Locked out of API with rate limit error, I am no where close to hitting rate limit

API
1

Hi,
I am running the following code with the API, which is taken directly from the documentation:
import openai

openai.api_key = 'sk-'
response = openai.ChatCompletion.create(
    model="gpt-3.5-turbo",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Who won the world series in 2020?"},
        {"role": "assistant", "content": "The Los Angeles Dodgers won the World Series in 2020."},
        {"role": "user", "content": "Where was it played?"}
    ]
)

I get the following erorr when running:

  File "/home/azureuser/test.py", line 3, in <module>
    response = openai.ChatCompletion.create(
               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/azureuser/miniconda3/lib/python3.11/site-packages/openai/api_resources/chat_completion.py", line 25, in create
    return super().create(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/azureuser/miniconda3/lib/python3.11/site-packages/openai/api_resources/abstract/engine_api_resource.py", line 153, in create
    response, _, api_key = requestor.request(
                           ^^^^^^^^^^^^^^^^^^
  File "/home/azureuser/miniconda3/lib/python3.11/site-packages/openai/api_requestor.py", line 298, in request
    resp, got_stream = self._interpret_response(result, stream)
                       ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/azureuser/miniconda3/lib/python3.11/site-packages/openai/api_requestor.py", line 700, in _interpret_response
    self._interpret_response_line(
  File "/home/azureuser/miniconda3/lib/python3.11/site-packages/openai/api_requestor.py", line 763, in _interpret_response_line
    raise self.handle_error_response(
openai.error.RateLimitError: You exceeded your current quota, please check your plan and billing details.

I know my account is not hitting any limits:

image
image1730×1322 152 KB

I am using exactly the same API key as that used in the September API calls. I also tried generating a new key and using that, but I get the same error.

I do have a valid credit card submitted to the payments methods of thebilling section.

What could be causing this?

2

Hey champ

And welcome to the community forum!

It’s the rate limit you’re hitting, not the usage limit :laughing:

You can find more information on the rate limits here:

3

You used $20. Did you only pay $20 for credits?

“please check your plan and billing details” should be the hint.

4

Hi, sorry the screenshot cuts off above, but my balance does have credits remaining:

image
image1454×644 48.2 KB

5

Hi @pa1994

What are your rate limits for gpt-3.5-turbo?

Also, are your org’s API key(s) being used somewhere/by someone else? Do you have other members in your org that could be making API calls?

6

You might double-check if you’ve forgotten usage limits you set yourself - it’s not mentioned anywhere in this topic.

Hard limit stops monthly usage at what you set it for.