BasetenPartial outage on Kimi K3 model API inference (non-US only)
This incident has been resolved.
Resolved
Outages and recoveries from the services you depend on.
40 incidents
This incident has been resolved.
Resolved
The data has all been posted. We apologize for the delay.
Resolved
This incident has been resolved.
Resolved
This incident has been resolved.
Resolved
This incident has been resolved.
Resolved
Following continued monitoring, we’ve confirmed that the issue affecting multiple Webflow services has been resolved. This incident is now closed. We appreciate your patience while we worked with our upstream provider to resolve this issue.
Resolved
This is resolved
Resolved
This incident has been resolved.
Resolved
This issue is now resolved.
Resolved
Newly pushed images and tags are now processing and appearing normally. We have resolved the issue and confirmed that pushed tags were stored correctly and were not lost.
Resolved
Some customers experienced timeouts affecting CloudWatch traffic in prod-us-central-0 for approximately one hour. Service has since been restored. This incident did not affect all customers. We are publishing this update retrospectively and apologise for the disruption.
Resolved
Wait times for macOS jobs are back to normal.
Resolved
This incident has been resolved.
Resolved
Issue has been fixed
Resolved
Between approximately 23:00 UTC on September 12, 2026 and 09:12 UTC on September 14, 2026, some Grafana Cloud Logs customers in AWS Sweden (prod-eu-north-0) may have intermittently experienced errors when submitting configuration changes through the Cloud Portal. This has been resolved, and configuration change requests are being accepted normally.
Resolved
This incident has been resolved.
Resolved
Public Gateway creation/update in fr-par-1 were stuck in a transient state.
Resolved
This incident has been resolved.
Resolved
We have pushed up a fix to draft-frontend and are declaring the incident resolved.
Resolved
The incident has been resolved.
Resolved
Current status: We've implemented the fix for this issue and monitored the environment to confirm that service was restored. If you experience additional issues or have questions, please open a support case via Snowflake Community or the Support page in Snowsight. Customer experience: Customers hosted in the affected deployments may have experienced performance degradation or issues logging into Snowflake, including delayed sign-ins, and SSO login loops. Incident start time: 22:22 UTC September 13, 2026 Incident end time: 05:18 UTC September 14, 2026 Preliminary root cause: An update intended to improve authentication handling caused a subset of single sign-on (SSO) sign-in attempts across multiple regions to fail or loop, preventing affected users from logging in to Snowflake. A root cause analysis (RCA) will be conducted and a summary will be made available within 5 business days.
Resolved
All impacted services have now fully recovered.
Resolved
The ATO has resolved their issue impacting customers trying to file tax returns from Xero.
Resolved
We are no longer seeing issues with Cloud SIEM Processing and normal operation has been restored at this time.
Resolved
Resolved: Between 23:30 and 23:37 UTC on September 13, 2026, async transcription requests experienced elevated turnaround times due to an unexpected spike in processing load. We scaled out additional capacity and turnaround times returned to normal levels. Requests submitted during this window were processed, with some taking longer than usual to complete.
Resolved
This incident has been resolved.
Resolved
On Sunday, September 13, 2026, from 8:24 a.m. to 10:55 a.m. Pacific Time, Vapi Chat experienced a service disruption on both daily and weekly channels. During this period, requests to `/session` and `/session/{id}` timed out or returned HTTP 504 (Gateway Timeout) and 500 (Internal Server Error) responses, affecting chat session creation, retrieval, and management. Service was restored at 10:55 a.m. Pacific Time. All other services, including voice calls, were unaffected on both channels.
Resolved
All impacted services have now fully recovered.
Resolved
The maintenance at Interac has concluded successfully. We’ve observed reduced error rates and improved response times with Interac payments in Canada. The issue is now resolved.
Resolved
We are pleased to inform you that the incident affecting our Storage offering has been resolved. <b>Start time :</b> 13/09/2026 12:43 UTC <b>End time :</b> 13/09/2026 15:11 UTC <b>Root Cause :</b> A service disruption occurred due to an unexpected infrastructure failure. We apologize for any inconvenience caused and appreciate your understanding.
Resolved
All impacted services have now fully recovered.
Resolved
We are pleased to inform you that the incident affecting our Compute - Instance offering has been resolved. <b>Start time :</b> 13/09/2026 09:02 UTC <b>End time :</b> 13/09/2026 10:06 UTC <b>Root Cause :</b> A service disruption occurred due to an unexpected underlying infrastructure malfunction. We apologize for any inconvenience caused and appreciate your understanding.
Resolved
The metrics ingestion delay in GCP us-east4 has been fully resolved. All queued data has been processed and metrics are now showing in the console in real time.
Resolved
This incident has been resolved.
Resolved
Issue has been resolved and the network in EUR-IS-1 DC is operating normally.
Resolved
This incident has been resolved.
Resolved
Some customers experienced blurry images that couldn't be downloaded across all clients, affecting files uploaded before a recent file storage update. We deployed a fix restoring proper file access, and confirmed it resolved the issue for affected customers. We apologize for how this incident affected you and your business. We will undertake a full investigation of the incident, establishing the technical trigger, the underlying cause, and preventive action to avoid a repeat in the future.
Resolved
All pending builds have been completed and the issue is resolved, we are adding additional safeguards and better alerting to make sure the builder queue is more reliable.
Resolved
This incident has been resolved.
Resolved
All impacted services have now fully recovered.
Resolved