There were 18 Elastic Cloud outages since February 6, 2026 totaling 113h 13m of downtime. Each is summarised below — incident details, duration, and resolution information.
We have identified and are working to mitigate an issue which is causing delayed AutoOps metrics for customers in AWS us-east-1.
This issue has now been resolved and we are continuing to monitor the system.
This issue has now been resolved.
Some users are seeing missing metrics visualizations in the Cloud console due to a disruption in metric data ingestion affecting deployments in the us-east-1 (US East) region. Some recent metric data may not appear in charts or monitoring views. We are actively investigating and will provide another update within 30 minutes.
Our investigation is ongoing. Some early signs of stabilisation have been observed, but metrics visualizations in the Cloud console remain impacted. We will provide a further update within 30 minutes.
Our investigation is ongoing. We continue to see early signs of stabilization, but metrics visualizations in the Cloud console remain impacted. We will provide a further update in 1 hour, or when there is a change in status.
We are continuing to see signs of stabilization and monitoring as the system recovers, but metrics visualizations in the Cloud console remains impacted until recovery is complete. We will provide a further update in 1 hour, or when there is a change in status.
The system has recovered and functionality has returned to normal.
We are currently investigating connectivity issues affecting a subset of customers in our EU West (Paris) region. Some requests may be experiencing elevated latency or failures. Our team is actively investigating, and we are working with our cloud infrastructure provider on the underlying issue. Other regions are not affected at this time. We will provide updates as the situation develops.
We are continuing to work on a fix for this issue.
Our monitoring system reports that AWS EU West 3 (Paris) region ingress layer traffic has recovered to normal levels as of 11:36 UTC and our SLO alerts have resolved. We are continuing to monitor and will update once we are confident the issue is fully resolved.
The connectivity issues affecting a subset of customers in our AWS EU West (Paris) region have been resolved. Failed probes recovered at 11:36 UTC following remediation of an issue with our underlying cloud infrastructure provider. We are no longer observing any elevated error rates or latency in the region. We apologise for any inconvenience caused and will conduct a post-incident review.
We're seeing elevated 5xx error rates for the Gemini Embedding v1 model in EIS. The following default inference endpoint is affected: - .google-gemini-embedding-001 We're investigating and will update again in 2 hours or if there's a change in status.
Errors are coming from the provider API (Google). The incident has been escalated to them, and we are still waiting for a response.
An incident with an upstream service provider has been resolved, and access to the model is now restored.
A recent change to our Privatelink implementation resulted in the URLs reported by the deployment API being incorrect in some cases, causing connectivity issues for customers who relied on those URLs. We have identified the issue and are working on a fix.
We have merged a fix and are working on deploying it to production
We are still working on moving the fix to production as we experienced some testing issues.
We have successfully deployed a fix for the PrivateLink hostname issue to the User Console. Customers who experienced incorrect PrivateLink URLs or connectivity issues with their deployments should now see correct hostnames. We apologize for the inconvenience.
We are aware of an issue when connecting to Kibana through the Elastic Cloud UI via SAML SSO, impacting hosted Cloud deployments. Our team is actively investigating. We will post an update to this status within the next hour.
We have identified that only PrivateLink customers are impacted and no other Hosted Cloud Deployments should see any issues.
We have identified the issue and are working on a fix. We will update again in 3 hours or earlier.
We have rolled out the fix and there should be no more customer impact
We have confirmed no further impact from this incident, and are now marking it as resolved.
We are investigating an issue in our Synthetics service on us-east-4. Some customer monitor jobs may not run on their expected schedule. We will provide an update in an hour or earlier.
We have identified the problem and are working on a solution. We should have an update within the next 2-3 hours.
Issue has been fixed and there should be no more customer impact
We're seeing elevated 5xx error rates for the Claude Sonnet 4.5 model in EIS. The following default inference endpoints are affected: - .anthropic-claude-4.5-sonnet-chat_completion - .anthropic-claude-4.5-sonnet-completion - .gp-llm-v2-chat_completion - .gp-llm-v2-completion We're investigating and will update again in 2 hours or if there's a change in status.
Endpoints are operating normally
We are currently investigating an outage of AutoOps in AWS us-east-1 region. Customer deployments in the region may be marked as inactive and recent metrics may not be available. We will provide an update when one is available or within the hour, whichever comes first.
