Nanonets Outage History
Nanonets is up right nowPingoru has recorded 50 incidents for Nanonets: 24 in the last 12 months and 2 in the last 90 days.
Show as a table
| Month | Incidents | Hours with an open incident |
|---|---|---|
| April 2026 | 2 | 2 of 720 (0%) |
| May 2026 | 2 | 1 of 744 (0%) |
| June 2026 | 4 | 6 of 720 (1%) |
| July 2026 | 1 | 1 of 744 (0%) |
| August 2026 | 0 | 0 of 744 (0%) |
| September 2026 | 1 | 2 of 720 (0%) |
| October 2026 | 1 | 5 of 527 (1%) |
Incidents, newest first
Notice October 1, 2026 Service Disruption Due to Google Cloud Outage - app.nanonets.com 5h 1m
Started Oct 01, 2026, 07:46 PM UTC· resolved Oct 02, 2026, 12:48 AM UTC
- investigating Oct 01, 2026, 07:46 PM UTC
Some of our models are seeing intermittent failures due to an ongoing issue with Google Cloud Platform (GCP). We're investigating, working with GCP, and applying mitigations to reduce the impact. We'll post another update sooner if anything changes. We apologize for the disruption
- monitoring Oct 01, 2026, 09:34 PM UTC
Error rates have dropped after we made some configuration changes. Services are partially restored, and some requests may still fail intermittently. We're continuing to work on full recovery and will keep you posted with further updates
- monitoring Oct 01, 2026, 09:36 PM UTC
We are continuing to monitor for any further issues.
- resolved Oct 02, 2026, 12:48 AM UTC
This incident has been resolved.
Major September 21, 2026 Delayed file processing for models in app.nanonets.com 1h 34m API
Started Sep 21, 2026, 03:21 PM UTC· resolved Sep 21, 2026, 04:55 PM UTC
- investigating Sep 21, 2026, 03:21 PM UTC
We are currently investigating this issue.
- identified Sep 21, 2026, 03:52 PM UTC
The issue has been identified and a fix is being implemented.
- monitoring Sep 21, 2026, 04:49 PM UTC
A fix has been implemented and we are monitoring the results.
- resolved Sep 21, 2026, 04:55 PM UTC
This incident has been resolved.
- postmortem Sep 21, 2026, 05:35 PM UTC
On 21st September 2026 between 15:00 UTC and 16:30 UTC, some customers experienced delayed document processing and intermittent request failures across multiple models. The cause was an internal resource-accounting component in our model gateway that entered a repeated retry loop. This exhausted connection capacity on the affected service and caused a subset of processing nodes to restart, slowing throughput. We identified the root cause and applied a configuration change that resolved the issue, with service returning to normal by 15:30 UTC and most files were processed before 16:30 UTC. A permanent fix to the underlying component is being rolled out, along with additional monitoring to detect this condition earlier. We sincerely apologize for the inconvenience this caused and we are implementing stricter safeguards to prevent a recurrence
Major July 23, 2026 Delayed file processing for ILM models in app.nanonets.com 59m API
Started Jul 23, 2026, 03:55 PM UTC· resolved Jul 23, 2026, 04:55 PM UTC
- investigating Jul 23, 2026, 03:55 PM UTC
We are currently investigating this issue.
- identified Jul 23, 2026, 04:19 PM UTC
The issue has been identified and a fix is being implemented.
- monitoring Jul 23, 2026, 04:39 PM UTC
A fix has been implemented and we are monitoring the results.
- resolved Jul 23, 2026, 04:55 PM UTC
This incident has been resolved.
