Account Registration, Droplets, and Related Services
Affected: GlobalGlobalGlobalReserved IP
DigitalOcean Outage History
DigitalOcean is up right nowDigitalOcean had 84 outages in the last 2 years totaling 196h 27m of downtime — averaging 3.5 incidents per month.
There were 84 DigitalOcean outages since November 8, 2025 totaling 196h 27m of downtime. Each is summarised below — incident details, duration, and resolution information.
Functions on App Platform
Affected: GlobalGlobal
Timeline · 3 updates
- investigating Aug 06, 2026, 07:01 PM UTC
Our Engineering team is investigating an issue impacting Functions on App Platform. During this time, users may experience build/deploy failures for Functions components, and requests to Functions endpoints may fail with a 504 error, caused by an SSL error when App Platform attempts to forward requests to Functions. This issue currently appears to be isolated to Functions deployed within App Platform. We apologize for the inconvenience and will share an update once we have more information.
- monitoring Aug 06, 2026, 08:02 PM UTC
Our Engineering team has implemented a fix for the issue affecting Functions on App Platform. Functions builds/deploys and requests to Functions endpoints should now be completing successfully. We are currently monitoring the situation to ensure the service has returned to normal operation and remains stable. We apologize for the inconvenience and will provide a further update once the incident is confirmed resolved.
- resolved Aug 06, 2026, 09:05 PM UTC
Our Engineering team has confirmed that the issue affecting Functions on App Platform has been fully resolved. Functions builds, deploys, and requests to Functions endpoints are all working as expected. The fix implemented earlier was successful, and we are no longer seeing any problems affecting Functions. However, if you continue to experience any issues, please don't hesitate to raise a support ticket for further investigation.
Multiple Services Availability
Affected: GlobalGlobalGlobalGlobalGlobalCloud FirewallDNS
Timeline · 1 update
Spaces Cold Storage Billing
Affected: GlobalBilling
Timeline · 4 updates
- investigating Aug 04, 2026, 04:13 PM UTC
Our Engineering team is investigating an issue affecting Spaces Cold Storage billing. During this time, customers with cold storage buckets may see incorrect values reflected in their daily usage and current invoices. We apologize for the inconvenience and are actively working to resolve the issue. We will provide an update as soon as more information becomes available.
- identified Aug 04, 2026, 06:52 PM UTC
Our Engineering team has identified the issue affecting Spaces Cold Storage billing. The team is actively working on a fix to resolve the issue. We apologize for the inconvenience and will provide another update as soon as more information becomes available.
- monitoring Aug 04, 2026, 08:44 PM UTC
Our Engineering team has implemented a fix for the issue affecting Spaces Cold Storage billing and is currently monitoring the situation. Customers with cold storage buckets should no longer see incorrect values reflected in their daily usage and current invoices. We will post an update as soon as the issue is fully resolved.
- resolved Aug 04, 2026, 09:42 PM UTC
As of 21:06 UTC, our Engineering team has resolved the issue affecting Spaces Cold Storage billing. An error in our billing processing system caused incorrect values to be reflected in daily usage and current invoices for customers with cold storage buckets. Our team identified and corrected an issue with the billing data sync, ensuring accurate usage reporting. If you continue to experience any issues, please open a ticket with our Support team. We apologize for any inconvenience this may have caused.
Cloud Control Panel Access
Affected: Cloud Control Panel
Timeline · 3 updates
- investigating Aug 03, 2026, 01:58 PM UTC
Beginning at 09:36 UTC on August 3, some customers may experience intermittent errors when accessing the DigitalOcean Cloud Control Panel, including an "mTLS verification failed" message. Our engineering team is actively investigating. We apologise for the inconvenience this may have caused. We will provide another update as soon as more information is available. If you have any questions related to this issue, please send us a ticket from your cloud support page. https://cloudsupport.digitalocean.com/s/createticket
- monitoring Aug 03, 2026, 04:39 PM UTC
We have implemented mitigation for the issue causing some customers to experience intermittent errors when accessing the DigitalOcean Cloud Control Panel. We are seeing recovery and are monitoring the service closely. We will provide another update once we have confirmed the issue is fully resolved
- resolved Aug 03, 2026, 05:59 PM UTC
Between 09:36 and 13:30 UTC on August 3, some customers experienced intermittent errors while accessing the DigitalOcean Cloud Control Panel. We renewed the affected internal certificates and restored access. The issue is resolved, and the Cloud Control Panel is operating normally. We apologize for the disruption.
