Long-running Serverless Requests Execute Twice, Doubling Billing Costs

[MohabGhobashy]

I’m experiencing an unexpected behavior when running long requests (with data payloads around 200k samples) on RunPod’s serverless platform. After the job finishes and posts the results, it unexpectedly triggers another execution of the same request. This behavior causes the job to run twice, effectively doubling my costs. Notably, when I run similar jobs with smaller payloads (e.g., 10k or 20k samples), they execute normally without any duplicate runs.

[nerdylive123]

i'd recommend to open a support ticket for this too

[deanq]

@MohabGhobashy what version of SDK are you using that causes this? Opening a support ticket would be helpful too since we would need to ask for specific IDs that I don't want you to publish here.