Skip to main content

With OpenAI app or with ChatGPT app, when sending the prompt as an action event, I am getting this error message: “invalid_request_error] This is a chat model and not supported in the v1/completions endpoint. Did you mean to use v1/chat/completions?”

I am aware that certain models don’t work in OpenAI app, but I am getting the same error on ChatGPT app as well. I can only use Gpt 3.5 but it’s very crucial for us to use newer models.

Anyone has an idea how to solve this?

Hi ​@darko 

For us to have more info, post these screenshots:

  • the encountered error in the Zap steps
  • how your Zap step is configured in EDIT mode with the field mappings visible

Hey Troy, thanks for the instructions.

Here is the Configure tab



and the Error when Testing

 



I can add more screenshots if needed, but I assure you that I am getting this exact same error in GPT app and in OpenAI app, no matter which model i choose. Only works with 3.5 turbo


@darko 

Try using a different ChatGPT action:

  • ChatGPT - Conversation
  • ChatGPT - Conversation with Assistant

 


Hi there ​@darko 👋

How did you get on with those other ChatGPT actions Troy suggested—did either of those do the trick or are you still seeing that same error message?

Looking forward to hearing from you! 🙂


Yes I had this same problem and switching to “Conversations” fixed the issue. Use that instead of Command Prompt.

 


Wow! Thank you for confirming that Troy’s resolution got the Zap running. This will significantly help our Community members to have as a reference for the same issue.


Reply