Reducto Outage History
Reducto is up right nowPingoru has recorded 51 incidents for Reducto: 47 in the last 12 months and 11 in the last 90 days.
Show as a table
| Month | Incidents | Hours with an open incident |
|---|---|---|
| April 2026 | 4 | 1 of 720 (0%) |
| May 2026 | 6 | 7 of 744 (1%) |
| June 2026 | 9 | 14 of 720 (2%) |
| July 2026 | 2 | 7 of 744 (1%) |
| August 2026 | 4 | 3 of 744 (0%) |
| September 2026 | 4 | 18 of 720 (2%) |
| October 2026 | 2 | 3 of 507 (1%) |
Incidents, newest first
Minor October 1, 2026 Degraded performance on Parse API in the EU region 56m Parsing
Started Oct 01, 2026, 09:13 PM UTC· resolved Oct 01, 2026, 10:10 PM UTC
- investigating Oct 01, 2026, 09:13 PM UTC
We are investigating degraded performance on the Parse API in the EU region (eu.platform.reducto.ai). Only the EU region is affected.
- resolved Oct 01, 2026, 10:10 PM UTC
The Parse API in the EU region returned no errors after 21:18 UTC. This incident is resolved.
Minor October 1, 2026 Degraded performance on Parse API 1h 52m Parsing
Started Oct 01, 2026, 07:07 PM UTC· resolved Oct 01, 2026, 09:00 PM UTC
- investigating Oct 01, 2026, 07:07 PM UTC
We are investigating degraded performance on the Parse API.
- monitoring Oct 01, 2026, 08:02 PM UTC
An outage of our OCR service caused the degraded performance on the Parse API. The OCR service has recovered. We are monitoring the results.
- resolved Oct 01, 2026, 09:00 PM UTC
The Parse API is fully recovered. This incident is resolved.
Minor September 28, 2026 Partial degradation of Parse 17h 3m Parsing
Started Sep 28, 2026, 03:05 AM UTC· resolved Sep 28, 2026, 08:09 PM UTC
- investigating Sep 28, 2026, 03:05 AM UTC
Parse requests are degraded. Only the /parse endpoint is affected. Extract, Split, and Edit are operating normally. We are investigating.
- identified Sep 28, 2026, 03:22 AM UTC
Parse latency is degraded because of an issue with our GPU clusters. Our engineers are working on a fix. Only the /parse endpoint is affected.
- monitoring Sep 28, 2026, 03:35 AM UTC
The GPU clusters are recovered, and Parse latency is back to normal. We are monitoring the results.
- resolved Sep 28, 2026, 08:09 PM UTC
This incident is resolved. Parse latency has been normal since 8:35 PM PDT on September 27.
Minor September 16, 2026 Partial degradation of Parse for requests with embed_pdf_metadata –
Started Sep 16, 2026, 02:51 AM UTC· resolved Sep 16, 2026, 02:51 AM UTC
- resolved Sep 16, 2026, 02:51 AM UTC
This is resolved. Parse requests with embed_pdf_metadata set to true are operating normally.
Minor September 9, 2026 Partial degradation of Deep Split 11m Splitting
Started Sep 09, 2026, 11:22 PM UTC· resolved Sep 09, 2026, 11:33 PM UTC
- investigating Sep 09, 2026, 11:22 PM UTC
Deep Split experienced partial degradation beginning at 16:22 PDT on September 9. Impact was limited to Deep Split requests.
- resolved Sep 09, 2026, 11:33 PM UTC
The change was rolled back at 16:33 PDT, restoring normal Deep Split operation. The degradation lasted approximately 11 minutes and was limited to Deep Split requests.
Minor August 18, 2026 Elevated latency for /parse 1h 29m Parsing
Started Aug 18, 2026, 04:52 PM UTC· resolved Aug 18, 2026, 06:22 PM UTC
- identified Aug 18, 2026, 04:52 PM UTC
Elevated latency for parse, due to an issue with one of our gpu clusters. We've identified the problem and are actively fixing it.
- resolved Aug 18, 2026, 06:22 PM UTC
This is resolved. The GPU cluster issue has been fixed and parse latency has returned to normal. We confirmed recovery across the fleet. Thank you for your patience.
