Cost for failed GPT requests

[celest osprey]

*new to discord *

Request to Chat models (gpt-3.5-turbo or gpt-4) can fail in 2 different ways:

• Issue from OpenAI side - This is case where model is overloaded with other requests
• Client adding a request time out - Here, for example, I as customer make a call with request time out as 10 seconds. The moment 10 seconds are passed, request is failed.

So in both situations, am I charged?

[sweet trench]

issue with openai - no - as long as it actually is issue with their server rather than u being an idiot and like using too many tokens

client adding time out - yes - because the request went through to openai but because of your time out it isnt getting back to you