Resolved -
Our Engineering team has implemented a fix, the issues impacting Gradient AI Platform have been resolved. All agents are back up and healthy. Service has been fully restored.
Mar 20, 14:14 UTC
Monitoring -
A fix has been implemented and services have been restored. We are continuing to monitor the system to ensure stability. We will provide further updates if needed.
Mar 20, 14:04 UTC
Update -
We've identified the issue and are actively working to restore the affected services. We're making steady progress and closely monitoring the situation. Further updates will be shared as they become available.
Mar 20, 11:05 UTC
Identified -
We’ve identified the issue and are currently working on restoring the services. We’ll continue to provide updates as progress is made.
Mar 20, 09:51 UTC
Investigating -
We are currently investigating issue affecting the accessibility of agents and services on the Gradient AI Platform. Users may experience failures or unresponsiveness when attempting to use these features. Our engineering team is actively working to identify the root cause and restore full functionality. We apologize for the inconvenience and will share an update once we have more information.
Mar 20, 08:50 UTC
Resolved -
The issue impacting delays in App Platform deployments has been confirmed to be resolved. Between approximately 00:08am UTC & 11:46am UTC, users may have noticed delays while creating or updating apps, or may have encountered failed deployments. For failed deployments, please trigger a redeploy, which should successfully resolve the issue.
We confirmed that the service is functioning as expected. Once again, we sincerely apologize for the inconvenience caused and appreciate your understanding.
However, if you continue to experience any issues, please don't hesitate to raise a support ticket for further investigation. We'll be happy to assist you.
Mar 20, 12:01 UTC
Monitoring -
Our Engineering team has deployed a fix to resolve the issue impacting new App Platform deployments using Dedicated Egress IP in FRA1 region. We are actively monitoring the situation to ensure stability and will provide an update once the incident has been fully resolved. Thank you for your patience and we apologize for the inconvenience.
Mar 20, 11:14 UTC
Investigating -
Our engineers are currently investigating an issue impacting new App Platform deployments using Dedicated Egress IP in FRA1 region. During this time, some users may experience delay when creating new App Platform apps or deploying existing apps. Existing apps are not affected and should continue to function normally. We apologize for any inconvenience, and we'll share more information as it becomes available.
Mar 20, 10:32 UTC
Resolved -
Our Engineering team has implemented a fix, the issues impacting model availability and performance have been resolved. All models, including those previously degraded, are back up and healthy. Service has been fully restored.
Mar 17, 19:49 UTC
Investigating -
Our Engineering team is investigating reports of Gradient AI model availability issues impacting multiple models. Users may experience issues with models availability, including Llama3.1-8b and Qwen3-32b, as well as embedding models such as GTE Large (v1.5), All-MiniLM-L6-v2, Multi-QA-mpnet-base-dot-v1, and Qwen3 Embedding 0.6B.
Additionally, Guardrails are not available, affecting associated agents, and users attempting to run inference on the Llama3.3-70b model will see degraded performance.
We apologize for the inconvenience and will share an update once we have more information.
Mar 17, 15:00 UTC
Resolved -
From 16:14 to 16:38 UTC, Our Engineering team observed an issue impacting Cloud control panel and API. During this time, users may experienced errors when trying to access the Cloud control panel and when trying to use the API. Our team has fully resolved the issues as of 16:38 UTC. If you continue to experience problems, please open a ticket with our support team from within your Cloud Control Panel. We apologize for any inconvenience caused.
Mar 16, 17:39 UTC
Resolved -
The issue is now resolved, all Anthropic BYOK models in Gradient AI should work normally. Contact support if issues persist.
Mar 15, 03:31 UTC
Investigating -
Our Engineering team is investigating an issue related to all Gradient AI agents and serverless inference that require BYOK Anthropic modles. Impacted users may experience degraded performance. We will provide an update as soon as possible
Mar 15, 02:55 UTC
Resolved -
As of 23:00 UTC, our Engineering team has confirmed that the issue causing delays in App Platform deployments has been fully resolved. The fix implemented earlier has been successful, and we are no longer seeing any delays or errors with deployments.
Users should now be able to deploy their apps successfully and without any issues. We apologize again for the inconvenience caused.
However, if you continue to experience any issues, please don't hesitate to raise a support ticket for further investigation.
Mar 14, 01:47 UTC
Monitoring -
After working with our upstream provider, our Engineering team has implemented a fix to resolve the issue that was causing delays in the deployment of new apps, and they are currently monitoring the situation.
During this time, users should no longer experience issues with creating new apps and all the stalled creation events should provision completely.
We will post an update as soon as the issue is fully resolved.
Mar 13, 23:39 UTC
Identified -
Our Engineering team is starting to see delays once again with new App Platform deployments. During this time, users may still experience delays with deploying new apps. We're working with our upstream provider to resolve the issue.
We again apologize for the inconvenience. We will post further updates once we have more information.
