[Bug]: LiteLLM keys not working on demo completion call

[ishaan-jaff]

What happened?

Tried copy pasting code on docs and it failed with this exception:

https://docs.litellm.ai/docs/

Code to repro

from litellm import completion
import os

## set ENV variables
os.environ["OPENAI_API_KEY"] = "sk-litellm-7_NPZhMGxY2GoHC59LgbDw" # [OPTIONAL] replace with your openai key

response = completion(
  model="gpt-3.5-turbo", 
  messages=[{ "content": "Hello, how are you?","role": "user"}]
)

Exception

Relevant log output

No response

Twitter / LinkedIn details

No response

[ishaan-jaff]

Also I have no idea what this error message means. It should probably tell me that the keys are invalid

the package is working fine -> it's making the openai proxy call -> the server is returning an error -> openai's python package is raising it as an invalid response error

what would you expect here @ishaan-jaff

[ishaan-jaff]

As a user of LiteLLM - shouldn't it just tell me invalid API key ?

Also for this ticket the issue im raising is to fix the proxy - it should not be throwing errors