RunPod: Upstream Issue: AWS Outages

What to do

Check whether your product depends on RunPod. Check your stack
Paste a package.json, lockfile, Terraform or a list of domains at down.guide/stack to see every provider you depend on.
Confirm your retries, queues and scheduled jobs caught up after the 6h 19m it lasted.
Anything that failed between 2025-10-20 08:24 UTC and 2025-10-20 14:43 UTC may need a replay.
Subscribe to RunPod's feed to hear about the next one first. RSS feed
https://down.guide/feed?provider=runpod works in Slack (/feed subscribe), Discord feed bots and any RSS reader.

updateOct 20, 2025, 8:24 AM UTC
AWS is having a large scale outage that is causing downstream issues on our hosting provider and causing partial or full downtime on console.runpod.io https://www.vercel-status.com/ Serverless and API calls are also seeing high levels of errors due to AWS outage https://health.aws.amazon.com/health/status https://downdetector.com/status/aws-amazon-web-services/
provider
updateOct 20, 2025, 12:48 PM UTC
AWS has redeclared the same incident, affecting our API service. We expect this will also impact the console, but nothing yet.
provider
updateOct 20, 2025, 2:01 PM UTC
We're currently working on migrating our services away from the affected AWS region. This may take a few hours. In the meantime, if the AWS region recovers sooner, our services should come back online as well, whichever happens first. Thank you for your patience. AWS health Status: https://health.aws.amazon.com/health/status
provider
updateOct 20, 2025, 2:32 PM UTC
We’re beginning to see early signs of recovery in the affected AWS region, and parts of our system are returning to normal operating thresholds. The team is closely monitoring the situation and will continue working on the migration as a precaution.
provider
resolvedOct 20, 2025, 2:43 PM UTC
Our GPU utilization is back to normal, and most clients’ serverless queue items have been processed. AWS still hasn’t updated their status page, but we’ll continue monitoring the situation.
provider

Reports count in aggregate; nothing about you is shown.

None so far.

Something wrong on this page? Report an error or send us a note. Every fix is listed here.

Is RunPod still down?

No, this incident was resolved 2025-10-20 14:43 UTC. For RunPod's live state, see https://down.guide/runpod.

How long did it last?

6h 19m, from 2025-10-20 08:24 UTC to 2025-10-20 14:43 UTC, by the times RunPod posted.

What caused it?

RunPod hasn't published a root cause. If it does, it shows here.

Where does this come from?

RunPod's official status page, https://uptime.runpod.io, quoted verbatim. down.guide's own probes, reports and social counts are labeled as ours.