The issue has been fixed. Models deployed during the outage returned errors in production. Those models have now been redeployed, and are working as intended.
Posted May 08, 2023 - 18:22 UTC
Identified
We have identified the cause of the issue and are validating a fix.
Posted May 08, 2023 - 17:47 UTC
Investigating
We are investigating an issue in which newly deployed models return errors at inference time. Previously-deployed, currently running models are unaffected.
Posted May 08, 2023 - 17:27 UTC
This incident affected: Modelbit Ohio (app.modelbit.com) (Running Models) and Modelbit Mumbai (ap-south-1.modelbit.com) (Running Models).