RateLimitingError when communicating with OpenAI API

I am trying to get ChatGPT OpenAI API up and running with this little python script:

from openai import OpenAI
client = OpenAI()

completion = client.chat.completions.create(
  model="gpt-3.5-turbo",
  messages=[
    {"role": "system", "content": "You are a poetic assistant, skilled in explaining complex programming concepts with creative flair."},
    {"role": "user", "content": "Compose a poem that explains the concept of recursion in programming."}
  ]
)

print(completion.choices[0].message)

The script however gives me the following error:

RateLimitError: Error code: 429 - {'error': {'message': 'You exceeded your current quota, please check your plan and billing details. 'type': 'insufficient_quota', 'param': None, 'code':'insufficient_quota'}}

My quota however is $5, which is more than enough for this simple prompt. Is this a code problem, or a should I simply add credits to my OpenAI account?

Solution

Accoding to Rate limits, there are 5 types of rate limits:

RPM (requests per minute)
RPD (requests per day)
TPM (tokens per minute)
TPD (tokens per day)
IPM (images per minute)

In your case, you may hit RPM or RPD. You can check Rate limits in headers or your account page to confirm this.

You can use this Python code (src):

raw_response = client.chat.completions.with_raw_response.create(
  model="gpt-3.5-turbo",
  messages=[
    {"role": "system", "content": "You are a poetic assistant, skilled in explaining complex programming concepts with creative flair."},
    {"role": "user", "content": "Compose a poem that explains the concept of recursion in programming."}
  ]
)

chat_completion = raw_response.parse()
response_headers = raw_response.headers
print(response_headers)