Llama 3.3 70B Service Unavailable

What to do

• Check whether your product depends on Cerebras. 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 2h 56m it lasted.

  Anything that failed between 2026-01-18 21:40 UTC and 2026-01-19 00:36 UTC may need a replay.

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

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

Updates from Cerebras 5

1. investigatingJan 18, 2026, 9:40 PM UTC

   The service is currently inaccessible. We are currently working urgently to restore service capabilities. We will provide further updates as we make progress.

   provider

2. identifiedJan 18, 2026, 11:52 PM UTC

   The issue has been root caused and fix is being implemented to bring the service backup.

   provider

3. monitoringJan 19, 2026, 12:03 AM UTC

   The fix has been rolled out and the service has resumed consuming traffic and being monitored.

   provider

4. investigatingJan 19, 2026, 12:35 AM UTC

   Between 12.45 PM PT and 4.00 PM PT users experienced service unavailability with Llama 3.3 70B, caused by a datacenter issue. We have deployed a fix and the issue is now resolved, model endpoint is operational.

   provider

5. resolvedJan 19, 2026, 12:36 AM UTC

   Between 12.45 PM PT and 4.00 PM PT users experienced service unavailability with Llama 3.3 70B, caused by a datacenter issue. We have deployed a fix and the issue is now resolved, model endpoint is operational.

   provider

Corrections

None so far.

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