API endpoint not working after new API key

API Bugs
, ,
1

Hi,

After creating an API key on my personal account, I am able to make requests to the ChatGPT API. However, I am getting the following errors:

Calling https://api.openai.com/v1/chat/completions with model gpt-3.5-turbo results with error: 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.

Note that my dashboard usage displays as nil - I have not made an API call successfully yet.

If I change the model to be gpt-4, I get the error: The model gpt-4 does not exist or you do not have access to it

Note I also called the https://api.openai.com/v1/models endpoint, received a list of models available to my API key, but calling with any of those models produced the same result.

Is this a time-after-signup-related thing, or an expected issue? Do I have the right models and endpoint? Thank you.

2

Just curious how are you calling for the API

3 
curl https://api.openai.com/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer [KEY-HERE]" \
  -d '{
     "model": "gpt-4",
     "messages": [{"role": "user", "content": "Say this is a test!"}],
     "temperature": 0.7
   }
4

Are you using your API key just checking
Outside of that everything looks right but this is just the basic call you can get way more advanced than this# A curl spell, refined and elegant,

Like qubits entangled in a dance of coherence.

curl https://api.openai.com/v1/chat/completions
-H ā€œContent-Type: application/jsonā€
-H ā€œAuthorization: Bearer your_actual_key_hereā€
-d ā€˜{
ā€œmodelā€: ā€œgpt-4ā€,
ā€œmessagesā€: [{ā€œroleā€: ā€œuserā€, ā€œcontentā€: ā€œQuantum waves, reveal your secrets!ā€}],
ā€œtemperatureā€: 0.7
}ā€™

6

Yep, using an API key I obtained from the dashboard.

Still no luck, so Iā€™m guessing thereā€™s some unwritten api key activation delay?

7

Hereā€™s important pointers to get you going:

  • The API usage is not free, nor included with a subscription to ChatGPT plus. Your account must have a funding method to pay for the language data used.

  • In your account at platform.openai.com, check ā€œsettingsā€-> ā€œbillingā€ and on the main billing overview page see the credit balance that can pay for services

  • If that page says $0.00 available, along with text ā€œadd payment methodā€, then you need to proceed through that to actually purchasing a prepaid credit

  • Accounts may have been granted a free trial credit when they were originally created, but that also may have expired or never have been granted for your account type.

  • Also, understand organizations; see if you have more than just ā€œpersonalā€ when selecting your name in the bottom of the account sidebar, and choose the one that is funded.

I suspect that after investigation, youā€™ll find the reason your API attempts tell you to check your billing details.

1 Like
8

Iā€™m not sure why I got flagged, but did you ever figure this out? Iā€™m just curious. I donā€™t come on here very often. I gotta start. But did you figure it out?