#Error code: 500: The model produced invalid content.

1 messages · Page 1 of 1 (latest)

soft sable
#

Has anybody else been getting this 500 error through the API? I've been trying to use the new gpt-4o-mini model for my existing project (which uses tool calling with a combination of gpt-4o and gpt-3.5-turbo models), but I'm getting the following error from time to time:

Error code: 500 - {'error': {'message': 'The model produced invalid content. Consider modifying your prompt if you are seeing this error persistently.', 'type': 'model_error', 'param': None, 'code': None}}

Not really sure what the reason might be. The same prompt + tool call and settings work with gpt-4o and gpt-3.5-turbo. When I switch the model name to the new one, it sometimes works but other times throws this error. It would be great if a dev at OpenAI could chime in and clarify if it is an issue on my end or it's on OpenAI's end.

last meteorBOT
#

@soft sable

Please follow the posting guidelines.

For better assistance from the community or an OpenAI team member, please follow the posting guidelines by clicking the button below.

soft sable
#

The problem is, I don't have this issue with other models (even gpt-3.5-turbo). I was hoping I could migrate to the new model without any extra model-specific tuning. I remember I got 500 errors when gpt-4o came out at the beginning (not the same error message as this one). It just went away with time. Maybe this is more of the same