I knew they were burning money with those earlier limits. But thanks we had them a good price until we needed them. Now that GLM, Opencode Go, Crof AI, Synthetic.new, and many many more. They give these opensource source models. I have switched from all big subscriptions and now have moved to many small subscriptions and I am now trying see who gives best accuracy(quants), Speed (tokens/second) and Usage Limits at low price.
Have you tried the plannatator? https://github.com/backnotprop/plannotator
I've been using it for few months now and I like how it let's me annotate the plan as I review and then send feedback or approve.