Yeah, OpenAI models now are really at the frontier of high performing, low-cost models: https://artificialanalysis.ai/#intelligence-comparison-tabs

I agree with the author on a lot points about the joys of using low cost models. My work would pay much more, but I prefer to use cheap models usually. Assuming cost correlates somewhat closely with energy used, I feel good about spending as little as possible, and the cheap models are so capable.