When using the synchronous (runsync) version of the Runpod API, the system works as expected. However, when switching to the asynchronous version (run), the service consistently returns HTTP error statuses such as 400, 502, and 520. The logs of my backend that runs not on the runpod show the following sequence of events:
Last error message I received indicated that I expected JSON, but instead I got a Cloudflare HTML page.
Please advise on potential adjustments or any additional configuration that might help the asynchronous mode function correctly without triggering Cloudflare errors. If further details are needed (e.g., additional debug logs or request headers), I am happy to provide them.
I'm using Python, and there are no logs from the RunPod instance—it never gets to the "up" or "queued" state.