Response Degradation Impacting Kimi-K3
Affected: Model Services
Timeline · 3 updates
- investigating Jul 29, 2026, 05:56 PM UTC
We are currently investigating this issue.
- investigating Jul 29, 2026, 09:41 PM UTC
Our Engineering team is investigating reports of empty or broken responses impacting Kimi-K3. At this point, users may experience degraded response quality, specifically empty or broken outputs (including repeated characters), when querying the Kimi-K3 service. We apologize for the inconvenience and will share an update once we have more information.
- resolved Jul 30, 2026, 06:15 AM UTC
Our Engineering team has resolved the issue causing empty or broken responses from Kimi-K3. If you continue to experience any problems, please open a ticket with our Support team. We apologize for any inconvenience this may have caused.
Agent Platform Requests Returning HTTP 500 Errors
Affected: Agent Runtime
Timeline · 3 updates
- investigating Jul 27, 2026, 06:31 PM UTC
We are currently investigating this issue.
- identified Jul 27, 2026, 07:44 PM UTC
The issue has been identified and a fix is being implemented.
- resolved Jul 28, 2026, 03:24 PM UTC
This incident has been resolved.
Network Connectivity from India to NYC
Affected: NYC1
Timeline · 3 updates
- identified Jul 24, 2026, 10:36 AM UTC
We have noticed network connectivity issues affecting some users connecting from India to resources in the NYC region. Based on our current investigation, users on Airtel and BSNL have reported increased latency, packet loss, or intermittent connectivity. We apologize for the inconvenience and will provide an update as soon as more information becomes available.
- monitoring Jul 24, 2026, 11:45 AM UTC
We are observing improvements in network connectivity for users in India accessing resources in our NYC region. Our team is monitoring the situation to ensure that the service has returned to normal operation and remain stable. We appreciate your patience and will provide an update once the issue is fully confirmed as resolved.
- resolved Jul 24, 2026, 12:42 PM UTC
Between 07:46 UTC & 10:24 UTC today, some users in India accessing resources in the NYC region may have experienced connectivity issues. The impact was limited to users using Airtel as their ISP. Our investigation determined that the issue was caused by an internal network issue within Airtel and was not related to DigitalOcean network. The connectivity issue now appears to be resolved, and users should no longer experience problems accessing their resources. We apologize for any inconvenience this may have caused. However, if you continue to experience any connectivity issues, please don't hesitate to open a support ticket for further investigation; we'll be happy to assist you further.
Llama-4-Maverick Model Availability
Affected: Inference
Timeline · 2 updates
- investigating Jul 23, 2026, 11:16 AM UTC
Our Engineering team is currently investigating an issue where the llama-4-maverick model is unavailable. Users may experience HTTP 500 errors while using this model with Serverless Inference. We apologize for the inconvenience. Our Engineering team is working with high priority to resolve the issue. Thank you for your patience and understanding.
- resolved Jul 23, 2026, 12:37 PM UTC
This incident has been resolved.
Gradient AI Serverless Inference Requests Timing Out for qwen3.5-397b-a17b
Affected: Inference
Timeline · 2 updates
- investigating Jul 22, 2026, 04:50 PM UTC
We are currently investigating this issue.
- resolved Jul 22, 2026, 07:42 PM UTC
This incident has been resolved.
Block Storage Volume NYC1, NYC3, SGP1, SYD1 and BLR1
Affected: BLR1NYC1NYC3SGP1SYD1
Timeline · 5 updates
- investigating Jul 19, 2026, 09:51 AM UTC
Our Engineering team is investigating an issue with attaching volume to the droplets in the NYC1 and NYC3 regions. During this time you may experience an issue with attaching volume to the Droplet(s). We apologize for the inconvenience and will share an update once we have more information.
- investigating Jul 19, 2026, 01:34 PM UTC
We are continuing to investigate this issue.
- investigating Jul 19, 2026, 01:36 PM UTC
We are continuing to investigate this issue.
- monitoring Jul 19, 2026, 02:52 PM UTC
Our Engineering team has identified the root cause of the issue preventing volume attachments to Droplets in NYC1, NYC3, SGP1, SYD1, and BLR1 and has successfully implemented a fix. You should now be able to attach volumes to your Droplet(s) without encountering any further errors or issues. We are actively monitoring the situation to ensure the fix remains effective and will provide another update once the issue has been fully resolved.
