I asked GPT4 to refactor a simple, working python script for my smart lights... and it completely butchered the code and apologized mid-generation.
No amount of pleading or correction would get it to function as it did just a week or two ago.
It is so over.
It does not add up that much unless you're tokenizing a metric ton of content. It's a few extra bucks and you can set a rate limit. I have rarely hit a 5 dollar mark with consistent writing. Limit it to a fiver and see how it goes. As for the settings, it is really model specific. There are a ton of guides out there, though for effective instructing. I believe Wolfram Alpha has a few. Their formatting is nice: https://medium.com/machine-minds/chatgpt-python-machine-learning-prompts-abefc544412c Playground pricing is what they use for commercial API use. It has to be affordable.