We have identified the issue and applied mitigations to bring AutoOps in the AWS us-east-1 region back to functionality. Customer deployments may still be marked as inactive, and recent metrics may still not be available. We expect AutoOps to return to full functionality within the next hour. We will provide an update when one is available or within the hour, whichever comes first.
We have mitigated the issue, and AutoOps is back to full functionality in the AWS us-east-1 region. We will continue monitoring the signals from the region to ensure AutoOps remains fully functional, and will share another update once the issue is fully resolved.
AutoOps is back to full functionality in the AWS us-east-1 region and the incident has been resolved.
We are aware of problems creating new Serverless projects in the GCP europe-west3 region. The engineering team has identified the problem and we are working on mitigating it. We will post the next updated in 2 hours.
The engineering team is validating the fix to restore project creation in the GCP europe-west3 region. We will post another update in 2 hours or sooner if needed
This issue is resolved. Customers are now able to create new Serverless projects in the GCP europe-west3 region
We have identified an issue impacting the provisioning of kibana resources for new projects. This may delay or fail requests for new projects. We are investigating the root cause, and will post updates shortly.
Further investigations has indentified additional impact across services hosted in the GCP us-central1 region. We are working internally, and with our hosting providers to determine the root cause.
The issue has been identified, and we are working with our hosting providers to reach a solution. Users may see an impact with the availability of the elastic docker registry (browsing, and pulling images) Users may see an impact with the orchestration of their hosted Serverless projects, leading to slower provisioning and scaling tasks.
We have seen an improvement regarding this service disruption. The docker registry is available, and project orchestration has been restored. We will continue to monitor the situation, and ensure a full service recovery.
This incident has been resolved.
We're seeing some errors from fleet-server in Elastic Cloud that are affecting new incoming connections for some projects. We will provide an update within the next 2 hours.
We have identified the root cause of those sporadic errors observed and have successfully mitigated the issue. We continue to observe the situation and provide an update within the next 2 hours.
This incident is resolved.
We currently investigating an issue causing intermittent 404 errors when visiting the elastic.co webpage. We will provide additional updates as they become available.
404 errors have been resolved on the elastic.co webpage.
We are currently aware of and investigating an issue causing failure to provision new capacity in Elastic Cloud Hosted Azure regions. We will provide additional updates as they become available.
This issue is now resolved.
We've identified an issue on the billing usage pages where some hosted deployments might be showing incorrect usage. We're working on a fix and will update again in 6 hours.
We have identified and fixed an issue on the billing usage pages that resulted in the pages showing incorrect billing totals. There should be no more customer impact.
We are investigating a degradation in BYOK deployment creation in Azure regions. We will update again in one hour.
We have identified a misconfiguration in our Azure set up and working on pushing out the fix. Will update soon once it has been released.
This issue has been resolved, and BYOK deployment creation has been confirmed as fully functional.
We've noticed a degradation in the `openai-gpt-oss-120b` model in EIS, we're investigating the root cause and we'll update again in 2 hours
We've identified the issue and have merged a fix. We are in the process of rolling this out but are blocked by a GitHub degradation. Will update as soon as we have some progress on the deploy.
We have completed our work to restore access to`openai-gpt-oss-120b` model in EIS.
We are currently investigating an issue that has resulted in provisioning delays affecting the creation of new Elastic Cloud Serverless projects within the AWS us-east-1 region. While existing projects remain operational and unaffected, customers may encounter errors or extended wait times when attempting to spin up new projects in this specific region. Our engineering team is actively working to identify the root cause and restore full functionality. We apologize for the inconvenience and will provide further updates as more information becomes available.
We have successfully identified the root cause of the provisioning delays in the AWS us-east-1 region and are now beginning the remediation phase. A fix has been developed and validated through internal testing, and we are currently rolling out the fix across the affected infrastructure. Customers may still see intermittent failures for a short period as the fix propagates.
The issues affecting Elastic Cloud Serverless project creation in the AWS us-east-1 region have been resolved. Our engineering team identified a DNS configuration error as the root cause; once the records were corrected and propagated, service functionality returned to normal. All systems are now operating as expected, and customers should no longer experience delays or errors when creating new projects. We appreciate your patience while we worked to clear this up.
Pingoru polls Elastic Cloud's status page every 5 minutes and alerts you the moment it reports an issue — before your customers do.
5 free monitors · No credit card required