Previous incidents
Delayed prediction start times
Resolved Jun 27 at 04:35pm UTC
Predictions are flowing as expected once again. We'll continue to monitor the situation.
1 previous update
Web and API failures
Resolved Jun 23 at 03:45pm UTC
The rollback fixed things and we're back to normal.
1 previous update
Garbled/corrupted responses
Resolved Jun 21 at 04:10pm UTC
We've identified what's causing this issue and have rolled back the change. Affected predictions will have completed successfully and you can re-request their status through the API.
1 previous update
Model autoscaling degraded
Resolved Jun 05 at 11:23pm UTC
Autoscaling issues have been resolved for all models and everything should be operating normally.
1 previous update
Prediction webhook delivery interrupted
Resolved May 24 at 07:36pm UTC
Prediction webhooks are now working as intended.
We made a change intended to fix a subtle bug in webhook handling, and unfortunately introduced a much less subtle bug: "completed" webhooks were dropped and not correctly delivered. We rolled that change back and are now working on a permanent fix for both bugs.
1 previous update
500s and slow responses from replicate.com website
Resolved May 23 at 09:35am UTC
The database issue was automatically resolved. We made some changes to our database schema in the wrong order, and this resulted in a brief interruption of service for the replicate.com website. Running predictions was not affected.
1 previous update