I don't know if how close Europe is, but I'm sufficiently whelmed by Mistral that I don't need to look elsewhere yet. It's kind-of like having a Toyota Corolla while everybody else is driving around in smart cars but it gets it done. On top of it, there's a loyal community that (maybe because I'm not looking) I don't see with other products. It probably depends on your uses, but if I spent all my time chasing the latest chat models (like Kimi K2 for instance) I wouldn't actually get anything done.

> I don't know if how close Europe is, but I'm sufficiently whelmed by Mistral that I don't need to look elsewhere yet. It's kind-of like having a Toyota Corolla while everybody else is driving around in smart cars but it gets it done.

My problem was that it really doesn't, none of the models out there are that great at agentic coding when you care about maintainability. Sonnet 4.5 sometimes struggles and is only okay with some steering, same for Gemini Pro 2.5, GPT-5 recently seems like it's closer to "just working" with high reasoning, but still is expensive and slow. Cerebras recently started offering GLM-4.6 and it's roughly on par with Sonnet 4 so not great, but 24M tokens per day for 50 USD seems like good value even with 128k context limitation.

I don't think there is a single model that is good enough and dependable enough in my experience out there yet, I'll probably keep jumping around for the next 5-10 years (assuming the models keep improving until we hit diminishing returns so hard that it all evens out, hopefully after they've reached a satisfying baseline usefulness).

Don't get me wrong, all of those models can already provide value, it's just that they're pretty finnicky a lot of the time, some of it inherent due to how LLMs work, but some of it also because they should just be trained better and more. And the tools they're given should be better. And the context should be managed better. And I shouldn't see something as simple as diffs fail to apply repeatedly just because I'm asking for 100% accuracy in the search/replace to avoid them messing up the brackets or whatever else.

Coding isn't the only use case.

Neither is being bleeding edge.

I use Mistral's models, I've built an entire internal-knowledge-pipeline of sort using Mistral's products (which involved anything from OCR, to summarization, to linking stuff across different services like Jira or Teams, etc) and I've been very happy with it.

We did consider alternatives and truth to be told none was as cost-effective, fast and satisfying (and also our company does not trust US AI companies to not do stuff with our data).

My god the cost right? It's so much less than any of the competition that just feeding off of an api key (for coding, yeah) works great.

But as you say the rest of it is good too. I use it for research and to me it does a great job, all for a fraction of the price and the carbon of the U.S. players.

So you're not able to trust inference providers like Google Cloud w/ ZDR etc with your data?

My EU-based clients are unwilling to do so as we see all clouds as black boxes you have no real idea what you getting into.

Most of our hosting is also on European providers, my team's the only one that deploys some services on Azure.

Probably cuz you aren't looking yeah. Anthropic seems to be leading the "loyalty" war in the US.

Yeah and I'll probably end up going that way as work locks down the models we're allowed to use, saving Mistral for personal projects.

You have to try the latest Corolla then. Really smart. Lane and collision assistance, ... Unlike my old Corolla which is total dumb. It even doesn't turn the light off when I leave the car

Hah! I need to update my analogies.

Not anywhere near close.

Europe doesn't have the infrastructure (legal or energy) and US companies offer far better compensation for talent.

But hey, at least we have AI regulation! (sad smile :))