Minor August 18, 2026 Elevated latency for Extract with citations 2h 8m Extraction
Started Aug 18, 2026, 04:13 PM UTC· resolved Aug 18, 2026, 06:22 PM UTC
- identified Aug 18, 2026, 04:13 PM UTC
Extract requests that use citations or confidence scores are seeing elevated latency. The cause is an issue with one of our GPU clusters.
- monitoring Aug 18, 2026, 04:13 PM UTC
We have rolled out a fix and latency has returned to normal. We are monitoring to confirm the issue is fully resolved.
- resolved Aug 18, 2026, 06:22 PM UTC
This is resolved. The GPU cluster issue has been fixed and Extract latency, including requests that use citations or confidence scores, has returned to normal. We confirmed full recovery. Thank you for your patience.
Minor August 13, 2026 Elevated parse latency 30m Parsing
Started Aug 13, 2026, 05:40 PM UTC· resolved Aug 13, 2026, 06:10 PM UTC
- investigating Aug 13, 2026, 05:40 PM UTC
We are investigating elevated latency on the parse API. Some parse jobs take longer than normal to complete.
- resolved Aug 13, 2026, 06:10 PM UTC
We corrected a misconfiguration in our GPU inference fleet. Parse latency returned to normal levels.
Minor August 13, 2026 Degraded latency for Extract 23m Extraction, Splitting
Started Aug 13, 2026, 04:31 PM UTC· resolved Aug 13, 2026, 04:54 PM UTC
- investigating Aug 13, 2026, 04:31 PM UTC
We are seeing elevated latency on Extract and Split requests. Requests are completing, but slower than normal. We are investigating and will post an update shortly.
- resolved Aug 13, 2026, 04:54 PM UTC
This is resolved. The cause was a Redis connection issue, which we have fixed. Extract and Split latency is back to normal. Thank you for your patience.
Minor July 28, 2026 Investigating latency in EU 1h 32m Extraction
Started Jul 28, 2026, 01:46 PM UTC· resolved Jul 28, 2026, 03:18 PM UTC
- investigating Jul 28, 2026, 01:46 PM UTC
We are investigating increased latency for jobs hitting our EU endpoint
- resolved Jul 28, 2026, 03:18 PM UTC
We identified all related bottlenecks and have deployed a hardened version of our API. We are seeing recovery on our end.
Minor July 23, 2026 Elevated failures on OCR-dependent Parse/Extract requests 5h 8m Parsing, Extraction
Started Jul 23, 2026, 12:34 PM UTC· resolved Jul 23, 2026, 05:43 PM UTC
- identified Jul 23, 2026, 12:34 PM UTC
We are seeing elevated failures on a subset of parse and extraction requests which touch an upstream cloud depednency and are actively mitigating.
- identified Jul 23, 2026, 01:29 PM UTC
We've implemented a rough fallback due to the Google Cloud side service disruption causing a subset of requests to fail. We are no longer seeing failing requests. There may be some accuracy degradation for multi-lingual document processing and rotated documents until the root cause is resolved.
- identified Jul 23, 2026, 03:39 PM UTC
Multilingual parsing is good now ✅ Some documents with rotations may have degraded accuracy. EU endpoint has an elevated failure rate and we're deploying a fix there now. We're continuing to be in touch with Google Cloud to restore traffic away from fallbacks ASAP.
- monitoring Jul 23, 2026, 04:58 PM UTC
GCP has rectified the issue and our fallbacks have started to disengage. We're seeing systems start to be healthy again but are continuing to monitor.
- resolved Jul 23, 2026, 05:43 PM UTC
This incident is now resolved. The upstream Google Cloud Vision OCR degradation recovered at approximately 09:48 PT / 16:48 UTC. Our fallback OCR paths have fully disengaged, error rates have returned to baseline, and Parse/Extract requests are operating normally. We will continue to monitor. Thank you for your patience.
Minor June 26, 2026 High Latency and Degraded API Performance 2h 16m Parsing
Started Jun 26, 2026, 01:44 AM UTC· resolved Jun 26, 2026, 04:01 AM UTC
- investigating Jun 26, 2026, 01:44 AM UTC
Parse jobs might experience higher latency and degradation. We are actively investigating.
