When I use the free version of the open ai api, as soon as i make my first request i get a rate limit error. I know that the free version of the api allows 3 requests per minute but i cant even get one through. It clearly says rate limit error. Once i get this error i wait for ten fifteen minutes before trying again but same results, sometimes i get a connection reset error but have never been able to make a single successful call using my own api_key. Importing open ai library etc. is all successul, i am using Python 3.8 on Windows (anaconda environment).
One possibility, which I have experienced myself, is that you ask GPT to do too much with a free account. For example, certain finetuning tasks are not possible with a free account and will lead to a rate limit error.
There may be other causes (besides from the possibility that your account was hacked and used) but I would not know what these could be (I do not work at openai).
I also same across this discussion. Maybe there’s a solution for you there.
I have the same issue. Just getting setup and submitted my first request and I get the Rate Limit Error
Here is another take. There may just be too many users at a particular point in time, or the model may be (temporarily) down.
Not sure if you are attempting to run in your own notebook? In which case, you will need to get your own key from the openai portal under user->API keys.
- You can then check the billing overview page to determine if you have any $ left on your free trial. - If not, you will need to sign up for a paid account with a credit card
- then return to your notebook and replace the key assignment line with
openai.api_key = ‘’ or add to your .env file
You may have to wait a minute or so before you rerun but it should work then. Just did for me. Now, you’ll have to watch the usage and set any limits.
Hope that helps!