Current Status
Machine Size | Status | Remarks |
Free(CPU) | Operational | |
Medium | Operational | |
Large | Operational | |
Extra Large | Operational | |
2X Large | Operational | |
2XL Plus | Operational | Limited Supply, please try 2x large if failed. |
Scheduled Maintenance
Past Incidents/Maintenances
Incident | Updates |
2025-07-09 03:00 UTC | Launching are failing. Our engineers are investigating |
2025-07-09 04:20 UTC | Back to normal. |
Incident | Updates |
2025-06-13 12:05 UTC | Back to normal. |
2025-06-13 11:40 UTC | Launching are failing intermittently. Our engineers are investigating |
Incident | Updates |
2025-06-04 12:40 UTC | Back to normal, monitoring. |
2025-06-04 12:20 UTC | Launching are failing intermittently. Our engineers are investigating |
Incident | Updates |
2025-04-30 10:30 UTC | Launching are back online. Monitoring. |
2025-04-30 10:20 UTC | Please relaunch if failed. |
2025-04-30 10:10 UTC | Launching are failing intermittently. Our engineers are investigating |
Maintenance | Updates |
2025-02-24 06:30AM UTC | Done. Machine launching back to normal. |
2025-02-24 06:00AM UTC | We will stop machine launching for about 30mins to update core infrastructure. Your running machines will not be affected during the update. |
Incident | Updates |
2025-02-06 9:20 UTC | Machine Launchings are back online. Monitoring. |
2025-02-06 9:00 UTC | Underlying storage provider major incident, we are working with them to bring back the services. |
2025-02-06 8:20 UTC | Launching failed. Our engineers are investigating |
Maintenance | Updates |
2025-01-22 08:30AM UTC | Update finished. |
2025-01-22 08:00AM UTC | Update in progress. |
2025-01-22 06:30AM UTC | We will update in 1 hour. |
2025-01-22 06:00AM UTC | We are postponing this update a bit later. Will post back once we know the time. |
2025-01-22 05:00AM UTC | We will stop the machine launching and “Add Funds” / Subscription for about 2 hours to update our core infrastructure. Your running machines will not be affected during the update. |
Incident | Updates |
2024-01-17 19:40 UTC | We applied a fix and machine launching are back to normal. Monitoring. |
2024-01-17 19:04 UTC | Still Investigating. |
2025-01-17 18:00 UTC | Launching failed. Our engineers are investigating |
Incident | Updates |
2024-01-06 18:00 UTC | Back to normal. |
2024-01-06 17:04 UTC | Most launches are successful now. Please relaunch if failed. |
2024-01-06 16:46 UTC | Please relaunch if failed. Should be working now. |
2024-01-06 16:36 UTC | Found a temp fix, patch applied. |
2024-01-06 16:00 UTC | Launching failed. Our engineers are investigating. |
Incident | Updates |
2024-12-05 00:04 UTC | Machine launching back to normal. |
2024-12-04 23:00 UTC | We are investigating. Underlying storage issue. |
2024-12-04 18:00 UTC | Launching failed. |
Incident | Updates |
2024-11-29 04:30 UTC | Launching is stable now. Monitoring. |
2024-11-29 02:30 UTC | Our network upstream provider is having a major outage, we are engaging with them to have a quick fix. |
2024-11-29 01:00 UTC | Launching failed. Our engineers are investigating. |
Incident | Updates |
2024-11-27 15:50 UTC | Launching is stable now. Monitoring. |
2024-11-27 14:43 UTC | https://www.cloudflarestatus.com/ Cloudflare is investigating delays in propagation of updates to DNS records. Please relaunch if failed. |
2024-11-27 14:00 UTC | Launching failed. Our engineers are investigating. |
Incident | Updates |
2024-11-12 04:30 UTC | Back to normal with intermittent failures. |
2024-11-12 04:10 UTC | Still working on a fix. |
2024-11-12 02:00 UTC | Launching failed. Our engineers are investigating. |
Incident | Updates |
2024-11-11 14:28 UTC | Back to normal. |
2024-11-11 14:00 UTC | Launching failed. Our engineers are investigating. |
Incident | Updates |
2024-11-4 08:30 UTC | Back to normal, working on a fix to prevent future failures. |
2024-11-4 07:30 UTC | Launching is failing intermittently. Still working on a fix. |
2024-11-4 06:00 UTC | Launching failed. Our engineers are investigating. |
Incident | Updates |
2024-10-14 21:00 UTC | Launching back to normal. Backend component connection issue. |
2024-10-14 20:44 UTC | Investigating and working on a fix. |
2024-10-14 19:48 UTC | Launching failed. |
Incident | Updates |
2024-10-09 09:30 UTC | Launching back to normal. Backend server libs issue. |
2024-10-09 07:00 UTC | Free(CPU) launching failed. Working on a fix. |
Maintenance | Updates |
2024-10-09 07:00AM UTC | Upgrade is done. |
2024-10-09 06:30AM UTC | Our engineers are working on finalizing the update. |
2024-10-09 05:30AM UTC | Still in progress. |
2024-10-09 05:00AM UTC | In progress. |
2024-10-09 04:00AM UTC | We will shutdown the machine launching for about 2 hours to update our core infrastructure. |
Incident | Updates |