- postmortem Jul 23, 2026, 05:37 PM UTC
**Date of Incident:** 23-July-2026 **Region Affected:** US **Duration:** 14:10 UTC – 16:40 UTC **Severity:** Partial degradation \(no data loss\) **Summary** On the date above, customers in the US region using document-level instant learning models experienced elevated processing times on [app.nanonets.com](http://app.nanonets.com). The issue was isolated to document-level model processing and did not affect other regions or services. **Impact** Users submitting documents for processing via document-level instant learning models in the US region saw delayed responses and higher-than-normal latency during the incident window. No documents or data were lost, and all queued requests were processed once the issue was resolved. **Root Cause** An internal message-processing component responsible for routing document jobs to our instant learning models encountered a permissions fault that prevented it from passing messages through as expected. This caused jobs to back up in the processing queue, which in turn drove up response times for affected requests. **Resolution** Our engineering team identified the faulty component, corrected the permissions issue, and restored normal message flow. The backlog of queued documents was drained and fully processed shortly after the fix was applied. Service returned to normal operating latency by 16:40 UTC. We sincerely apologize for the inconvenience this caused and we are implementing stricter safeguards to prevent a recurrence
Major June 28, 2026 Brief Service Unavailability on June 29 for app.nanonets.com 5h 30m
Started Jun 28, 2026, 11:00 PM UTC· resolved Jun 29, 2026, 04:30 AM UTC
- resolved Jun 29, 2026, 04:41 AM UTC
Between 04:21 AM UTC and 04:25 AM UTC on June 29th, app.nanonets.com experienced a brief service disruption, during which the application was unavailable. The issue was caused by an unexpected error encountered during backend infrastructure operations, resulting in a temporary interruption of service. The issue was identified and resolved promptly, and all services have been fully restored. We apologize for the inconvenience and appreciate your patience.
Notice June 25, 2026 Processing delay on Agent Tasks –
Started Jun 25, 2026, 10:30 PM UTC· resolved Jun 25, 2026, 10:30 PM UTC
- resolved Jun 30, 2026, 12:07 PM UTC
Our database was running at capacity due to disk usage surge, this lasted for an hour before we recognized the problem and scaled the database.
Major June 25, 2026 Agents UI freezing issue –
Started Jun 25, 2026, 01:30 PM UTC· resolved Jun 25, 2026, 01:30 PM UTC
- resolved Jun 26, 2026, 07:06 AM UTC
Frontend resources taking time to load causing UI to freeze in loading state. Appropriate CDN fixes were implemented to fix the issue.
Notice June 24, 2026 Processing Delay on Agents –
Started Jun 24, 2026, 01:30 PM UTC· resolved Jun 24, 2026, 01:30 PM UTC
- resolved Jun 30, 2026, 12:03 PM UTC
We observed processing delay on tasks in Agents Platform for a couple of hours caused by architectural changes introduced by our team to increase observability of our platform.
Notice May 31, 2026 Brief Service Unavailability on June 1 for app.nanonets.com 7m
Started May 31, 2026, 07:23 PM UTC· resolved May 31, 2026, 07:30 PM UTC
- resolved May 31, 2026, 07:35 PM UTC
Between 12:53 AM IST and 01:00 AM IST on June 1, app.nanonets.com experienced a brief service disruption, during which the application was unavailable. The issue was caused by an unexpected error encountered during backend infrastructure operations, resulting in a temporary interruption of service. The issue was identified and resolved promptly, and all services have been fully restored. We are reviewing the incident and strengthening our deployment and validation processes to further reduce the likelihood of similar occurrences. We apologize for the inconvenience and appreciate your patience.
Major May 14, 2026 RCA: Performance Degradation for LLM Nano Models on May 14 1h 15m
Started May 14, 2026, 10:00 PM UTC· resolved May 14, 2026, 11:15 PM UTC
- resolved May 15, 2026, 07:14 AM UTC
From 22:00 UTC to 23:15 UTC on May 14th, we observed performance degradation in the oneshot service affecting LLM Nano models. The issue was primarily caused by a network issue with our GPU service provider. Our team worked with the provider to stabilize the service and performance has since recovered. As an additional preventive measure, we are introducing stronger fallback mechanisms to route requests to more accurate backup models during such events. We apologize for the inconvenience caused and appreciate your patience.
Major April 28, 2026 Elevated 5xx Errors & Timeouts for Instant Learning (LLM Nano) 46m API
Started Apr 28, 2026, 05:16 AM UTC· resolved Apr 28, 2026, 06:02 AM UTC
- investigating Apr 28, 2026, 05:16 AM UTC
We are currently investigating an issue affecting our GPU service provider infrastructure, which is causing elevated 5xx errors and timeouts for Instant Learning models using LLM Nano. Our team is actively working with the provider to identify and resolve the underlying network issues. We will share further updates as soon as we have more information.
