Given how much time these models can save me, I'd rather optimize for capability and just accept whatever the price is as a cost of doing business. (Within reason I guess—I probably wouldn't go beyond $2-3k per month at this point, unless there was very clear ROI on that spend.)
Also, it's not only about saving time. More powerful AI tools allow me to build things it would otherwise be impossible to build... that's just as important as the time/cost equation.
I mean, you pour money down the drain if you think it's helping, have at it :P
You're not actually getting all the files you add in the context window, you're getting a RAG'd version of it, which is generally much worse if the un-RAG'd code is still within the effective context limit.
1. Claude Code 2. Cursor 3. Cline. 4. Windsurf
I'll stick with Windsurf, especially given their upcoming announcement.