jonas_scholz

They wont, they are very public about never subsidising any products. I doubt they change that after 29 years now.

also slightly disrespectful to think that this was a single prompt, but ok:D

yeah, but why would LLM inference now triple the price of the other products? Or am I misunderstanding what you're saying?

"no reason" like hardware prices going through the roof?

Why do you think this would be madness? It seems like, at least in the EU, there is barely competition for the big open-weight models?

fine, i agree that this doesnt sound like me. But the content is correct and not a hallucination!

I mostly use Hetzner baremetal servers and not cloud, but the support there is in my experience very competent, but also VERY german and direct. I can imagine if youre neither german or super technical that this can be intimidating or considered unfriendly

what is the hallucination here? it is fast, free and fun to try. And I genuinely think that the hardware decision (if they get bigger gpus) decides if this will be a banger product or not?

yea, but no prompt caching right? This makes it unusable for my usecase at least, the cost would be insane

I really hope they dont stop at the small models though! The bigger ones that dont fit on a single GPU are more interesting I think

agree. I have a usecase for a bigger open-weight model hosted by an EU company and the selection isnt really great, hard to make the regulatory gods (and the devs) happy at the same time right now

My writing wasnt clear here I think, without the option it defaults to reasoning enabled. With "without it" I meant without enable_thinking=False!

Interesting, didn’t know about them! Weird model selection though, no glm or deepseek?

we love and support netbird at sliplane <3 https://docs.sliplane.io/private-networking/netbird

Thank you for mentioning Sliplane! Really cool project.

afaik no firecracker support with virt-manager. There's firectl to make it a bit easier but the tooling is generally still pretty rough

Yes, we're on Hetzner! The availability is actually insane. Thank you :)

Thats cool! Id like to check that out if you want to share! jonas@sliplane.io or you can find me on Twitter/X (JonasScholz19) :)

BTW, this is also kinda how Sliplane started. We both are coming from a freelancing background and had built similar things for clients before

Yes! And its not like we don't care about that or don't want to follow all the rules, it's just really hard. Especially when you're not funded and a tiny team.

We are working on that! One of our most requested features

docker compose is one of our most requested features, we're working on that!

Yeah fair point, its a bit confusing. We really wanted to have the cheapest price under 10, and just kept the other prices at a point that make this business sustainable for us. Pricing is hard :D

Good point, will change that asap. Thanks!

Thanks! No, I dont think this is a direction we want to go in. For now we are focused on simpler usecases :)

We are trying to be more focused on just Docker and our pricing model is different. At sliplane you pay a flat fee for your resources and never more, at railway you pay exactly for the resources you use. If you have high utilization sliplane should be cheaper, but that depends on your usecase!

Because your time is either worth more doing other things or you don't know how to do it :)

Copying from another reply: I love coolify and I think they are doing amazing work! In the end it mostly comes down to convenience I'd say. With coolify you are still responsible for more things like migrating away if your host decides to die. I think a lot of people also chose us because we have pretty good support

Re footgun: Yes, just dont want to start with fear mongering marketing :D

I love coolify and I think they are doing amazing work! In the end it mostly comes down to convenience I'd say. With coolify you are still responsible for more things like migrating away if your host decides to die. I think a lot of people also chose us because we have pretty good support

Thank you! Yea we also heavily rely on the Go Docker SDK, also had a fair share of weird Docker edge cases to solve. I've spent more time in the Docker source code to debug stuff than I'd like to admit.