Serverless Inference

What to do

• Check whether you use DigitalOcean Agent Runtime. 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 1h 49m it lasted.

  Anything that failed between 2026-04-15 01:07 UTC and 2026-04-15 02:56 UTC may need a replay.

• Subscribe to DigitalOcean's feed to hear about the next one first. RSS feed

  https://down.guide/feed?provider=digitalocean works in Slack (/feed subscribe), Discord feed bots and any RSS reader.

Updates from DigitalOcean 3

1. investigatingApr 15, 2026, 1:07 AM UTC

   Our Engineering team is investigating an issue causing elevated error rates due to service instability and terminating open connections which causes some 500s. Some requests may fail while we work to resolve it. We apologize for the inconvenience and will share an update once we have more information.

   provider

2. monitoringApr 15, 2026, 2:24 AM UTC

   Our Engineering team has implemented a fix for the issue causing elevated error rates due to service instability. We are currently monitoring the situation to ensure stability and confirm that error rates, including HTTP 500 responses, have returned to normal levels. We will provide a further update once we confirm the issue is fully resolved.

   provider

3. resolvedApr 15, 2026, 2:56 AM UTC

   From 23:20 UTC to 02:00 UTC, users may have experienced elevated error rates due to service instability, which resulted in intermittent HTTP 500 errors and terminated connections. Our Engineering team has confirmed full resolution of the issue, and all systems are now operating normally. If you continue to experience any issues, please open a ticket with our support team. We apologize for any inconvenience caused.

   provider

Corrections

None so far.

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