Clerk Outage History

The Ask AI functionality in Clerk docs has been restored.

We are investigating an issue with the Ask AI functionality in the Clerk Docs.

The incident is now resolved

We have implemented a fix for this incident and are monitoring to ensure the issue does not recur.

Latency is back to normal. We have identified the issue and are actively working on fixing it.

We are investigating increased latency for the Clerk Dashboard!

Despite extensive efforts to reach out to Apple about this issue we still do not have a resolution from them. As this incident has been ongoing for over a month, we have decided to move towards displaying a warning message on sign in from development instance when apple emails are used to sign in and taking down this incident notification. We apologize for the inconvenience and genuinely hope that we hear back from Apple soon on this matter.

We discovered today that emails sent only from development instances to Apple email addresses (icloud.com, me.com) are being rejected by Apple. We have reached out to Apple to inquire further and are hoping for a swift resolution on their end. In the meantime, we recommend using test emails () or an email address from a non-Apple domain to test/send emails from your development instances.

All systems are functional

Webhook delivery is normal at the moment. We are closely monitoring

Delays in webhook deliveries for some customers

All systems are working

A mitigation has been applied. Webhooks are being delivered at the normal pace. We continue monitoring

Currently there are delays for some customers in webhook delivery. The issue has been identified and we are working towards a resolution

Delivery to Microsoft-hosted mailboxes has been normal since 12:40 UTC. All delayed emails were delivered. This incident is resolved.

Delivery to Microsoft-hosted mailboxes returned to normal at about 12:40 UTC and delayed emails have been delivered. We are monitoring to confirm it stays that way.

We've found the cause. Emails to Microsoft-hosted mailboxes (Outlook.com, Hotmail, Microsoft 365) are being rate limited on the receiving side, and other email senders are seeing the same thing today. Emails are still accepted but some are delayed by several minutes while they're retried. Emails to all other providers are delivering normally. We're monitoring and will update when delivery times return to normal. If a code hasn't arrived, requesting a new one is the fastest workaround.

We are seeing delays in email delivery for recipients on Microsoft-hosted mailboxes (Outlook.com, Hotmail, Microsoft 365). Affected emails, including one-time passcodes and verification links, may arrive late or require re-sending. Emails to other providers are delivering normally. We are working with our email provider to restore normal delivery.

Latency and error rates have held steady since the last update. We will re-open if there is a resurgence in errors or latency.

latency metrics have returned to baseline, and we're seeing recovery in error rates. We are continuing to monitor for any signs of resurgence and will update accordingly.

We are noting recovery in the path between our services and the database provider, but latency and error rate are still elevated above baseline.

The path between our services and the database provider is currently impacted, leading to connection churn and elevated error rates.

Dashboard analytics have recovered and we're continuing to monitor for additional impact from the GCP incidents.

GCP has several incidents open in us-central1 currently. We are proactively monitoring impact to customer traffic and have so far noted impact to analytics and some of our metrics. We will update shortly with further information.

API performance has remained stable following mitigation. This incident has been resolved.

Mitigation has been applied and API performance has stabilized. We've deployed additional safeguards and are monitoring to confirm continued stability.

We identified elevated traffic affecting the Backend API and user-related requests, causing increased latency and intermittent failures. We've applied mitigation and are monitoring its effect. We'll provide another update once we confirm service stability.

We're investigating elevated latency and intermittent timeouts affecting Clerk API requests. Some customers may see slow responses when loading user and organization data. Our team is looking into it and will post another update once we have more information.

We've resolved the issue with our upstream provider.

Our upstream provider has applied a fix and we've seen latency and errors subside. We continue to monitor the situation.

We've identified the issue with our upstream provider and are working on resolution.

We are currently investigating an increase in latency and errors in our FAPI and BAPI services.

All systems are operational

Elevated error rate across all service

Custom domain provisioning is fully operational again

A fix has been implement by the downstream provider. We are closely monitoring.

Domain provisioning is currently delayed due to degraded availability at a third-party infrastructure provider. Existing live applications and session/sign-in/sign-up traffic are not affected. Affected domains will provision automatically once the provider recovers. No action is needed on your side. We will update once resolved.

Elevated error rates when provision a custom domain. Existing live applications and sign-in/sign-up and sessions are not affected.

We have confirmed that error rates have returned to baseline.

We've deployed a fix and are seeing error rates decrease. We are monitoring.

We're continuing to investigate.

We're continuing to investigate.

Reports of 429 error responses from API endpoints

There was a service degradation on our caching layer that affected the latency of our APIs. The caching layer is back to normal and latency dropped to normal levels.

There is increased latency on our APIs. We are investigating.

The underlying issue has been identified and the Account Portal is now fully functioning again.

We are observing evaluated errors in account portal and actively investigating the source of the problem

We have identified the cause of the delays and our mitigations have been successful. We are continuing to monitor webhook delivery.

We are investigating delays in webhook delivery. We have deployed mitigations and are continuing to monitor.

A fix has been published and confirmed it's now resolving SVGs correctly

A fix has been deployed and we're seeing improved rates of resolution on the SVGs

SVGs are not loading properly, the team is investigating a fix

Services are up and running.

A fix has been implemented, we are currently monitoring the affected services.

Issue identified

Dashboard Overview page is not loading properly.

Systems are fully operational

Elevated errors were observed in platform API when communicating with an upstream service

All systems are operational

A fix has been implemented by the upstream provider. We are monitoring the results

An upstream provider has a partial outage. Errors or delays might be encountered when a Clerk application goes live. We are monitoring the situation.

APIs have returned to normal operation.

We have deployed a mitigation to our APIs and observed errors return to a normal level. We are continuing to investigate and monitor.

We are investigating elevated level of internal errors in APIs.

Systems are back to normal.

Our upstream provider has implemented a fix for domain provisioning. We are seeing signs of recovery and are continuing to monitor the situation.

There is an ongoing issue with one of our upstream providers which is impacting the provisioning of domains.

The upstream provider marked the issue as resolved, we're continuing to monitor the database, but no error was observed.

We're monitoring the database health, no error has been found on the last 10 minutes.

Our upstream database provider is facing issues with a specific region where our database is deployed, we're currently seeing intermittent errors on the SCIM services. The rest of clerk is not affected