Fireworks hosts the available models themselves which probably solves the problem consistency problem that OP had to deal with.

It's been a few months since I looked around at this topic, but Fireworks and Openrouter were the two options I (briefly) tried.

Fireworks has high variance amongst models and while some are served correctly; many of them are junk / broken and degraded and it seems like they don’t even know; because even running 1k MMLU Pro questions would flag it very quickly.

Good info, thanks!

About twenty years ago I used tinyurl.com/lvorv to link to a flash animation.

I assume there's some divine intervention going on, but it still works!

It links to https://www.albinoblacksheep.com/flash/mudah

I switched to Cachy in late February this year.

First day was a bit rough, first week was still a little rough, but it's been pretty smooth since then, even when learning how to fix things and trying new software.

I'm using Niri and Noctalia as my desktop setup, and it's been different than my Windows experience, but it feels fun and cool to just use a computer in a new way.

A what

I think he meant fuck.

probably full-featured :)

When I dropped my Claude sub a few months ago I first went to try pi. At first I was a little overwhelmed by having to browse extensions to get the experience I want (coupled with finding new model providers to use).

So I looked elsewhere and found Crush and Hermes. They're both very a e s t h e t i c, which I think can make using them fun, but ultimately if I had a nitpick, I would look back over at pi, and the grass looked greener. (And not to mention, both Hermes and Crush seem to have some drama/baggage.)

I'm back on pi, and happy with just a few packages I've downloaded for it.

I understand that hermes needs to do be able to do "everything" but I can't stand how much crap comes along with it.

It feels like when you do a fresh Windows install and you have to debloat it from all the spyware and candy crush type games.

Pi is the perfect clean slate, I absolutely love it.

what model(s) did you end up using with pi?

I want to move away from claude but don't have the hardware for "good" local llms, and would rather use a ZDR api instead of one of the big apis for privacy reasons.

Sorry for the late reply (relatively new to HN)

After my Claude subscription ended, I tried using Fireworks and OpenRouter to be less vendor-locked and access cheaper models. MiniMax, Kimi, and Qwen were the three I tried the most since they're fairly cheap, but I still burned thorugh credits way too fast. Now I'm using Codex.

I've heard that if you can deal with slower output, local LLMs can run on gaming graphics cards well enough. So they're not great for a live coding assistant, but running some tasks/agents overnight is an option.