I have expired credits for the regular models. I’m making calls to the codex models which are in private beta so the usage isn’t charged. I’m testing for now, meaning the max requests I make for now are just 2 req/min. I’ll change the model names, and hope things start working again.
Same here, but did you notice that even at 1000 length the output is too small compared to what we were getting before using text-davinci-003, etc you could have had 4-5 paragraphs at length 256 now you barely get 1 with 1000 length and it feels like the output comes out of davinci-002, not text-davinci-003.
I’m getting this same error, using code-davinci-002
Rate limit reached for default-code-davinci-002 in organization org-XXXX on tokens per min. Limit: 40000.000000 / min. Current: 80000.000000 / min. Contact support@openai.com if you continue to have issues.
However email support and no reply, very frustrating…
Added payment card to file, still the same error
I created a new API key, still the same error
Waiting 10 mins… and it started working!! I hope it stays this way.
hi I have the same error But I haven’t done it even once till date… But today when I did chat completion in python with the help of “ChatGpt” API. what should i do