- monitoring Apr 28, 2026, 05:37 AM UTC
We’ve temporarily routed LLM Nano traffic to LLM Mini, a more stable, accurate and higher-capacity variant, to mitigate errors. File processing should now be faster and more reliable while we continue working on resolving the underlying issue.
- resolved Apr 28, 2026, 06:02 AM UTC
This incident has been resolved.
Major April 9, 2026 Intermittent 503 Errors for Subset of Users on app.nanonets.com 59m
Started Apr 09, 2026, 06:30 AM UTC· resolved Apr 09, 2026, 07:29 AM UTC
- resolved Apr 10, 2026, 07:13 AM UTC
Between 7:19 UTC and 7:29 UTC, a subset of users experienced intermittent 503 errors when accessing app.nanonets.com. A backend node went down and was replaced by a new node. Due to a DNS caching issue, traffic for some users could not be routed to the new node, resulting in failed requests. Other users were unaffected. The issue was identified and resolved by updating the load balancer configuration to ensure proper traffic routing. Preventive measures have been put in place to avoid recurrence.
Major March 10, 2026 Delayed file processing for all ILM models on app.nanonets.com 1h 15m API
Started Mar 10, 2026, 02:43 PM UTC· resolved Mar 10, 2026, 03:58 PM UTC
- investigating Mar 10, 2026, 02:43 PM UTC
We are currently investigating this issue.
- identified Mar 10, 2026, 03:19 PM UTC
The issue has been identified and a fix is being implemented.
- monitoring Mar 10, 2026, 03:34 PM UTC
A fix has been implemented and we are monitoring the results.
- resolved Mar 10, 2026, 03:58 PM UTC
This incident has been resolved.
- postmortem Mar 10, 2026, 04:50 PM UTC
On March 10 between 1:10 PM and 3:30 PM UTC, we experienced a service degradation that impacted Instant Learning Models \(ILM\) on [app.nanonets.com](http://app.nanonets.com/). **Impact**: During this period, our vector database experienced unusually high load due to the query planner selecting a suboptimal execution path for certain queries. This led to elevated database response times and eventually triggered a database restart. As a result, overall system throughput temporarily decreased. Customers may have observed the following effects during this window: * Asynchronous uploads for ILM models experiencing delayed file processing. * Synchronous uploads for ILM models encountering intermittent failures. Only **Instant Learning Models on** [**app.nanonets.com**](http://app.nanonets.com) were affected. Other services and model types remained fully operational. **Resolution:** Our engineering team identified the root cause related to query planning behaviour in the vector database and implemented targeted customizations to ensure the optimal execution path is used. This stabilized database performance and restored normal processing capacity. **Next Steps:** System is stable now and we are actively working on additional database optimizations and long-term improvements to further strengthen system stability and prevent similar issues from recurring. These enhancements will be rolled out in the coming days. We sincerely apologize for the inconvenience caused and appreciate your patience while we worked to resolve the issue. Please feel free to reach out to our support team incase if you have any questions.
Major March 4, 2026 RCA for Processing Delays for Instant Learning Models on app.nanonets.com – 04 Mar 2h 10m
Started Mar 04, 2026, 11:00 AM UTC· resolved Mar 04, 2026, 01:10 PM UTC
- resolved Mar 05, 2026, 09:37 AM UTC
On 04th March between 11:00 AM and 1:10 PM UTC, we experienced a service degradation that affected Instant Learning models hosted on app.nanonets.com During this time window, the secondary database serving part of the processing workload experienced unusually high load. This temporarily reduced our overall processing capacity to approximately 50%. As a result Asynchronous uploads may have experienced increased response times and delayed file processing. Synchronous uploads may have encountered intermittent failures. Only Instant Learning models on app.nanonets.com were affected. Other model types and other regions remained fully operational. Our engineering team identified the source of the elevated database load and implemented corrective actions to stabilize the system. Processing capacity was restored and services returned to normal by 1:10 PM UTC. We are implementing additional optimizations to improve database performance and resilience. These improvements will be deployed over this week and will not require any downtime. We sincerely apologize for the inconvenience caused and appreciate your patience while we worked to resolve the issue. Please feel free to reach out if you have any questions.
