I assume you're talking about ChatGPT and not GPT-4? You can craft your own prompt when calling GPT4 over API. Don't blame you though, the OP is also not clear if they are comparing Chat GPT powered by GPT3.5 or 4, or the models themselves.
I can understand why they might make changes to ChatGPT, but it seems weird they would "nerf" the API. What would be the incentive for OpenAI to do that?
The API though? That's mostly used by technical people and has the capability (supposedly) of querying different model versions, including the original GPT4 public release.