but u wouldnt get caching savings
Show HN: Echo – Fable-level results at 1/3 the cost using open-weight models
71–80 of 254 posts
Re: Show HN: Echo – Fable-level results at 1/3 the cost using open-weight models
#72but u wouldnt get caching savings
You definitely still would, but you need to pay the full input cost twice, so the equation really depends on how much first message vs repeat message matter.
Re: Show HN: Echo – Fable-level results at 1/3 the cost using open-weight models
#73Intuitively, your savings depend heavily on how hard the tasks are in the first place. If you have a base rate where 99% of your tasks can be routed to a cheap model, yeah, you can save a ton by not using Fable for that. So “1/3 the cost” really depends.
Sometimes expensive models are cheaper on easier tasks because they use fewer tokens, too.
Re: Show HN: Echo – Fable-level results at 1/3 the cost using open-weight models
#74such a scam, there is only one fable-like model, that somewhat behind, it cost half, not 3x. so from here you can stop reading.
They're obviously not claiming this is a new model that is fable-like at 1/3. It's a router that saves money by only using Fable when necessary. I don't think you should be calling someone's post a "scam" without doing a minimum of research. (I'm not associated with the company, but very interested in this.)
Re: Show HN: Echo – Fable-level results at 1/3 the cost using open-weight models
#75That’s basically the same idea IBM advertises with Bob?
This looks different, it's not a main agent delegating to subagents, it's a router.
Re: Show HN: Echo – Fable-level results at 1/3 the cost using open-weight models
#76Re: Show HN: Echo – Fable-level results at 1/3 the cost using open-weight models
#77Intuitively, your savings depend heavily on how hard the tasks are in the first place. If you have a base rate where 99% of your tasks can be routed to a cheap model, yeah, you can save a ton by not using Fable for that. So “1/3 the cost” really depends.
Sometimes expensive models are cheaper on easier tasks because they use fewer tokens, too.
Yeah apparently Opus and Sonnet are like that.
Re: Show HN: Echo – Fable-level results at 1/3 the cost using open-weight models
#78enjoying how people are re-discovering ensemble methods.
Re: Show HN: Echo – Fable-level results at 1/3 the cost using open-weight models
#79No benchmarks, no info on which models are used, ai generated video, just a signup page with nothing else. Anyhow, this kinda reminds me of that quote about architecture: "We replaced our monolith with micro services so that every outage could be more like a murder mystery."
The evaluator is public here: https://echo.tracerml.ai/eval/ It currently exposes 907 stored rows across seven benchmark families, with prompts, outputs, grades, and cost records. More benchmarks are coming soon. Echo does not disclose its per-request routing decision because that policy is the product. We can, however, publish some of the eligible open-weight model pool, version dates, aggregate allocation mix, and…
Isn't the relevant benchmark RouterBench? https://arxiv.org/html/2403.12031v2#S7
Re: Show HN: Echo – Fable-level results at 1/3 the cost using open-weight models
#80> Fable-level results at 1/3 the cost
I am guessing this is not targeting those of us on the heavily subsidized $200/mo plans. Sure, these plans may be temporary, but none of us really know how temporary they are. Until then, 1/3rd of the published API pricing is not very appealing.