2024-09-17 11:32 UTC | Launching back to normal. We are still investigating the root cause of this incident. Will update back once it is understood. |
2024-09-17 11:00 UTC | Machine launching failed. We are investigating. |
Incident | Updates |
2024-08-14 7:44 UTC | Back to normal. Network issue in the data center. |
2024-08-14 6:00 UTC | Machine launching failed. We are investigating. |
Maintenance | Updates |
2024-08-02 11:10AM UTC | Update finished |
2024-08-02 10:30AM UTC | We will shutdown the machine launching for about 1 hours to update our core infrastructure. |
Incident | Updates |
2024-06-16 12:50 UTC | All back online. |
2024-06-16 12:47 UTC | All GPU machines are back online, still fixing Free(CPU). |
2024-06-16 11:21 UTC | Still investigating. |
2024-06-16 10:49 UTC | Machine launching failed. We are investigating. |
Maintenance | Updates |
2024-06-13 03:00 UTC | Update is done. Launching back to normal. |
2024-06-12 21:00 UTC | We will shutdown the machine launching for about 4 hours to update our core infrastructure. |
Incident | Updates |
2024-05-29 18:00 UTC | Launching service restored. Monitoring |
2024-05-28 16:21 UTC | Machine launching failed intermittently. |
Incident | Updates |
2024-05-23 08:08 UTC | Launching back online, we are monitoring the situation. |
2024-05-23 07:28 UTC | Machine launching failed. Investigating. |
Incident | Updates |
2024-05-14 02:20 UTC | Launching back to normal. |
2024-05-14 00:28 UTC | Machine launching failed. Investigating. |
Maintenance | Updates |
2024-05-9 12:02 UTC | Update finished. |
2024-05-9 11:02 UTC | In progress. |
2024-05-9 11:00 UTC | We will shutdown the machine launching for about 1 hour to update our core infrastructure. |
Incident | Updates |
2024-05-08 14:25 UTC | Back to operational. |
2024-05-08 11:35 UTC | Fix is in and monitoring. Please retry in 10 mins if you see errors. |
2024-05-08 11:00 UTC | Observing elevated errors, working on a fix. |
2024-05-08 8:00 UTC | Implemented a fix and monitoring performance. Please retry if you see errors. |
2024-05-08 6:00 UTC | Still working on this issue, sorry about the inconvenience. Come back in couple of minutes to retry. |
2024-05-08 1:00 UTC | Still working on fixing this issue |
2024-05-07 20:00 UTC | Reactivated incident |
2024-05-07 15:00 UTC | Back to normal. |
2024-05-07 14:05 UTC | Machine Launching resumed. Still Monitoring the situation. |
2024-05-07 13:20 UTC | RunComfy is investigating issues with failed Launching. |
Maintenance | Updates |
2024-04-16 00:35 UTC | We had verified all functions are now working properly. |
2024-04-16 00:00 UTC | we will shut down the whole website and upgrade everything. The upgrade will take about 30 mins and the verification should last no more than another 30 mins. We expect the whole process will be finished within 1 hour. |
Incident | Updates |
2024-04-16 00:31 UTC | All machines are back online. |
2024-04-15 19:53 UTC | All machines are back online with intermittent failure, ETA 4 hours. |
2024-04-15 19:00 UTC | RunComfy is investigating issues with server provider. |
2024-04-15 18:40 UTC | RunComfy is investigating issues with failed Launching. |
Incident | Updates |
2024-04-08 05:48 UTC | All machines are back online. |
2024-04-08 01:53 UTC | All machines are back online with intermittent failure. ETA 4 hours to fully resolve the intermittent failure issue. |
2024-04-07 22:49 UTC | We are still working on a fix. No ETA at the moment. |
2024-04-07 17:00 UTC | RunComfy is investigating issues with underlying network provider. |
2024-04-07 16:40 UTC | RunComfy is investigating issues with failed Launching. |
Maintenance | Updates |
2024-04-02 15:15 UTC | We had verified all functions are now working properly. |
2024-04-02 14:00 UTC | we will shut down the whole website and upgrade everything. The upgrade will take about 30 mins and the verification should last no more than another 30 mins. We expect the whole process will be finished within 1 hour. |
Incident | Updates |
2024-03-30 01:57 | No issues are found during the recent Extra Large Machine sessions. Closing it for now. |
2024-03-29 06:34 | The fix is in. We are closely monitoring the Extra Large machine launching process. |
2024-03-29 05:56 | A fix has been implemented and we are verifying the fix. |
2024-03-29 03:56 | We are still working on a fix for Extra Large machine. No ETA at the moment. |
2024-03-29 01:45 | RunComfy is investigating issues with failed Extra Large Launching. Customer can launch other machine size at the moment. |
Incident | Updates |
2024-03-28 09:25 | Everything is back online. |
2024-03-28 09:09 | We are working on bringing everything back online. ETA 10mins. |
2024-03-28 08:52 | We are still investigating the issues. No ETA at the moment. |
2024-03-28 08:12 | We are still investigating the issues. No ETA at the moment. |
2024-03-28 06:00 | Machine Launching Failed. Investigating. |