- resolved Jul 19, 2026, 03:32 PM UTC
Our Engineering team has confirmed that the issue regarding volume attachment to Droplets in the NYC1, NYC3, SGP1, SYD1, and BLR1 regions has been fully resolved, and all services are now operating normally. If you continue to experience any issues, please contact our Support team by opening a ticket. We apologize for any inconvenience caused.
Networking in BLR1
Affected: BLR1
Timeline · 4 updates
- investigating Jul 19, 2026, 06:57 AM UTC
We are currently investigating an issue affecting outbound network traffic for Droplets in the BLR1 region. Customers may experience timeout errors or connectivity issues when attempting to reach external services. Our Engineering team is actively investigating the issue and working to identify the root cause. We will provide additional updates as soon as more information becomes available.
- identified Jul 19, 2026, 08:27 AM UTC
Our Engineering team has identified an issue affecting upstream network connectivity for Droplet-based services in the BLR1 region and is actively working with the relevant upstream providers to implement a resolution. Customers may continue to experience intermittent timeouts or connectivity issues when attempting to reach external endpoints from Droplets in BLR1. We will provide another update once the issue has been fully resolved or when additional information becomes available.
- monitoring Jul 19, 2026, 09:31 AM UTC
Our engineering team has implemented the necessary fixes affecting upstream network connectivity for Droplet-based services in the BLR1 region. Users should now be able to connect to the external endpoints from Droplets in BLR1. We are currently monitoring the situation to ensure that the service has returned to normal operation and remain stable. We appreciate your patience and will provide an update once the issue is fully confirmed as resolved.
- resolved Jul 19, 2026, 09:52 AM UTC
Our engineering team has resolved the outbound network connectivity issue in the BLR1 region. If you continue to experience problems, please open a ticket with our support team. We apologize for any inconvenience.
Reserved IP routing in TOR1
Affected: Reserved IPTOR1
Timeline · 4 updates
- investigating Jul 16, 2026, 01:39 PM UTC
Our Engineering team is investigating an issue affecting Reserved IP routing in the TOR1 region. The issue is causing inbound and outbound traffic to and from Reserved IPs in TOR1 to fail. In the meantime, detaching and reassigning the Reserved IP to the Droplet may restore connectivity. We recommend trying this workaround if you are experiencing issues with your Reserved IP in TOR1. Our engineering team is actively investigating the root cause and working towards a resolution. We will provide updates as more information becomes available.
- identified Jul 16, 2026, 03:30 PM UTC
Our Engineering team has identified the cause of the issue affecting Reserved IP routing in the TOR1 region, which was causing inbound and outbound traffic to and from Reserved IPs in TOR1 to fail. Detaching and reassigning the Reserved IP to the Droplet may restore connectivity in the meantime. We recommend trying this workaround if you are still experiencing issues with your Reserved IP in TOR1. Our engineering team is now working on implementing a fix. We will provide updates as more information becomes available.
- monitoring Jul 16, 2026, 05:01 PM UTC
Our Engineering team has implemented a fix for the issue affecting Reserved IP routing in the TOR1 region, and we are currently monitoring the results. Inbound and outbound traffic to and from Reserved IPs in TOR1 should now be restored. If you reassigned your Reserved IP as a workaround and are still experiencing issues, please reach out to our support team. We will continue to monitor the situation closely and provide a further update once we have confirmed the issue is fully resolved.
- resolved Jul 16, 2026, 05:24 PM UTC
Our Engineering team has confirmed that the underlying issue affecting Reserved IP routing in the TOR1 region has been fully resolved, and services are now operating normally. If you continue to experience any issues, please contact our Support team by opening a ticket. We apologize for any inconvenience caused.
Serverless Inference - Gemma4 Latency Issues Causing Timeouts & Slow Responses
Affected: Inference
Timeline · 5 updates
- identified Jul 13, 2026, 07:04 PM UTC
We are currently experiencing an issue where customers using the Gemma 4 model on our Serverless Inference and Dedicated Inference platforms may experience severe latency or request timeouts. Our engineering team has identified a backend configuration issue as the root cause, which is temporarily degrading performance. We are actively working on a fix to restore normal response times and will provide another update as soon as the mitigation is in place
- monitoring Jul 13, 2026, 10:24 PM UTC
A fix has been deployed to resolve the backend configuration issue. We are closely monitoring system performance to ensure full recovery and normal response times for all Gemma 4 inference workflows.