Minor February 11, 2026 Post-Processing Failures Impacting app.nanonets.com Models 15m API
Started Feb 11, 2026, 09:10 AM UTC· resolved Feb 11, 2026, 09:26 AM UTC
- investigating Feb 11, 2026, 09:10 AM UTC
We are currently investigating this issue.
- monitoring Feb 11, 2026, 09:15 AM UTC
A fix has been implemented and we are monitoring the results.
- resolved Feb 11, 2026, 09:26 AM UTC
This incident has been resolved.
Minor February 3, 2026 Delayed File Processing and Intermittent Failures Across Regions 22m API
Started Feb 03, 2026, 03:13 PM UTC· resolved Feb 03, 2026, 03:35 PM UTC
- identified Feb 03, 2026, 03:13 PM UTC
One of our GPU service provider is facing issues. We are working on resolving the issue with them.
- monitoring Feb 03, 2026, 03:22 PM UTC
A fix has been implemented and we are monitoring the results.
- resolved Feb 03, 2026, 03:35 PM UTC
This incident has been resolved.
Major January 28, 2026 Delayed file processing for all ILM models in app.nanonets.com 1h 50m API
Started Jan 28, 2026, 03:09 PM UTC· resolved Jan 28, 2026, 04:59 PM UTC
- investigating Jan 28, 2026, 03:09 PM UTC
We are currently investigating this issue.
- identified Jan 28, 2026, 03:35 PM UTC
We have identified the issue. A secondary database migration impacted indexes on a few core tables, leading to the current disruption. Our engineering team is actively working on restoring the database and we expect processing to resume once recovery is complete. We apologize for this unanticipated issue and will share an update as soon as services are fully restored.
- identified Jan 28, 2026, 04:20 PM UTC
We have recovered the db. Processing has resumed and we are working on clearing the backlog.
- monitoring Jan 28, 2026, 04:39 PM UTC
A fix has been implemented and we are monitoring the results.
- resolved Jan 28, 2026, 04:59 PM UTC
This incident has been resolved.
- postmortem Jan 30, 2026, 05:46 AM UTC
**Incident Summary** On 28th Jan 03:00 PM UTC, a secondary database migration unintentionally impacted indexes on a small number of core database tables. This led to degraded performance and temporary disruption of processing. **Impact** During this period, some prediction requests were delayed or unable to complete successfully until the database was stabilized. **Root Cause** A database schema change applied as part of a migration caused unintended modifications to critical indexes. While the migration itself completed, the index impact affected normal query performance on core tables because of high traffic volume. **Resolution** Our engineering team promptly identified the issue and initiated recovery actions, including restoring affected indexes and stabilizing database performance. Once recovery was complete, normal processing resumed. **Preventive Measures** To avoid similar incidents in the future, we are implementing the following improvements: * Database migrations will no longer be executed during peak usage hours for secondary database as well. * All future migrations will be scheduled during low-traffic windows with defined rollback plans. * Additional pre-deployment checks and safeguards will be added to detect potential impact on core database structures. We sincerely apologize for the inconvenience this incident may have caused. We understand the importance of reliability and take full responsibility for the disruption. Please be assured that we are taking concrete steps to ensure safer deployments and uninterrupted service going forward.
Minor January 27, 2026 Delayed file processing for models using async api in EU region 4h 48m API
Started Jan 27, 2026, 05:24 PM UTC· resolved Jan 27, 2026, 10:12 PM UTC
- investigating Jan 27, 2026, 05:24 PM UTC
We are currently investigating this issue.
- identified Jan 27, 2026, 06:27 PM UTC
The issue has been identified and a fix is being implemented.
- monitoring Jan 27, 2026, 09:32 PM UTC
A fix has been implemented and we are monitoring the results.
- resolved Jan 27, 2026, 10:12 PM UTC
This incident has been resolved.
