Error code 429, how to solve this problem even if I have pay plan acount

Hey,
I have an openAI Plus account.
I am trying to develop an application that will use the openAi API, I set the API-KEY as required, and when I try to send a request to my application I encounter error code 429 with the following details:

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’

what should I do ?

I am facing same issue too. I recharged with 5$ in january, then only used .02$. Now when I tried again, it returned me the same error as OP. I also tried creating new api key as well as project api key.

Welcome to the Forum!

It sounds like you are referring to your ChatGPT Plus subscriptions. Note that ChatGPT and the API are different products and are treated differently from a billing perspective. In order to start using the API you need to load a minimum of $5 to your developer account. You can do so under Settings > Organization > Billing on the developer platform.

1 Like

Welcome to the Forum!

Can you please confirm that your $5 are still shown as valid on the usage dashboard? Did you pay in the $5 with your own money or are you referring to the free credits that used to be granted by OpenAI? If the latter, then these have likely expired after six months.

Hi. I can still see remaining 4.98$ in my dashboard. I remember recharging with 5$ in around early this year, and used 0.02$ from it.

Should still be there then unless it was the free $5 which likely expired.

I am pretty sure I recharged with new top-up, but still how do I verify? I can see on my dashboard the remaining $4.98

For your reference

That’s not 100% sure … :wink:

https://platform.openai.com/organization/usage

Are you looking there? It should differentiate between credits you got free and ones you bought…

Updated screenshot. Please have a look.

Thanks.

What calls are you trying to make?

Are you aware of the rate limits?

https://platform.openai.com/docs/guides/rate-limits

Might try minting a new API key too… Let us know…

Thanks for replying, I am trying use chatcompletition.

def chat_gpt(prompt):
    time.sleep(10)
    response = client.chat.completions.create(
        model="gpt-3.5-turbo",
        messages=[{"role": "user", "content": prompt}]
    )
    return response.choices[0].message.content.strip()
  1. I have tried creating new key. It was the same for me.
  2. Yes, I am adding enough sleep to avoid rate limit.

Hrm. Yeah, if you’re sure you have credits, you’ll need to reach out to help.openai.com