_j
18
After purging keys, I would submit the same inputs to a local python API example for a while, and see if they get you the same false GPT-4. That would indicate some database corruption on the OpenAI side.
See if you can work around with creating a second account allowed on your phone number. Inviting it to your organization as reader. Setting the default API key billing on that to your organization, and making only a new key there. Submitting that account’s keys to your local simulator, then to API product, separated by the 10 minute intervals to see where the fault lies or where you’ve been compromised.
deved
19
I manually, select between the two. I tested after restarting the server. This only started happening yesterday mid-day. I have been using the code I wrote for the last 2+ months with no issues.
Around 10AM yesterday is when things started going crazy.
Verified logs, verified sen/rev packets all look normal but OpenAI is recording the API usage completely different than what is happening.
And what happens if you globally set the maximum tokens to 21? Not doubting you. Just curious and would like to see what’s going on.
deved
21
Check this out. Brand new key. Nobody has this key. I only did two prompts. I just created it and its still going off like I am using it… lol The node server is shut down…
1 Like
What happens if you simply leave it alone?
deved
23
It stops. I am try another complete rebuild… see what happens.
deved
24
Cannot test the results until the balance is settled… will update when I can.
Encountring the same issue excessive API requests and balance consumed in 1h !
Revoke your key and try to see where it may have been leaked.
What kind of application do you have?
cation
28
Unfortunately, I have the same issue. The usage just went up like crazy. All from gpt4 API requests.
cation
29
I have the api key stored in Firebase only and my app is using gpt-3-turbo not gpt4. I just found out about when I receive the email from openai telling that my soft limit has been reached which I set for $80.
I went to check the usage is all gpt4 requests. And the in the API settings page the last used status for the key ( I only have one) is still at 3 Oct and all the gpt4 api requests are happening during the last 6 days up to now.
cation
31
All the gpt4 requests:
Every hour is like that, and is like this for the past 6 days.
cation
32
I revoked the API key twice already and gpt4 api requests still go up like crazy. So after the email I went to revoke the key and an hour later, I see the requests went up again, then I revoked again and generated a new one it still happening.
cation
34
Thanks for helping. The original key was only placed in Firebase nowhere else.
cation
35
OpenAI support is still not responding to my support chat.
@cation I am also experiencing a very similar situation like what you described in this thread. what was the solution for you then? did Openai resolve it for you?
cation
37
They have not resolved the issue but they refunded the money.
1 Like