Closed babusri closed 6 months ago
Could you run (setq gptel--debug t)
, then try using ChatGPT, and paste the contents of the buffer that opens up?
Important: This buffer will have your API key near the top, please remove it before pasting it.
I have given the error message below. Note: I have never used the api key before. I just saved it in password manager. I always used ChatGPT 3.5 from the browser. This may not be relevant but I signed up for ChatGPT 4.0 a week back. I have only made a few requests via the browser for ChatGPT 3.5 or 4 and so this error is puzzling. In any case, this looks like a ChatGPT issue and not related to your nice package.
HTTP/1.1 429 Too Many Requests Date: Sat, 30 Dec 2023 08:03:02 GMT Content-Type: application/json; charset=utf-8 Content-Length: 337 Connection: keep-alive vary: Origin x-request-id: b3b017312c49748de541a62af97c08bb strict-transport-security: max-age=15724800; includeSubDomains CF-Cache-Status: DYNAMIC Set-Cookie:
{ "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": null, "code": "insufficient_quota" } }
Looks like an OpenAi billing issue. They changed the system a couple of times -- I think you have to preload your account with credit to access the API now. This is independent of the ChatGPT plus service, or whatever it's called.
Thanks for your prompt response. https://platform.openai.com/usage says $0/$18 limit
So, not sure why I am getting this error.
You can close this as a non-issue.
There seems to be some discussion about this error -- if you generated your API key before you paid them, it's possible you may need to generate a new one.
I'll close this issue as this is unrelated to gptel, but please update if you find a solution, as it can help others.
Karthik,
Looks like the API credits expire in 3 months if not used. I will purchase some credits.
The https://platform.openai.com/usage shows
[image: image.png]
Because the url says usage , I thought that 0% was the amount used. But as you can see, almost 0% was used (green) but the rest (pink) says Expired.
Babu
On Sat, Dec 30, 2023 at 2:42 PM karthink @.***> wrote:
There seems to be some discussion https://stackoverflow.com/questions/75898276/openai-chatgpt-gpt-3-5-api-error-429-you-exceeded-your-current-quota-please about this error -- if you generated your API key before you paid them, it's possible you may need to generate a new one.
I'll close this issue as this is unrelated to gptel, but please update if you find a solution, as it can help others.
— Reply to this email directly, view it on GitHub https://github.com/karthink/gptel/issues/162#issuecomment-1872489169, or unsubscribe https://github.com/notifications/unsubscribe-auth/AACOXAEWDSYUJDXPNBZHGP3YL7LGXAVCNFSM6AAAAABBHJ5XF6VHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMYTQNZSGQ4DSMJWHE . You are receiving this because you authored the thread.Message ID: @.***>
I tried gptel today and I get the following error: Querying ChatGPT... ChatGPT error (HTTP/1.1 429 Too Many Requests): Could not parse HTTP response.
Tried it couple of times. Then I tried chatgpt in the browser and it works fine.
I had not used chatgpt at all in the last day and so I don't think there is an issue of exceeding the rate of messages.
Windows 11: GNU Emacs 29.1 (build 2, x86_64-w64-mingw32) of 2023-07-31