Encountering Error 429 (Insufficient Quota / RateLimitError) when running OpenAI GPT-4o in the Agentic AI lab.

Course Q&A Agentic AI
,
1

Hi everyone,

I am currently working through the Agentic AI course and I am running into a RateLimitError while trying to execute a chat completion with tools using the aisuite client.

Here is the code block I am trying to run:

Python

response = client.chat.completions.create(
    model="openai:gpt-4o",
    messages=messages,
    tools=[get_current_time],
    max_turns=5
)

# See the LLM response
print(response.choices[0].message.content)

When I run this, I receive the following traceback, pointing specifically to a quota issue:

Python

LLMError: An error occurred: 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'}}

Questions:

  1. Is the provided lab environment’s API key out of credits, or do I need to refresh/restart my workspace to get a fresh key?

  2. If this is a BYOK (Bring Your Own Key) setup, is there a specific place I should be inserting my personal OpenAI API key that has active billing?

Any guidance on how to bypass this and continue with the lab would be greatly appreciated!

2

staff is looking into this issue, kindly wait for their response.

regards
Dr. Deepti