I've been using openrouter.ai to use "all llm's". No subscription, and can be tied to your editor of choice
[1] Source: https://kanoppi.co/search-engines-vs-ai-energy-consumption-c...
If ChatGPT handles 1 billion queries a day, that's like the energy cost of 10 billion Google searches every single day.
Someone has to pay the electricity bill. We all know it's not free like you claim.
seconding openrouter and fal, having to muck around with idiosyncrasies of each vendor just to try their "bestest model" and find out it does not satisfy your requirements is a chore.
Also, Andy's blog post doesn't mention infrastructure-scale impacts. Even small actions add up, and as AI scales exponentially, so does the demand on energy and water. That part gets left out.
I'll stick with the research papers published by AI researchers [1] and investigative journalists [2], but thanks for sharing your link, it gives me a good idea of what lobbyists in Washington aren't saying.
[1] https://eng.ox.ac.uk/case-studies/the-true-cost-of-water-guz...
[2] https://www.bloomberg.com/graphics/2025-ai-impacts-data-cent...
You sent over two links about the environmental impact of data centres. There is no denial that these are burdensome on the environment; the question is to what degree AI and its applications contribute to that effect. If you wanted to argue in good faith you'd be advocating for everyone to stop watching Netflix, because video streaming generates a far greater demand than AI currently does, but I don't see you doing this.