pingoru pingoru Venice had 31 outages in the last 2 years totaling 63h 43m of downtime, averaging 1.3 incidents per month.
There were 31 Venice outages since April 15, 2025 totaling 63h 43m of downtime. Each is summarised below. Incident details, duration, and resolution information.
Most Agentic Chat responses are resulting in an error. We are actively investigating.
A fix has been implemented and we are monitoring the results.
This incident has been resolved.
We are currently investigating this issue.
Default chat (agentic and classic in auto mode)
A fix has been implemented. Most services are operational and will continue to improve in the coming minutes.
We are continuing to monitor for any further issues.
A fix has been implemented. Most services are operational and will continue to improve in the coming minutes.
A fix has been implemented. Most services are operational. We are continuing to monitor.
This incident has been resolved.
We are currently investigating an incident which is preventing several models and agentic chat from functioning.
A fix has been implemented and we are monitoring the results.
This incident has been resolved.
Agentic Chat, as well as a few other models, are currently offline due to a partner incident. We're working with the provider to restore service ASAP.
The provider has resolved the issue and we are monitoring
This incident has been resolved.
Agentic Chat is degraded. We are currently working on adding capacity.
A fix has been implemented and we are monitoring the results.
We are continuing to monitor for any further issues.
This incident has been resolved.
We are seeing increased error rates with several chat models. We are currently investigating
The incident appears to be resolved. We're still investigating the root cause and monitoring the situation.
This incident has been resolved.
We are investigating the issue, and will post updates as we have them. Select text models like GLM 4.6 and GLM 5 are offline.
A fix has been implemented and we are monitoring the results.
This incident has been resolved.
We are tracking an issue with a major internet infrastructure provider that may be the causing Venice as well as other sites not to respond in a timely fashion.
We have been informed that a fix is rolling out and the situation is improving rapidly
The provider has confirmed a fix and everything is operational.
We are receiving occasional reports that some users still cannot log in. We will continue to monitor as the provider fix rolls out.
We will continue to monitor as the provider fix rolls out.
This incident has been resolved.
We are tracking an issue with a major internet infrastructure provider that may be the causing Venice as well as other sites not to respond in a timely fashion.
Resolving as this is a duplicate status update. Please see the other incident for updates.
We are investigating an issue with several of our image models which is resulting in slow or unresponsive image generation
We have identified that the issue is with one of our infrastructure providers. We have added more capacity elsewhere to improve image throughput and reduce timeouts.
A fix has been implemented and we are monitoring the results.
This incident has been resolved.
We are currently investigating this issue.
This issue affects all image generation across the platform, not just the mobile app. We're continuing to investigate and will provide updates as we have them.
The issue has been identified and a fix is being implemented.
A fix has been implemented and we are monitoring the results.
This incident has been resolved.
We are currently investigating this issue.
We've identified the root cause and implemented a mitigation. API performance should now be more stable. We're continuing to monitor.
This incident has been resolved.
We are currently investigating this issue.
We are continuing to investigate this issue.
We are continuing to investigate this issue.
This incident has been resolved.
We're investigating login issues affecting Android devices and some web browsers. Users may experience login loops, failed requests, or missing chat history. iOS appears unaffected. We're actively working on a fix and will update shortly.
This incident has been resolved.
We are investigating
The issue has been identified and a fix is being implemented.
This incident has been resolved.
Video models are currently offline. All other models are operational.
This incident has been resolved.
Image Models are current offline. We are investigating the issue. Other models are functioning within normal operating parameters.
A fix has been implemented and we are monitoring the results.
This incident has been resolved.
We are working with one of our partner infrastructure providers on a networking issue. Most models are performing within range, but users may see occasional timeouts.
Our partner has resolved the issue and latencies are within range. We will continue to monitor the situation.
This incident has been resolved.
Our crypto API provider is currently experience an outage related to ongoing issues with their cloud provider which is affecting a range of internet services outside of Venice. Crypto related operations may be degraded or non functional.
The situation has improved significantly but will leave this incident open as we are still seeing occasional errors
In addition to issues with our crypto API provider, our database has been having issues and is causing failures with our API and slower App performance. Again, these issues are related to a major cloud incident that is affecting a wide range of internet services outside of Venice.
A fix has been implemented and we are monitoring the results.
This incident has been resolved.
We are experiencing performance issues with Venice Large. We are currently investigating.
This incident has been resolved.
We are currently investigating this issue.
All systems appear healthy. We believe that there is a severe networking issue affecting multiple data centers. We have migrated our services to a different region and re-routed traffic. We will continue to monitor the situation before considering this incident resolved.
The incident is resolved. We are still working with our infrastructure provider to determine the root case.
Several models are degraded or offline due to an issue at one of our partner data centers.
We are continuing to investigate this issue.
Most models are now functional but some remain in a partially degraded state. New capacity is coming online from other data centers to accommodate traffic.
All models are functional. Capacity is still being added to several models.
All models are now performing within operational parameters. We are working with our partner to better understand the root cause of the incident. Thank you for your patience.
We are continuing to investigate this issue.
This incident has been resolved.
We're currently investigating an issue causing high database load, which is leading to degraded performance across the app. Our engineering team is actively working to identify the root cause and restore full performance as quickly as possible.
We are continuing to investigate this issue.
A fix has been implemented and we are monitoring the results.
This incident has been resolved.
We are seeing errors from our authentication provider that prevent user sessions from loading. As a result, the web app, PWA, and API may hang on the loading screen or return 500 errors.
This outage has been resolved. Clerk has fixed its authentication outage and logins are working again. We’re monitoring for full stability. More details: https://status.clerk.com/