I've just found myself using OpenRouter if we need Google models for a project, it's worth the extra 5% just not to have to deal with the utter disaster that is their product offering.
FWIW I had to bail on the same thing because my results were drastically different. There was something happening with images through open router. Although outside of that I’d absolutely do the same thing, their apis are awful and billing worse. Maybe it makes sense for huge orgs but it’s a nightmare on the smaller scale.
This is the wrong interpretation of the oxcaml project. If you look at the features and work on it, it's primarily performance or parallelism safety features.
The latter going much further than most mainstream languages.
If you're going to depreciate the battery then your return will be substantially greater than 7.3%. You can't use BOTH the capex AND the depreciation as your denominator, choose one.
And even when it does copy other products, it seems to be doing a terrible job of them.
Google's AI offering is a complete nightmare to use. Three different APIs, at least two different subscriptions, documentation that uses them interchangeably.
For Gemini's API it's often much simpler to actually pay OpenRouter the 5% surchargeto BYOK than deal with it all.
I still can't use my Google AI Pro account with gemini-cli..
I had great fun this week with the batch API. A good morning lost trying to work out how to do a not particularly complex batch request via JSONL.
The python library is not well documented, and has some pretty basic issues that need looking at. Terrible, unhelpful errors, and "oh, so this works if I put it in camel-case" sort of stuff.
I find Gemini is their first API that works like that. Not like their pre-Gemini vision, speech recognition, sheets etc.. Those were/are a nightmare to set up indeed.
Idk, I think this is easier to talk about than “codex” by open ai which means either means the cli or the web interface to an agent with its own computer.
For example, Google's inexplicable design decisions around libraries and APIs means it's often worth the 5% premium to just use OpenRouter to access their models. In other cases it's about which models particular agents default to.
Sonnet 4 is extremely good for tool-usage agentic setups though - something I have found other models struggle to do over a long-context.
In your first comment you mentioned you used Mistral because of its permissive license (so guessing you used 7B, right?). Then you compare it to a bunch of cutting edge proprietary models.
Have you tried Mistral's newest and proprietary models? Or even their newest open model?
Interesting. I'd say that Americans tend to overestimate the degree of common identity among Europeans. The polls are clear: for most Europeans, their European identity comes a distant second. The EU in particular is an elitist project and it's only slowly gaining popular legitimacy.
That said, I personally am a very patriotic European.
100% this. We actually use OpenRouter (and pay their surcharge) with Gemini 2.5 Pro just because we can actually control spend via spent limit on keys (A++ feature) and prepaid credit.
I live in a locale that has cheap energy, in fact one that makes solar a pretty bad deal. Depending on the real generation numbers of the panels it would take about 20 years for me to payback that level of generation.
So saying most people have an 80 year payback period just feels wildly off (depending on the assumptions in the calculation I think that implies less than a penny per kWh generated).
