Change OpenAI default testing model to gpt-4o-mini

[jasonkang14]

Self Checks

• I have searched for existing issues search for existing issues, including closed ones.
• I confirm that I am using English to submit this report (我已阅读并同意 Language Policy).
• [FOR CHINESE USERS] 请务必使用英文提交 Issue，否则会被关闭。谢谢！:）
• Please do not modify this template :) and fill in all the required fields.

1. Is this request related to a challenge you're experiencing? Tell me about your story.

The current Dify configuration mandates enabling GPT-3.5-turbo to add an API key. However, GPT-3.5-turbo has been deprecated and is costlier compared to GPT-4o-mini, which offers superior performance at a lower cost. It would be beneficial to consider updating the configuration to support GPT-4o-mini, optimizing both performance and cost efficiency

2. Additional context or comments

It would be advantageous if Dify utilized GPT-4o-mini for integrating OpenAI's models instead of GPT-3.5-turbo. GPT-4o-mini not only offers enhanced performance but also provides a more cost-effective solution compared to the now deprecated GPT-3.5-turbo.

3. Can you help us with this feature?

• I am interested in contributing to this feature.

[telmoss7]

I'm having the same problem, but after the changes that u put it remains still the same model on default.
Shouldn't the default model be upgraded to gpt-4o-mini with that changes?
Or should be something more changed ?