I have a Tier 1 OpenAI account with access to GPT-4. When I try using the API through a Python script, I get the following error:
openai.RateLimitError: Error code: 429 - {
‘error’: {
‘message’: ‘You exceeded your current quota, please check your plan and billing details. For more information on this error, read the docs: https://platform.openai.com/docs/guides/error-codes/api-errors.’,
‘type’: ‘insufficient_quota’,
‘param’: None,
‘code’: ‘insufficient_quota’
}
}
However, when I use the OpenAI Playground, the models (including GPT-4.1) work just fine.
Here’s the code snippet I’m running:
Have you tried printing the API key the code obtains, to ensure you have set the key you think you are using?
Here’s a better version of finding out the credentials that are used - which are automatic and don’t need you to specify the default environment variable key.
import openai
def get_org_model(client, model="gpt-4o-mini"):
try:
return client.models.retrieve(model).id # Makes test API call
except Exception as your_error:
return your_error
def env_info():
client=openai.Client() # automatically imports from env variables
# client=openai.Client(api_key="sk-proj-lengthy-hardcoded-bad-key-test")
print(f"API test: {get_org_model(client)}")
org = client.organization or "(no organization set)"
proj = client.project or "(no project set)"
api_key = client.api_key or "(no API key set)"
if len(api_key) > 20:
elided_key = f"{api_key[:14]}...{api_key[-6:]}"
else:
elided_key = "(invalid short API key)"
print(f"Used `openai` module version {openai.__version__}")
print(f"API Key: {elided_key}\nOrganization: {org}\nProject: {proj}")
if __name__ == "__main__":
env_info()
It may be necessary with a recent initial payment or tier upgrade to generate a new project API key.
For this test case, to ensure success, use the default or a new project, and with no restrictions set up on either the project or the key itself.