- postmortem Jan 30, 2026, 05:56 AM UTC
**Incident Summary** On 27th Jan 17:00 UTC, we experienced elevated load on one of our core LLM processing engines due to a sudden increase in traffic volume. This primarily affected file processing workflows in the **EU region**. **Impact** * **Synchronous APIs** may have experienced intermittent failures or increased error rates. * **Asynchronous file processing** was degraded, with increased processing times. * Files submitted during this period were not lost and were eventually processed once the backlog was cleared, though with higher-than-usual latency. **Root Cause** A surge in traffic led to sustained high load on a core LLM engine, resulting in slower processing and queue buildup for async workflows in the EU region. **Resolution** Our engineering team actively monitored the situation and added additional processing capacity to handle the increased load and clear the backlog. Due to the size of the queue, backlog clearance took several hours, during which async response times were elevated. Once capacity was scaled and the backlog was processed, services returned to normal operation. We sincerely apologize for the inconvenience caused by this incident. We are working on adding more capacity on-demand so that this issue wont repeat again. Thank you for your understanding.
Minor January 23, 2026 Delayed File Processing in EU & EU-Open Region 1h 8m API
Started Jan 23, 2026, 05:55 PM UTC· resolved Jan 23, 2026, 07:04 PM UTC
- investigating Jan 23, 2026, 05:55 PM UTC
We are currently investigating this issue.
- identified Jan 23, 2026, 06:25 PM UTC
The issue has been identified and a fix is being implemented.
- monitoring Jan 23, 2026, 06:48 PM UTC
A fix has been implemented and we are monitoring the results.
- resolved Jan 23, 2026, 07:04 PM UTC
This incident has been resolved.
Major January 21, 2026 Async file processing & Extract data section file visibility issue for users using app.nanonets.com 35m API, Web App
Started Jan 21, 2026, 08:58 AM UTC· resolved Jan 21, 2026, 09:34 AM UTC
- investigating Jan 21, 2026, 08:58 AM UTC
We are currently investigating this issue.
- monitoring Jan 21, 2026, 09:07 AM UTC
A fix has been implemented and we are monitoring the results.
- resolved Jan 21, 2026, 09:34 AM UTC
This incident has been resolved.
Major December 11, 2025 Delay in file processing for Instant learning models in US region 1h 55m API
Started Dec 11, 2025, 07:56 AM UTC· resolved Dec 11, 2025, 09:52 AM UTC
- investigating Dec 11, 2025, 07:56 AM UTC
We are currently investigating this issue.
- monitoring Dec 11, 2025, 09:30 AM UTC
Our sync API is now operating normally. For async uploads, most results are already available and any remaining pending results will be processed within the next few minutes as we clear the backlog. Our team is addressing the issue on priority. We sincerely apologize for the inconvenience caused.
- resolved Dec 11, 2025, 09:52 AM UTC
This incident has been resolved.
- postmortem Dec 12, 2025, 07:45 AM UTC
One of our core processing services experienced an unexpected surge in load, which slowed down parts of our system and led to a backlog in processing. Our engineering team identified the underlying bottleneck and implemented fixes to stabilize performance. We are also rolling out improvements to make our platform more resilient to sudden spikes in usage. We sincerely apologize for the inconvenience caused.
Critical December 8, 2025 IN region Outage 6m API, Web App, Website
Started Dec 08, 2025, 07:52 AM UTC· resolved Dec 08, 2025, 07:59 AM UTC
- investigating Dec 08, 2025, 07:52 AM UTC
Service Disruption on https://in.nanonets.com US and EU regions are not affected
- identified Dec 08, 2025, 07:58 AM UTC
The issue has been identified and a fix is being implemented.
- resolved Dec 08, 2025, 07:59 AM UTC
This incident has been resolved.
Major December 3, 2025 High Response Times for Instant learning models in US region 6h 1m API
Started Dec 03, 2025, 03:08 PM UTC· resolved Dec 03, 2025, 09:10 PM UTC
- investigating Dec 03, 2025, 03:08 PM UTC
We are currently investigating this issue.
- identified Dec 03, 2025, 04:35 PM UTC
The issue has been identified and a fix is being implemented.
