Rate limit reached error

[peme969]

Known Issues I have used other models before but I got a Chinese response when translated said that the system quota was reached in your area. But for this gpt-4o model it returns a ratelimit reached error. Possibly due to bug when retrying providers?

Bug description I simply used this code to use the model:

    person = "bot personality here"
    message = input("enter chat message")
    client = Client()
    response = client.chat.completions.create(
        model="gpt-4o",
        messages=[{"role": "system", "content": person}, {"role": "user", "content": message}]
    )
    return response.choices[0].message.content

Screenshots

Environment

• python3.12
• Texas, USA

[github-actions[bot]]

Bumping this issue because it has been open for 7 days with no activity. Closing automatically in 7 days unless it becomes active again.

[againh3x]

i had the same issue with the Chinese response when using the gpt3.5-turbo model. I thought this was because I set my location to china a month prior by accident.

[peme969]

i had the same issue with the Chinese response when using the gpt3.5-turbo model. I thought this was because I set my location to china a month prior by accident.

thats because the system quota was reached. i had that error only with the gpt-3.5/gpt-3.5-turbo model. i had to translate it and it says that the system quota was reached in my area

[againh3x]

i had the same issue with the Chinese response when using the gpt3.5-turbo model. I thought this was because I set my location to china a month prior by accident.

thats because the system quota was reached. i had that error only with the gpt-3.5/gpt-3.5-turbo model. i had to translate it and it says that the system quota was reached in my area

We have the same problem. I only get this error with gpt-3.5-turbo, and it assumes my location is in China when it is in the United States. When I use another model like gpt-4o, it gives me a CORS error which is weird because I have the correct header required. Someties when I run 3.5-turbo I don't get the Chinese response error which is also weird. its sort of random.

[peme969]

it doesnt assume your location is in china. its because the API's system that xtekky hacked is in china. also for the gpt-4o model i think it works but i tried it like a few weeks ago so i dont know what happen currently. its not random. i feel like when we hit the limit usage it instantly returns that chinese response. i dont know the limits so it may seem random

On Tue, Jun 4, 2024 at 3:06 PM againh3x @.***> wrote:

i had the same issue with the Chinese response when using the gpt3.5-turbo model. I thought this was because I set my location to china a month prior by accident.

thats because the system quota was reached. i had that error only with the gpt-3.5/gpt-3.5-turbo model. i had to translate it and it says that the system quota was reached in my area

We have the same problem. I only get this error with gpt-3.5-turbo, and it assumes my location is in China when it is in the United States. When I use another model like gpt-4o, it gives me a CORS error which is weird because I have the correct header required. Someties when I run 3.5-turbo I don't get the Chinese response error which is also weird. its sort of random.

— Reply to this email directly, view it on GitHub https://github.com/xtekky/gpt4free/issues/1996#issuecomment-2148328937, or unsubscribe https://github.com/notifications/unsubscribe-auth/BAN47WSDROKD3F4NRJ472HLZFYM3LAVCNFSM6AAAAABICX5DECVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZDCNBYGMZDQOJTG4 . You are receiving this because you authored the thread.Message ID: @.***>

[github-actions[bot]]

Bumping this issue because it has been open for 7 days with no activity. Closing automatically in 7 days unless it becomes active again.