- identified Jul 14, 2026, 11:07 AM UTC
We are currently experiencing an issue affecting customers using the Gemma 4 model on our Serverless Inference platform. Customers may experience significantly increased latency or request timeouts. Our Engineering team has identified a backend configuration issue as the root cause, which is temporarily impacting model performance. Please be assured that our Engineering team is actively working on a fix and is treating this issue with high priority. We sincerely apologise for any inconvenience this may have caused and appreciate your patience and understanding. If you have any further questions, please create a support ticket so that we can investigate your specific case further.
- monitoring Jul 15, 2026, 10:06 AM UTC
A fix has been deployed to resolve the issue. We are closely monitoring system performance to ensure full recovery and normal response times for all Gemma 4 inference workflows.
- resolved Jul 15, 2026, 09:46 PM UTC
The deployed fix has successfully restored full functionality, and our monitoring shows that system performance has completely stabilized. Response times for all Gemma 4 inference workflows have returned to normal baseline levels. We will continue to track platform stability moving forward to ensure long-term reliability. We apologize for any disruption this may have caused to your workflows and appreciate your patience throughout the recovery process.
Kubernetes Deployments in NYC1
Affected: NYC1
Timeline · 3 updates
- investigating Jul 09, 2026, 08:31 PM UTC
Our Engineering team is investigating an issue affecting Kubernetes deployments in NYC1. Users may see intermittent DNS failures and NodeNotReady events from application workloads during this time. We apologize for the inconvenience, we'll share new information on this page as soon as it is available.
- monitoring Jul 10, 2026, 01:18 AM UTC
The issue affecting Kubernetes deployments in NYC1 has subsided. Workloads should now be functioning normally. Our Engineering team is continuing to monitor the affected systems to confirm full resolution. We'll update this page if any further action is needed. We apologize for the inconvenience this may have caused.
- resolved Jul 11, 2026, 01:27 AM UTC
The issue affecting Kubernetes deployments in the NYC1 region has been resolved. Our investigation found intermittent DNS timeouts affecting a small number of DOKS clusters, with affected worker nodes running on shared-CPU Droplets. This is a documented limitation for latency-sensitive cluster DNS workloads such as CoreDNS. The affected clusters are currently functional. To reduce the risk of recurrence, we recommend running CoreDNS on non-shared/dedicated CPU node pools and using sufficient CoreDNS replicas. If you continue to see DNS failures or NodeNotReady events, please open a support ticket so we can investigate that cluster specifically.
Limited access to Deepseek V4 Pro model
Affected: InferenceModel Services
Timeline · 3 updates
- investigating Jul 04, 2026, 10:13 PM UTC
Our Engineering team is investigating reports of an incident affecting the Deepseek V4 Pro model in Serverless Inference and Agent Platform. Users may experience errors when attempting to use this model, specifically receiving error 429 messages. We apologize for the inconvenience and are working to resolve the issue as soon as possible. We will provide an update once we have more information.
- monitoring Jul 04, 2026, 11:18 PM UTC
Our Engineering team has implemented a fix for the issue with the Deepseek V4 Pro model in Serverless Inference and Agent Platform. The model should now be operational, and users should no longer receive error 429 messages when attempting to use it. We are currently monitoring the situation to ensure the fix is successful and the model is functioning as expected. We will post an update if any further issues arise. If you continue to experience problems, please open a ticket with our Support team. We apologize for any inconvenience this may have caused.
- resolved Jul 05, 2026, 12:53 AM UTC
Our Engineering team has confirmed that the issue with the Deepseek V4 Pro model in Serverless Inference and Agent Platform has been fully resolved. The model is now operational, and users should be able to use it without experiencing any errors. If you continue to experience any problems, please open a ticket with our Support team. We apologize for any inconvenience this may have caused and appreciate your patience.
Droplet Actions in NYC3
Affected: NYC3NYC3
Timeline · 2 updates
- monitoring Jul 04, 2026, 02:42 PM UTC
Our Engineering team has implemented a fix to address the issue affecting Droplets in the NYC3 region. The issue, which began at 12:38 UTC, caused disruptions to customers attempting to perform actions on their Droplets in the NYC3 region. During this time, customers may also have experienced errors when trying to create Droplets in this region. We are actively monitoring the situation to ensure the fix remains effective and will provide another update once the issue has been fully resolved.
