Duration: 16 minutes

Affected Components: OCR API (us-east-1), OCR API (eu-central-1), OCR API (ap-southeast-1)

Mar 24, 22:07:00 GMT+0
Investigating - We are investigating an issue affecting v3/text in us-east-1 and eu-central-1\. API requests may be returning errors or timeouts..

Mar 24, 22:15:00 GMT+0
Identified - The issue in us-east-1 and eu-central-1 has been resolved. Failover traffic has caused degraded v3/text performance in ap-southeast-1\. We are actively working to resolve this..

Mar 24, 22:23:00 GMT+0
Resolved - All services are fully restored across all regions. Total incident duration was approximately 16 minutes. .

Duration: 1 day and 5 hours

Affected Components: OCR API (ap-southeast-1), OCR API (eu-central-1), OCR API (us-east-1)

Mar 20, 12:52:00 GMT+0
Investigating - We are investigating an issue affecting v3/text, v3/pdf, and v3/batch across all regions. API requests may be returning errors or timeouts. Live status: [monitor.mathpix.com](http://monitor.mathpix.com).

Mar 20, 12:59:00 GMT+0
Identified - Global impact has been resolved. We have identified a secondary issue in ap-southeast-1 caused by v3/pdf failover traffic. Customers using v3/text in ap-southeast-1, and some v3/pdf customers whose traffic was routed to that region, may still be experiencing errors. We are actively working to resolve this..

Mar 20, 13:21:00 GMT+0
Resolved - All services are fully restored across all regions. We are conducting a root cause analysis and will implement safeguards to prevent recurrence..

Duration: 28 minutes

Affected Components: OCR API (eu-central-1), OCR API (ap-southeast-1), Snip, OCR API (us-east-1)

Dec 27, 07:14:00 GMT+0
Investigating - We are investigating an issue causing intermittent errors and elevated latency for OCR API requests across multiple regions. Some OCR API requests may fail or time out during this period..

Dec 27, 07:42:00 GMT+0
Resolved - The issue has been resolved and OCR API requests are now processing normally. We will continue monitoring system health. Live status is available at <https://monitor.mathpix.com/>..

Duration: 2 hours and 16 minutes

Affected Components: Snip, OCR API (us-east-1)

Oct 20, 07:11:00 GMT+0
Identified - We have identified an issue affecting the PDF API due to an ongoing AWS outage impacting services in the US-East-1 region. Customers may experience elevated error rates or failed requests. We are actively monitoring the situation and working to restore normal operation as quickly as possible. Further updates will be provided as more information becomes available. **More details on affected services at:** [https://monitor.mathpix.com/.](https://monitor.mathpix.com/).

Oct 20, 09:27:00 GMT+0
Resolved - This incident has been resolved. AWS services in the US-East-1 region have recovered, and we are no longer observing errors or elevated latency for the PDF API. We are continuing to investigate why traffic was not automatically routed to other regions during the outage and are working to ensure our failover mechanisms handle similar events more effectively in the future. All systems are operating normally at this time. More details on affected services at: <https://monitor.mathpix.com/> ..

Affected Components: OCR API (ap-southeast-1), OCR API (eu-central-1), OCR API (us-east-1)

May 21, 07:35:00 GMT+0
Resolved - This incident has been resolved..

May 21, 07:15:00 GMT+0
Identified - We are continuing to work on a fix for this incident..

Duration: 2 hours

Affected Components: OCR API (ap-southeast-1), OCR API (eu-central-1), Snip, OCR API (us-east-1)

May 7, 14:30:00 GMT+0
Identified - We've identified an issue with our autoscaling being limited by AWS GPU capacity. We're adding more availability zones and scaling up manually..

May 7, 17:00:00 GMT+0
Resolved - All systems are back to normal..

Duration: 5 minutes

Jan 25, 06:11:09 GMT+0
Resolved - OCR API is now operational! This update was created by an automated monitoring service..

Jan 25, 06:06:01 GMT+0
Investigating - OCR API cannot be accessed at the moment. This incident was created by an automated monitoring service..

Duration: 2 hours

Affected Components: OCR API (us-east-1)

Sep 13, 12:45:00 GMT+0
Identified - A service disruption was caused by an error in our autoscaling policy. Unexpected usage patterns from some of our top customers revealed flaws in our autoscaling algorithm. This led to service degradation to our Image Convert API endpoints for customers routed to our US data centers, while customers closer to Europe or Asia were unaffected..

Sep 13, 14:45:00 GMT+0
Resolved - Our engineering team quickly identified the issue and implemented a fix to restore normal service operations. We conducted a thorough investigation to pinpoint the root cause and have developed long-term solutions to strengthen our system: * **Autoscaling Improvements:** We've revised our autoscaling policies and algorithms to better handle unexpected usage behaviors and high-demand scenarios. * **Enhanced Monitoring:** Implementation of advanced monitoring tools to detect anomalies in real-time. * **Resource Allocation:** Additional resources have been allocated to ensure robust performance during traffic surges..

Affected Components: OCR API (us-east-1)

Jan 20, 19:32:00 GMT+0
Resolved - This incident has been resolved. The PDF processing API was unavailable for processing requests from approximately 9:32-10:35 UTC .

Affected Components: OCR API (us-east-1)

Jan 20, 16:30:00 GMT+0
Resolved - This incident has been resolved. The PDF processing API was unavailable for processing requests from approximately from 18:30 to 21:00 UTC..

Affected Components: OCR API (us-east-1)

Dec 11, 04:44:59 GMT+0
Resolved - This incident has been resolved..