Error - insufficient_quota, Usage is ok and I am a Plus member

[_j]

Also note that your code won’t work.

gpt-3.5-turbo requires the chat completions endpoint, and messages instead of prompt. Its response is parsed differently.

Here’s a forum example of getting a response from the chat model after doing pip install --upgrade openai for use of the OpenAI python library and also placing your API key as an environment variable OPENAI_API_KEY

Is it me or everyone else? GPT api doesn't work any more

That’s great to hear! The code snippet above, mind you, is for gpt-3.5-turbo-instruct, a special “completion” model that operates a bit differently than the “chat” you may be expecting. Here’s getting a response from the chat gpt-3.5-turbo AI with the latest Python openai library: from openai import OpenAI client = OpenAI() system = [{"role": "system", "content": "You are HappyBot."}] chat_history = [] # past user and assistant turns for AI memory user = [{"role": "user", "content": "Are you …