your traffic