Total and utter frustration

API Feedback
1

Dear OpenAI Support,

I am a paying client, but I was unable to utilise the help option because the link is not active. I have return to start doing some development after some months and having no end of trouble where it was not an issue in the past.

I am encountering a persistent rate limit error with my API key, despite having no visible activity in my usage dashboard. Here are the details:

  1. Verified the API key is correct and valid.
  2. Created a new API key and updated the script.
  3. Ran a minimal test script (see below) to verify functionality.
  4. Checked billing details and subscription plan.
  5. Ensured stable network connection without proxies or firewalls.
  6. Tried running the script in a different environment.
  • Script Used:
import openai

OPENAI_API_KEY = "your_new_openai_api_key"

openai.api_key = OPENAI_API_KEY

def test_openai_api():
    try:
        response = openai.ChatCompletion.create(
            model="gpt-3.5-turbo",
            messages=[
                {"role": "system", "content": "You are a helpful assistant."},
                {"role": "user", "content": "Hello, can you confirm that the API is working?"}
            ]
        )
        print("API response:", response.choices[0].message['content'].strip())
    except openai.error.RateLimitError as e:
        print(f"Rate limit error: {e}\nPlease check your plan and billing details: https://platform.openai.com/account/billing")
    except openai.error.AuthenticationError as e:
        print(f"Authentication error: {e}\nPlease check your API key.")
    except openai.error.APIConnectionError as e:
        print(f"API connection error: {e}\nPlease check your network connection.")
    except openai.error.OpenAIError as e:
        print(f"An error occurred: {e}")

if __name__ == "__main__":
    test_openai_api()

Despite these efforts, the issue persists, and no usage is reflected in the dashboard. Your assistance in resolving this matter would be greatly appreciated.

Best regards, Marc Dimmick
2

Hi there!

When you refer to being a paying customer, does that mean you have a ChatGPT subscription or you have available credits in your developer account?

In order to use the API a minimum balance of USD 5 under your developer account is required. As ChatGPT is a separate product, a Plus subscription does not count towards the use of the API.

I hope that helps for clarification.

3

If you are in pay as you go billing method before, you need to change to prepaid. OpenAI changed the billing method to prepaid for everybody since March this year.

1 Like