- identified Dec 03, 2025, 05:08 PM UTC
We have identified the issue and increased our throughput to process requests faster. However, clearing the backlog may take some additional time. Our team is continuously monitoring the situation. We apologize for the inconvenience and appreciate your patience.
- monitoring Dec 03, 2025, 08:50 PM UTC
Our sync prediction API for instant learning models is now operating normally. Async results for older files are available for most users and for few users we see some backlog which is getting cleared
- resolved Dec 03, 2025, 09:10 PM UTC
This incident has been resolved.
- postmortem Dec 04, 2025, 05:57 AM UTC
**Overview** One of our secondary databases experienced connection issues following an unexpected spike in load. This sudden surge placed significant pressure on the database engine, causing request latency to increase substantially. **Root Cause** A rapid increase in incoming traffic caused a large number of concurrent connections to accumulate on a secondary database. This overwhelmed the database’s connection handling capacity, resulting in slow responses and delayed processing for dependent services. **Resolution** Our engineering team quickly identified the issue, took corrective actions to stabilize the database, and restored normal operation. Once the database recovered, the system began processing the accumulated backlog. This recovery phase took additional time due to the volume of pending requests. **Impact** * **Affected:** Only Instant Learning models in the **US region** * **Unaffected:** All other regions and services apart from above continued operating normally throughout the incident
Minor November 8, 2025 Failures in some instant learning models 2h 13m API, Web App, Website
Started Nov 08, 2025, 06:33 PM UTC· resolved Nov 08, 2025, 08:46 PM UTC
- identified Nov 08, 2025, 06:33 PM UTC
The issue has been identified and a fix is being implemented.
- monitoring Nov 08, 2025, 08:04 PM UTC
A fix has been implemented and we are monitoring the results.
- monitoring Nov 08, 2025, 08:04 PM UTC
We are continuing to monitor for any further issues.
- resolved Nov 08, 2025, 08:46 PM UTC
This incident has been resolved.
Critical October 20, 2025 Service Disruption Due to Global AWS Outage 32m API, Web App
Started Oct 20, 2025, 09:11 PM UTC· resolved Oct 20, 2025, 09:43 PM UTC
- identified Oct 20, 2025, 09:11 PM UTC
On 20th Oct, a global AWS outage impacted one of our feature flag service providers, resulting in intermittent failures for some of our models. The issue originated from the provider's infrastructure dependency on affected AWS regions, which caused disruptions in feature flag evaluations within our system. Our engineering team promptly identified the root cause and implemented mitigation measures to restore functionality. We are continuously monitoring the situation and working with our partners to ensure full stability. We apologize for the inconvenience caused and appreciate your patience and understanding.
- monitoring Oct 20, 2025, 09:28 PM UTC
A fix has been implemented and we are monitoring the results.
- monitoring Oct 20, 2025, 09:29 PM UTC
We are continuing to monitor for any further issues.
- resolved Oct 20, 2025, 09:43 PM UTC
This incident has been resolved.
Critical September 22, 2025 app.nanonets.com down 15m API, Web App
Started Sep 22, 2025, 12:01 PM UTC· resolved Sep 22, 2025, 12:17 PM UTC
- investigating Sep 22, 2025, 12:01 PM UTC
We are currently investigating this issue.
- identified Sep 22, 2025, 12:07 PM UTC
The issue has been identified and a fix is being implemented.
- monitoring Sep 22, 2025, 12:09 PM UTC
A fix has been implemented and we are monitoring the results.
- resolved Sep 22, 2025, 12:17 PM UTC
This incident has been resolved.
- postmortem Sep 22, 2025, 02:09 PM UTC
**Temporary Service Disruption on Sept 22nd \(US Region\)** We experienced a temporary outage affecting our US region application \([_app.nanonets.com_](http://app.nanonets.com)\) between **11:58 and 12:09 UTC on Sept 22nd**. Other regions remained unaffected. The disruption was caused by an unexpected resource issue on one of our database nodes, which impacted application stability. Our team quickly identified the issue, applied a fix, and restored normal operations. We sincerely apologize for the inconvenience and we are implementing additional safeguards to prevent such issues in the future. Thank you for your understanding.