Mar 13, 22:01 UTC
Monitoring -
Starting at 20:40 UTC, users may have seen delays with deploying new apps on App Platform.
At this time, our Engineering team is seeing signs of recovery, and users should be able to deploy new apps without issue. We're currently monitoring the situation to ensure full recovery.
We apologize for the inconvenience. We'll post an update once the issue has been confirmed to be resolved.
Mar 13, 21:30 UTC
Resolved -
Our Engineering team has confirmed the resolution of the issue impacting DNS timeouts for newly provisioned Managed Kubernetes nodes. At this time all cluster services should now be functioning normally. If you continue to experience problems, please open a ticket with our support team. We apologize for any inconvenience.
Mar 13, 16:35 UTC
Monitoring -
Our Engineering team has implemented a fix to address the issue causing DNS timeouts for newly provisioned Managed Kubernetes nodes. Further investigation has confirmed that this issue primarily affected customers utilizing a NAT Gateway within their VPC and running a VPC-native cluster. We are actively monitoring the situation to ensure overall stability.
We appreciate your patience and will provide a further update once the issue is fully confirmed to be resolved.
Mar 13, 13:55 UTC
Identified -
Our Engineering team is investigating an issue impacting newly provisioned Managed Kubernetes nodes. During this time, Only customers who run a NAT Gateway in their VPC and a VPC-native clusters are affected and may experience DNS timeouts. We apologize for the inconvenience and will share an update once we have more information.
Mar 13, 12:32 UTC
Investigating -
Our Engineering team is investigating an issue impacting newly provisioned Managed Kubernetes nodes. During this time, new nodes may experience DNS timeouts, which could temporarily affect cluster services. We apologize for the inconvenience and will share an update once we have more information.
Mar 13, 11:26 UTC
Resolved -
From 17:50 to 19:06 UTC, Our Engineering team observed an issue with mirrors.digitalocean.com. During this time, users may have experienced errors when trying to update packages on Debian and Ubuntu Images. Our team has fully resolved the issues as of 19:06 UTC. If you continue to experience problems, please open a ticket with our support team from within your Cloud Control Panel. We apologize for any inconvenience caused.
Mar 9, 19:23 UTC
'
},
showLink: false,
cookie: {
domain: '.digitalocean.com',
expiryDays: '-1'
},
onStatusChange: function(status) {
onCookieConsentStatusChange(status);
}
});
});
}
})();
const incidentStates =
[ 'investigating'
, 'identified'
, 'monitoring'
, 'resolved'
];
$(function() {
// Add the twitter button
$('@dostatus').appendTo('.updates-dropdown-container');
if ($('.status.incident').length == 1) {
$('.components-affected').insertAfter('.page-title');
}
if ($('.status.status-index').length == 1) {
// Make the incident titles h3s and add links below the bodies
$('.incident-container').each(function() {
updateTitle($(this), 'h3', 'Incident Details');
});
$('.scheduled-maintenance').each(function() {
$(this).
children('.incident-title').
prepend('');
updateTitle($(this), 'h3', 'Maintenance Details');
});
// move the outage to the header
$('.page-status').appendTo('#header-incidents-inner-container');
// move the incidents to the header
$('.unresolved-incidents').appendTo('#header-incidents-inner-container').removeClass('unresolved-incidents');
// move the scheduled maintenance to the header
$('.scheduled-maintenances-container').appendTo('#header-incidents-inner-container');
// set the border-radius on second group
$('.component-container').attr('style','border-radius:3px !important');
// add the icon div
$('.unresolved-incident').each(function() {
var state; $(this).children('.updates').children('.update').each(function() {
state = $(this).
children('strong').
text().
toLowerCase();
if (incidentStates.indexOf(state) !== -1) {
return false;
}
});
$(this).
children('.incident-title').
prepend('');
updateTitle($(this), 'h2', 'Incident Details');
});
// rename "Past Incidents" to "Status History"
$('.incidents-list .font-largest').html('Status History');
// rename "Incident History" to "Show History"
$('.history-footer-link').html('Show History')
// weird opacity trick i'm doing don't touch
$('.layout-content').css('opacity',1);
} else {
$('#header-incidents-outer-container').remove();
$('.custom-header-container').addClass('bottom-padded');
}
});
function updateTitle(element, type, linkText) {
var titleCont = element.children('.incident-title');
var link = titleCont.children('a:not(.subscribe)');
var title = link.html();
$('<'+type+' class="title">'+title+''+type+'>').prependTo(titleCont);
link.html(linkText);
link.removeClass('actual-title').
removeClass('with-ellipsis').
addClass('incident-details');
link.appendTo(element);
}
$(function() {
$('.component-container').toggleClass('closed')
});
// Regional services layout
$('
').prependTo('.components-section')
$('
Regional Services Status
').appendTo('.regional')
$('.components-container').appendTo('.regional')
// Global services layout
$('