- monitoring Jun 26, 2026, 02:53 AM UTC
The issue looks like it's resolved and we are monitoring it.
- resolved Jun 26, 2026, 04:01 AM UTC
all systems operational
Minor June 24, 2026 Elevated Latency on API 4h 15m Parsing, Extraction
Started Jun 24, 2026, 05:42 PM UTC· resolved Jun 24, 2026, 09:57 PM UTC
- investigating Jun 24, 2026, 05:42 PM UTC
Investigating elevated latency on API
- monitoring Jun 24, 2026, 06:06 PM UTC
We are seeing services fully recovered, will continue to monitor for a short period to verify.
- monitoring Jun 24, 2026, 08:33 PM UTC
all systems operational
- resolved Jun 24, 2026, 09:57 PM UTC
all systems operational
Minor June 23, 2026 Studio degraded/unavailable 11m Studio
Started Jun 23, 2026, 06:07 PM UTC· resolved Jun 23, 2026, 06:18 PM UTC
- investigating Jun 23, 2026, 06:07 PM UTC
We're aware of an issue affecting Reducto Studio and are actively investigating. Some users may be unable to access the product or experience errors. We'll post an update within 30 minutes.
- investigating Jun 23, 2026, 06:11 PM UTC
Studio is currently impacted due to an upstream vendor outage (Convex)
- resolved Jun 23, 2026, 06:18 PM UTC
Resolved - Convex service is restored
Minor June 23, 2026 Vendor Service Degredation 1h 42m Parsing
Started Jun 23, 2026, 11:28 AM UTC· resolved Jun 23, 2026, 01:10 PM UTC
- investigating Jun 23, 2026, 11:28 AM UTC
API requests are 5xx’ing because containers are failing to spin up. Vendor is undergoing service degradation.
- resolved Jun 23, 2026, 01:10 PM UTC
Requests to the Triton Inference Endpoint in Modal entered an unstable event loop with 5xx request failures. We spun down the container and launched several more restoring the appropriate number of pods so the system is stable. The system is operational again.
Minor June 16, 2026 Elevated endpoint latency 38m Parsing, Extraction
Started Jun 16, 2026, 05:16 PM UTC· resolved Jun 16, 2026, 05:54 PM UTC
- investigating Jun 16, 2026, 05:16 PM UTC
Upstream inference provider is experiencing partial outage leading to elevated latency
- identified Jun 16, 2026, 05:28 PM UTC
The upstream inference provider is showing initial signs of recovery. We continue to process the backlog of jobs submitted.
- monitoring Jun 16, 2026, 05:32 PM UTC
Backlog of jobs should now be processed. We continue to monitor the queue to ensure optimal latency with inference.
- resolved Jun 16, 2026, 05:54 PM UTC
Services should now be fully restored.
Minor June 11, 2026 Degraded performance on parse with use_checkboxes 4m Parsing
Started Jun 11, 2026, 08:43 PM UTC· resolved Jun 11, 2026, 08:47 PM UTC
- investigating Jun 11, 2026, 08:43 PM UTC
/parse with config use_checkboxes set to true are failing
- identified Jun 11, 2026, 08:43 PM UTC
identified and reverting deploy
- monitoring Jun 11, 2026, 08:44 PM UTC
monitoring fix
- resolved Jun 11, 2026, 08:47 PM UTC
recovered - a portion of parse requests from 1330-1343 PST failed, all operational now
Minor June 9, 2026 Degraded performance on ocr_system = legacy 1h 30m Parsing
Started Jun 09, 2026, 10:10 PM UTC· resolved Jun 09, 2026, 11:41 PM UTC
- investigating Jun 09, 2026, 10:10 PM UTC
Requests that set ocr_system = legacy in the v3 config, or ocr_system = highres in the v2 config are experiencing increased latency / transient errors
- monitoring Jun 09, 2026, 10:33 PM UTC
Latency back to normal for legacy ocr service, monitoring
- resolved Jun 09, 2026, 11:41 PM UTC
All services functional
Minor June 5, 2026 Queue saturation in US processing 1h 1m Parsing, Studio, Extraction
Started Jun 05, 2026, 02:24 PM UTC· resolved Jun 05, 2026, 03:25 PM UTC
- identified Jun 05, 2026, 02:24 PM UTC
Degraded performance due to queue saturation on US processing.
