OpenAI error: invalid_request_error

Symptoms

You’re using the Send Prompt action and see the error message of "[invalid_request_error] This is a chat model and not supported in the v1/completions endpoint. Did you mean to use v1/chat/completions?" when using the OpenAI app. This error happens when testing the Zap or if the Zap is turned on.

Causes

This can happen when you’ve selected an incorrect chat model that isn’t compatible with the OpenAI app. 

How to fix it

To fix this:

• Go to the affected OpenAI step.
• In the Model dropdown menu, select one of the deprecated chat model alternatives:
  • babbage-002
  • davinci-002
  • gpt-3.5-turbo-instruct

Tip

Use the ChatGPT app, if you want to use any of these chat models:

• GPT-4o
• GPT-4 Turbo and GPT-4
• GPT-3.5 Turbo