Spaces:
Paused
gpt-4o
Hi.
I have set up LibreChat using Huggingface and this template, as shown in the documentation. I can only get some of the small models to work: gpt-4o-mini and gpt-3-turbo.
I am trying to just call OpenAI api directly.
I have set gpt-4o to the allowed list in OpenAI Project Allow list.
Is there any additional steps I should include to get something like gpt-4o working?
are you on their free tier?
sounds like rate limits on their side
https://platform.openai.com/docs/guides/rate-limits/usage-tiers
Check your limits in your account:
https://platform.openai.com/account/rate-limits
Thank you for your quick answer. I don't think it is a tier thing, I am on usage tier 4 and I have used almost no tokens this month.
Here is the error from the log:
2024-08-28 09:07:54 warn: [OpenAIClient.chatCompletion][stream] API error
2024-08-28 09:07:54 error: [handleAbortError] AI response error; aborting request: 400 invalid model ID
Can it be something about the wrong user requesting the API call?
My OpenAI user is not on the same email as my huggingface user, do you know if this is something OpenAI looks for when they take the request?
"400 invalid model ID"...
what exact model did you use? maybe there's a typo in the model name 🤔
on the demo we're using this list:
OPENAI_MODELS
chatgpt-4o-latest,gpt-4o-2024-08-06,gpt-4o-mini,gpt-4o,gpt-3.5-turbo-0301,gpt-3.5-turbo,gpt-4-turbo,gpt-4-turbo-2024-04-09,gpt-4,gpt-4-0613,gpt-4-vision-preview,gpt-3.5-turbo-0613,gpt-3.5-turbo-16k-0613,gpt-4-0125-preview,gpt-4-turbo-preview,gpt-4-1106-preview,gpt-3.5-turbo-1106,gpt-3.5-turbo-instruct,gpt-3.5-turbo-instruct-0914,gpt-3.5-turbo-16k
everything on it is working afaik