- resolved Jun 05, 2026, 03:25 PM UTC
Resolved queue saturation incident.
Minor June 3, 2026 Elevated failure rate with upstream inference provider 2h 40m Parsing, Extraction
Started Jun 03, 2026, 01:12 PM UTC· resolved Jun 03, 2026, 03:53 PM UTC
- investigating Jun 03, 2026, 01:12 PM UTC
We’re seeing an increase in failures and latency. Investigating now.
- identified Jun 03, 2026, 01:32 PM UTC
We identified an issue with our GPU cloud subprocessor. We have engaged our emergency fallback inference system and are seeing initial recovery albeit with degraded performance.
- monitoring Jun 03, 2026, 03:40 PM UTC
Inference provider fallbacks were put in place for short-term mitigation. We're seeing complete recovery across all endpoints
- resolved Jun 03, 2026, 03:53 PM UTC
All endpoints should now be working as expected. All upstream provider issues are now resolved.
- resolved Jun 03, 2026, 03:53 PM UTC
All endpoints should now be working as expected. All upstream provider issues are now resolved.
Minor May 21, 2026 Elevated Failure Rate 8m Parsing, Studio, Extraction
Started May 21, 2026, 05:07 PM UTC· resolved May 21, 2026, 05:15 PM UTC
- identified May 21, 2026, 05:07 PM UTC
Investigating elevated failure rates.
- resolved May 21, 2026, 05:15 PM UTC
Fully mitigated.
Minor May 20, 2026 Rolling deploy caused transient failures 8m Parsing, Studio, Extraction
Started May 20, 2026, 08:30 PM UTC· resolved May 20, 2026, 08:38 PM UTC
- identified May 20, 2026, 08:30 PM UTC
Rolling deploy started causing transient failures due to a change in contract boundary between two systems.
- resolved May 20, 2026, 08:38 PM UTC
Fully resolved.
Minor May 19, 2026 Degraded Split and Extract Endpoints 1h 47m Parsing, Extraction
Started May 19, 2026, 01:50 PM UTC· resolved May 19, 2026, 03:38 PM UTC
- investigating May 19, 2026, 01:50 PM UTC
We’ve seen an uptick in errors for our /split endpoints and are looking into upstream service errors
- identified May 19, 2026, 01:52 PM UTC
We’ve identified downtime from our upstream cloud provider and are working with their team for prompt mitigations.
- identified May 19, 2026, 02:00 PM UTC
Degraded parse latency due to issues with an infrastructure provider
- resolved May 19, 2026, 03:38 PM UTC
all systems operational
Minor May 8, 2026 Investigating degraded performance on Reducto's API 4h 1m Parsing, Extraction
Started May 08, 2026, 12:02 AM UTC· resolved May 08, 2026, 04:03 AM UTC
- investigating May 08, 2026, 12:02 AM UTC
Reducto's API is experiencing latency degradation due to a downstream cloud provider issue (https://status.modal.com/). We are investigating actively.
- monitoring May 08, 2026, 12:07 AM UTC
The cloud provider remediated the issue and we are monitoring. https://status.modal.com/incident/890522
- monitoring May 08, 2026, 12:48 AM UTC
Degraded performance, affected by AWS outage, monitoring.
- resolved May 08, 2026, 04:03 AM UTC
We are seeing full recovery.
Minor May 6, 2026 Investigating Elevated Error Rates 41m Parsing, Extraction
Started May 06, 2026, 10:43 PM UTC· resolved May 06, 2026, 11:24 PM UTC
- investigating May 06, 2026, 10:43 PM UTC
Investigating elevated error rates in EU region.
- monitoring May 06, 2026, 10:54 PM UTC
Errors have subsided. We're continuing to monitor to verify.
- resolved May 06, 2026, 11:24 PM UTC
Resolved.