3
European, reputable inference providers with a large repertoire? (programming.dev)
submitted 4 days ago* by to c/aicoding@programming.dev
5 comments fedilink hide all child comments
 

Many companies now provide some kind of agentic tooling and expect its use. Some mandate which one, some are open. Most however, use US products and are sending all their data to Anslopic, Microslop, Goolag, ClosedAI, and so on. Not only that, they are expensive af. I've seen bills above 600€ per employee where management didn't even flinch.

There are "inference providers", but every single one on HuggingFace is a US company. There are also the model providers themselves but again, US or Chinese with the exception of Mistral in Europe.

To be able to convince management to use something else, it would have to be cheaper yet "powerful" (DeepSeek fits but is in China), have enough choice (it can't be a single model provider like Mistral, Anslopic, etc.), and be in Europe.

Does such a thing exist?

all 5 comments

sorted by: hot top controversial new old
[–] 5 points 4 days ago (2 children)

https://tokenfactory.nebius.com/ did you see these guys?

  • permalink
  • fedilink
  • source
  • hideshow 4 child comments
    •
  • [–] [S] 1 point 3 days ago

    They are very close to what I'm looking for! Right now the major problems are:

    • servers in the US. not sure why they're doing that. some models are in the EU, some in the US, and one might pick a model hosted in the US by mistake
    • it requires a google or a github account: we can't use our corporate accounts to manage spending - specifically it seems like finance would have to create a github account to login on nebius. very bizarre

    Are you using them by any chance? Do you know if their management interface has controls that allow using normal email addresses or some kind of user management without signing up to some extra service (github, google).

  • permalink
  • fedilink
  • source
  • parent
    • [–] 2 points 4 days ago (1 child)

    How about a cloud provider and then taking a open model to that? Also difficult to find, but it's better chance... Hetzner comes to mind. Then you may self-host ollama and some gateway to monitor token usage.

    Even if it came to API key on a asian or american company, self host makes sense to me to relax on the lock in (e.g. Bifrost) and have some management dashboard. There's a growing ecosystem of self-hosted tools, the lates I saw was experientiallabs.ai that was aimed to save costs.

    (6I'm on a similar track tho I am just a 1-man army with lended over pro plans (no apis) setting up omp.sh to combine and decouple tasks among providers and differentially sized models.)

  • permalink
  • fedilink
  • source
  • hideshow 2 child comments
    •
  • [–] [S] 1 point 3 days ago

    How about a cloud provider and then taking a open model to that?

    That would require somebody managing that and there's no way my company would pay for that. From what I could find on Hetzner, it costs 0.4€/hour just for the instance. The rest will come on top.

    https://www.experientiallabs.ai/ seems like a self-hosted wrapper around other paid services. You'd need to get an Anslopic subscription, a Goolag subscription, and so on.

    I'm looking for an EU company like one of the companies on this list. DeepInfra, fal, basten, and so on. They show you a list of models they have a price, and all you have to do is sign up, whip out the credit card, copy paste the API URL into your harness (pi, opencode, claude code, whatever) and you're a hundreds lighter as a company but with no headache about running the entire thing yourself.

  • permalink
  • fedilink
  • source
  • parent