Inference API parallelism

Hello, I am trying to try out parallelism after subscribing to the pro plan. I am following the example in this page: Parallelism and batch jobs

However I am getting the following error code:

< Successful login
asyncio.exceptions.IncompleteReadError: 0 bytes read on a total of 2 expected bytes

What would be the problem that is even causing the example to run into an error? Please help, thanks!