- resolved Jul 04, 2026, 03:10 PM UTC
Our Engineering team has confirmed that the issue impacting Droplets in the NYC3 region has been fully resolved. Users can now perform actions on their Droplets or create new Droplets in this region without any issues. We appreciate your patience while we worked to resolve this issue. If you continue to experience any problems, please open a support ticket from your account so our team can investigate further.
Managed Database Clusters
Affected: GlobalGlobal
Timeline · 4 updates
- investigating Jul 02, 2026, 10:04 PM UTC
Our engineering team is investigating an issue affecting Managed Database Clusters. Currently, users may encounter delays when creating/scaling/forking and restoring Standard MySQL, Standard PostgreSQL, OpenSearch, Kafka, and Valkey clusters through the Cloud Control Panel or API. We apologize for the inconvenience and will provide further updates as soon as more information is available.
- investigating Jul 03, 2026, 02:28 AM UTC
Our engineering team is still investigating the issue affecting Managed Database Clusters. Users may still encounter delays creating/scaling/forking/restoring the aforementioned Managed Database Clusters. We are working to resolve this as soon as possible. we apologize for the inconvenience. We will post an update here once we have more information.
- monitoring Jul 03, 2026, 06:08 AM UTC
Our engineering team has implemented a fix to resolve the issue with Managed Database Clusters and is monitoring the situation. We will post an update as soon as the issue is fully resolved.
- resolved Jul 03, 2026, 08:20 AM UTC
Our engineering team has resolved the issue with Managed Database Clusters. All database systems should now be operating normally. If you continue to experience problems, please open a ticket with our support team. We apologize for any inconvenience.
DNS Lookup Failures for Managed Database
Affected: FRA1FRA1DNS
Timeline · 3 updates
- investigating Jul 01, 2026, 11:35 AM UTC
As of 06:39 UTC, our Engineering team is investigating reports of intermittent DNS lookup failures for Managed Database hostnames from Managed Kubernetes, primarily affecting connections from Managed Kubernetes to Managed Database hostnames. At this point, customers in the FRA1 region may experience intermittent connectivity issues. We apologize for the inconvenience and will share an update once we have more information.
- investigating Jul 01, 2026, 12:15 PM UTC
We are continuing to investigate this issue.
- resolved Jul 01, 2026, 04:28 PM UTC
The intermittent DNS lookup failures between Managed Kubernetes and Managed Database hostnames in the FRA1 region have been resolved for now but please let us know if you see the issue again. Connectivity has remained stable, and all systems are operating normally. If you continue to experience any problems, please open a ticket with our support team. Thank you for your patience, and we apologize for any inconvenience.
Droplet Resize
Affected: Cloud Control Panel
Timeline · 3 updates
- investigating Jul 01, 2026, 11:13 AM UTC
Our Engineering team is investigating an issue affecting Droplet resizes using the "Downscale Anytime" option. At this time users may find this option unavailable or unresponsive in the Cloud Control Panel. As a workaround, resizes can be performed via the API while we work to resolve this issue. We apologize for the inconvenience and will share an update once we have more information.
- monitoring Jul 01, 2026, 12:43 PM UTC
Our Engineering team has identified the root cause of the issue affecting Droplet resizes using the "Downscale Anytime" option and has implemented a fix. Users should now be able to resize their Droplets using the "Downscale Anytime" option without experiencing any issues or errors. We are actively monitoring the situation to ensure the fix remains effective and will provide another update once the issue has been fully resolved.
- resolved Jul 01, 2026, 01:28 PM UTC
Our Engineering team has confirmed that the issue impacting Droplet resizes using the "Downscale Anytime" option has been fully resolved. Users can now resize their Droplets using the "Downscale Anytime" option without any issues. We appreciate your patience while we worked to resolve this issue. If you continue to experience any problems, please open a support ticket from your account so our team can investigate further.
Agent Timeouts While Retrieving Data from Knowledge Bases
Affected: Agent RuntimeKnowledge Bases
Timeline · 3 updates
- investigating Jul 01, 2026, 06:25 AM UTC
Our Engineering team is currently investigating an issue where Agents are experiencing timeouts while retrieving data from Knowledge Bases. As a result, affected Agents may fail to retrieve data and return the following error: "Failed to retrieve data from Knowledge base(s) - timeout" Please be assured that we are treating this as a high-priority issue and are actively working to mitigate it. We sincerely apologise for any inconvenience this may have caused and appreciate your patience and understanding. If you have any further questions, please create a support ticket so that we can investigate your specific case further.
