Is 4o model going deprecated? is giving me error even in the API playground with some specific inputs with web search

API Bugs
1

I have this specific query that asks fir some links about research in low fertility rates in my country, in python with the Responses API, and it gives me this error, the funny thing is any other query doesn’t fail.

openai.InternalServerError: Error code: 500 - {‘error’: {‘message’: ‘The server had an error processing your request. Sorry about that! You can retry your request, or contact us through our help center at help.openai.com if you keep seeing this error. (Please include the request ID req_abc13e102c67873df254f1a6052b8359 in your email.)’, ‘type’: ‘server_error’, ‘param’: None, ‘code’: None}}

Even in the API playground, it starts to write with no problem and out of the blue it stops and gives an error.

Any thougths?

1 Like
2

The model is not being deprecated in the API, you can see the schedule here for deprecations.

If you haven’t already, it is recommended to open a support ticket, so that they can investigate further, since it seems to be a very specific error.

1 Like
3
  • The API model works well in every query except this one.
  • The error message tells me to contact via the help center and to include a request ID.

Is a logical conclusion:

  • go to the OpenAI developer forum where your fellow users cannot see request IDs;
  • inquire about a possible future shut-off date?

A different path you can go:

  • The alias name “gpt-4o” points to the actual model gpt-4o-2024-08-06
  • Knowing that, you can also try the versioned models “gpt-4o-2024-11-20” or “gpt-4o-2024-05-13” and see if they exhibit the same issue, and even implement a fail-over to these similar models in an application.
4

Hi Team,

Facing the same issue from my end as well.

Please share if any solutions / workarounds are found for this issue.

Thanks in advance !

5

yeah, I get it, maybe it was silly, my question about deprecation is because the system worked flawless by three months or so, and it starts to fail just the day OpenAI launches gpt-5 and gets gpt-4o out of sight, I wanted to know if other users had the same problem, now I’m on the right track, thanks for your response anyway. I changed the model to o3 (more expensive but does the job better) and everything works ok.

2 Likes
6

I am also getting the same error:
with status code 500 Response Body:{ “error”: { “message”: “The server had an error processing your request. Sorry about that! You can retry your request, or contact us through our help center at help.openai.com if you keep seeing this error. (Please include the request ID [REDACTED] in your email.)”, “type”: “server_error”, “param”: null, “code”: null } }

I am using the responses api /api.openai.com/v1/responses with web search tool enabled. How did you resolve this issue?