Use API with model "gpt-3.5-turbo-instruct"?

API
1

Hello - i try to answer some questions from a text using the following code / request

   resp = openai.ChatCompletion.create(
          model = "gpt-3.5-turbo",
          messages=[{"role": "user", "content": wText}],
          request_timeout = 60, 
          temperature = 0.5,
        )

This works fine with this model - but i want to try also the model “gpt-3.5-turbo-instruct”
But when i try this i get this error message when running the program

Error happened: This is not a chat model and thus not supported in the v1/chat/completions endpoint. Did you mean to use v1/completions?

How can i use also the model “gpt-3.5-turbo-instruct”?

1 Like
2

gpt-3.5-turbo-instruct, unlike other gpt-3.5-turbo models, is designed to be consumed on the completions endpoint. Therefore, instead of a list of message objects, a string prompt will be passed in the call.

Here’s the API Reference.

1 Like