- identified Jul 01, 2026, 08:39 AM UTC
Our Engineering team has identified the issue causing Agents to experience timeouts while retrieving data from Knowledge Bases. Please be assured that our Engineering team is actively working on a fix and is treating this issue with high priority. We sincerely apologise for any inconvenience this may have caused and appreciate your patience and understanding. If you have any further questions, please create a support ticket so that we can investigate your specific case further.
- resolved Jul 02, 2026, 03:38 AM UTC
This incident has been resolved, and our teams continue to monitor the results. If you experience any further issues, please contact support.
Droplet Backup Service
Affected: Global
Timeline · 1 update
- resolved Jun 27, 2026, 06:24 PM UTC
Between 00:00 UTC & 16:00 UTC today, our Engineering team identified an issue affecting backup operations on Droplets. During this period, backups scheduled within this window may not have been created and may appear as missing. Our team has taken necessary measures to resolve the issue, and we can confirm that the backup service has been restored and is now functioning normally. Upcoming scheduled backups should be performed as expected. We sincerely apologize for any inconvenience this may have caused and appreciate your understanding. However, if you have any further questions or concerns, please create a support ticket for further analysis.
Anthropic Inference Model Availability
Affected: Inference
Timeline · 2 updates
- monitoring Jun 27, 2026, 04:43 AM UTC
Our Engineering team has mitigated an issue with Anthropic models. Previously, users may have encountered 400 errors when attempting to use any Anthropic model. Although the root cause of the issue is still being addressed by Anthropic, users should now be able to access and use Anthropic models again. We will continue to monitor the situation and provide updates if necessary. If you continue to experience problems, please open a ticket with our Support team. We apologize for any inconvenience this may have caused.
- resolved Jun 27, 2026, 05:15 AM UTC
Our Engineering team has resolved the issue that was causing HTTP 400 errors for requests to Anthropic models. Users should now be able to access Anthropic models without any issues. If you continue to experience problems, please open a ticket with our Support team so we can investigate further. We apologize for any inconvenience this may have caused.
Monitoring Graphs in the Cloud Control Panel
Affected: Global
Timeline · 3 updates
- investigating Jun 19, 2026, 02:00 PM UTC
Our Engineering team is currently investigating an issue affecting the visibility of monitoring graphs within the Cloud Panel. During this period, users may notice missing or unavailable monitoring graphs for services such as Droplets(with DO agent installed), Load Balancers, Databases, etc. We apologize for the inconvenience caused. We'll update once we have more information
- monitoring Jun 19, 2026, 02:50 PM UTC
Our engineering team has implemented the necessary fixes to address the issue affecting the visibility of monitoring graphs within the Cloud Panel. Users should now be able to view monitoring graphs for their services, including Droplets with DO Agent installed, Load Balancers, Databases, etc. We are currently monitoring the situation to ensure that the service has returned to normal operation and remain stable. We appreciate your patience and will provide an update once the issue is fully confirmed as resolved.
- resolved Jun 19, 2026, 04:37 PM UTC
Between 13:22 & 14:26 UTC today, users have experienced missing monitoring graphs for Droplets (with DO agent installed), Load Balancers, Databases, and other services within the Cloud Control Panel. Our engineering team has identified the root cause of the issue and has taken appropriate steps to restore functionality. We can confirm that services have been restored and are functioning as expected. We apologize for any inconvenience this may have caused. If you continue to experience issues viewing monitoring graphs, please create a support ticket for further analysis. Thank you for your patience and understanding
Intermittent 500 Errors on Serverless/GenAI Inference API
Affected: Inference
Timeline · 3 updates
- investigating Jun 16, 2026, 10:52 PM UTC
We are actively investigating an issue causing elevated HTTP 500 error rates for customers utilizing our Serverless/GenAI Inference API. Customer Impact: Customers making calls to the inference API—specifically targeting /v1/* endpoints—will experience intermittent HTTP 500 errors and failed requests.
- monitoring Jun 16, 2026, 11:29 PM UTC
Our engineering teams have successfully begun implementing mitigation steps to resolve the connectivity issues affecting the inference API. We will provide another update once the API has fully recovered and error rates return to normal.
- resolved Jun 17, 2026, 12:29 AM UTC
The connectivity issues affecting our Serverless/GenAI Inference API have been fully resolved. Our engineering teams successfully completed the connectivity restoration. All systems should be functioning normally, and the endpoint should be fully operational.