Is Replicate down?
Last checked 1m agoNo incidents right now.
Replicate is operational right now. Last checked 1m ago; the most recent incident resolved 3d ago.
Real-time Replicate status, recent outages, and incident history — pulled directly from Replicate's official status page at https://www.replicatestatus.com every 5 minutes. Pingoru tracks 0 Replicate services and has captured 11 incidents in the last 90 days (85.56% uptime). Get email, Slack, Discord, or webhook alerts the moment Replicate reports a new incident — free for 5 monitors, no credit card.
Recent outages & incidents
Past 90 days- A100 Hardware
Timeline · 3 updates
- investigating · Aug 26, 2026, 09:17 PM UTC
Status: Investigating We're seeing most A100 hardware automatically cordoned due to possible hardware failure. Affected components A100 Hardware (Partial outage)
- monitoring · Aug 26, 2026, 11:07 PM UTC
Status: Monitoring We are seeing pods start up again now and they are working through the backlog. Affected components A100 Hardware (Partial outage)
- resolved · Aug 27, 2026, 12:25 AM UTC
Status: Resolved We've been below capacity for A100 hardware for the past 30 minutes and all queues have been drained. Thanks for your patience 💖 Affected components A100 Hardware (Operational)
Latest: Status: Resolved We've been below capacity for A100 hardware for the past 30 minutes and all queues have been drained. Thanks for your patience 💖 Affected components A100 Hardware…
-
- L40S HardwareH100 Hardware
Timeline · 2 updates
- monitoring · Aug 10, 2026, 09:05 PM UTC
Status: Monitoring Scaling decisions were delayed by nearly 1 hour after the controller responsible for emitting queue metrics failed to schedule on a soft-failed node. We have since cordoned and drained the node, and the controller is emitting queue metrics again. Affected components H100 Hardware (Degraded performance) L40S Hardware (Degraded performance)
- resolved · Aug 10, 2026, 09:45 PM UTC
Status: Resolved All affected models have been scaling correctly for more than 30 minutes at this point, and we see no residual prediction queues. Thank you for your patience! Affected components L40S Hardware (Operational) H100 Hardware (Operational)
Latest: Status: Resolved All affected models have been scaling correctly for more than 30 minutes at this point, and we see no residual prediction queues. Thank you for your patience! Affe…
-
-
Timeline · 3 updates
- investigating · Aug 05, 2026, 09:30 AM UTC
Status: Investigating We are aware of a significant degradation with the service. We have identified the root cause and are taking steps to mitigate. Please hold tight for further information.
- monitoring · Aug 05, 2026, 11:25 AM UTC
Status: Monitoring We have made significant progress in recovering the services, and most traffic should be flowing normal. We are monitoring to make sure all traffic is recovered before closing the incident
- resolved · Aug 05, 2026, 11:33 AM UTC
Status: Resolved We have been monitoring for a while and services seem to be back. Thank you for your patience
Latest: Status: Resolved We have been monitoring for a while and services seem to be back. Thank you for your patience
-
-
Timeline · 2 updates
- identified · Aug 02, 2026, 04:09 PM UTC
Status: Identified The API for creating predictions for A100s is currently degraded as a piece of backing infrastructure failed. We are working on getting it back online
- resolved · Aug 02, 2026, 04:18 PM UTC
Status: Resolved We have restarted the affected component and service should be back to normal. Thank you for your patience
Latest: Status: Resolved We have restarted the affected component and service should be back to normal. Thank you for your patience
-
- A100 HardwareL40S HardwareH100 Hardware
Timeline · 4 updates
- identified · Jul 31, 2026, 09:25 PM UTC
Status: Identified Models that pull from huggingface during setup have not been succeeding, which is resulting in scale-out delays and queue backups. Affected components A100 Hardware (Degraded performance) H100 Hardware (Degraded performance) L40S Hardware (Degraded performance)
- identified · Jul 31, 2026, 09:26 PM UTC
Status: Identified We have confirmed that turning off our caching layer for huggingface downloads allows models to successfully set up, so we are making that change for all models while we continue to troubleshoot. Affected components H100 Hardware (Degraded performance) L40S Hardware (Degraded performance) A100 Hardware (Degraded performance)
- monitoring · Jul 31, 2026, 10:27 PM UTC
Status: Monitoring All affected hardware types have recovered and we are continuing to monitor and troubleshoot. Thanks for your patience! Affected components H100 Hardware (Operational) L40S Hardware (Operational) A100 Hardware (Operational)
- resolved · Jul 31, 2026, 11:39 PM UTC
Status: Resolved We're looking stable now, and with caching back on. Thanks again for your patience! Affected components A100 Hardware (Operational) H100 Hardware (Operational) L40S Hardware (Operational)
Latest: Status: Resolved We're looking stable now, and with caching back on. Thanks again for your patience! Affected components A100 Hardware (Operational) H100 Hardware (Operational) L40…
-
See the full Replicate outage history
5 more incidents in the last 90 days, plus the full multi-year archive of per-service events and update timelines.
Browse Replicate outage history →Or sign up free to get alerts when Replicate breaks · 10 free monitors · No credit card
- A100 hardware partial outage ResolvedStarted Aug 27, 2026, 12:25 AM UTC · Resolved Aug 27, 2026, 12:25 AM UTC · —
- Delayed scaling due to node failure ResolvedStarted Aug 10, 2026, 09:45 PM UTC · Resolved Aug 10, 2026, 09:45 PM UTC · —
- Significant degradation ResolvedStarted Aug 05, 2026, 11:33 AM UTC · Resolved Aug 05, 2026, 11:33 AM UTC · —
- API degraded for A100s ResolvedStarted Aug 02, 2026, 04:18 PM UTC · Resolved Aug 02, 2026, 04:18 PM UTC · —
- Started Jul 31, 2026, 11:39 PM UTC · Resolved Jul 31, 2026, 11:39 PM UTC · —
- Started Jul 23, 2026, 02:19 PM UTC · Resolved Jul 23, 2026, 02:19 PM UTC · —
- HuggingFace download issues ResolvedStarted Jul 16, 2026, 04:04 PM UTC · Resolved Jul 16, 2026, 04:04 PM UTC · —
- Started Jul 14, 2026, 05:27 PM UTC · Resolved Jul 14, 2026, 05:27 PM UTC · —