Inconsistent performance of chat api

[Zhang-Zelong]

Confirm this is an issue with the Python library and not an underlying OpenAI API

• This is an issue with the Python library

Describe the bug

When call the client.chat.completions.create(..., logprobs=True) with gpt-3.5-turbo-1106
Sometime it will raise below error

Error code: 400 - {'error': {'message': "This model does not support the 'logprobs' parameter.", 'type': 'invalid_request_error', 'param': 'logprobs', 'code': None}}

To Reproduce

Run the code snippets in jupyter about 5~8 times, sometime it run correctly, somtime will raise an error.
https://platform.openai.com/docs/api-reference/chat/create?lang=python

Code snippets

from openai import OpenAI
client = OpenAI()

completion = client.chat.completions.create(
  model="gpt-3.5-turbo",
  messages=[
    {"role": "user", "content": "Hello!"}
  ],
  logprobs=True,
  top_logprobs=2
)

OS

Linux

Python version

python3.9.13

Library version

openai v1.6.1

[rattrayalex]

This issue is a duplicate; see #975 (comment)