First time here? Check out the FAQ!
1

Wing 10.0.5.1: openai.BadRequestError: Error code: 400 - {'error': {'message': "The requested model 'gpt-4-turbo' does not exist."

In 10.0.5.1, with the AI Provider 'Model' field set to 'gpt-4o', the following appears in the Console when trying to do anything AI-related; e.g. start an AI chat; is there a workaround or a planned bug fix for this?

  File "C:\Program Files\Wing Pro 10\bin\__os__\win32\runtime-pip-openai-py3.11\lib\site-packages\openai\resources\beta\assistants\assistants.py", line 95, in create
    return self._post(
           ^^^^^^^^^^^
  File "C:\Program Files\Wing Pro 10\bin\__os__\win32\runtime-pip-openai-py3.11\lib\site-packages\openai\_base_client.py", line 1088, in post
    return cast(ResponseT, self.request(cast_to, opts, stream=stream, stream_cls=stream_cls))
                           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Program Files\Wing Pro 10\bin\__os__\win32\runtime-pip-openai-py3.11\lib\site-packages\openai\_base_client.py", line 853, in request
    return self._request(
           ^^^^^^^^^^^^^^
  File "C:\Program Files\Wing Pro 10\bin\__os__\win32\runtime-pip-openai-py3.11\lib\site-packages\openai\_base_client.py", line 930, in _request
    raise self._make_status_error_from_response(err.response) from None
openai.BadRequestError: Error code: 400 - {'error': {'message': "The requested model 'gpt-4-turbo' does not exist.", 'type': 'invalid_request_error', 'param': 'model', 'code': 'model_not_found'}}
Chad's avatar
11
Chad
asked 2024-08-26 20:17:30 -0600
Wingware Support's avatar
4.2k
Wingware Support
updated 2024-10-09 07:32:34 -0600
edit flag offensive 0 remove flag close merge delete

Comments

add a comment see more comments

1 Answer

0

This might indicate that your OpenAI key doesn't have access to that model. We've had some reports of this error but haven't yet figured out what causes it.

It could also be there is a problem with the API key. A known bug in 10.0.5.1 is that you can't use the Use Key option (pasting the key right into the configuration panel) but need to put the longer new-style OpenAI keys into a file (either the default location or a custom location). That bug will be fixed in the next update.

In general, gpt-4o should work, though.

I'll add for anyone using 10.0.5.0 and earlier that might see this (not relevant in your case): Messages about gpt-4o not working from the chat tool are fixed in version 10.0.5.1.

Please let me know if this doesn't help or if you find out what the problem was.

Wingware Support's avatar
4.2k
Wingware Support
answered 2024-08-27 18:54:22 -0600
edit flag offensive 0 remove flag delete link

Comments

10.0.6 fixed using long form keys with the Use Key option.

Wingware Support's avatar Wingware Support (2024-09-23 16:03:24 -0600) edit
add a comment see more comments

Your Answer

Please start posting anonymously - your entry will be published after you log in or create a new account. This space is reserved only for answers. If you would like to engage in a discussion, please instead post a comment under the question or an answer that you would like to discuss.

Add Answer