- Detected by Pingoru
- Oct 01, 2026, 10:10 PM UTC
- Resolved
- Oct 01, 2026, 10:10 PM UTC
- Duration
- —
Affected: Parsing
Timeline · 2 updates
-
investigating Oct 01, 2026, 09:13 PM UTC
Status: Investigating We are investigating degraded performance on the Parse API in the EU region (eu.platform.reducto.ai). Only the EU region is affected. Affected components Parsing (Degraded performance)
-
resolved Oct 01, 2026, 10:10 PM UTC
Status: Resolved The Parse API in the EU region returned no errors after 21:18 UTC. This incident is resolved. Affected components Parsing (Operational)
Read the full incident report →
- Detected by Pingoru
- Oct 01, 2026, 09:00 PM UTC
- Resolved
- Oct 01, 2026, 09:00 PM UTC
- Duration
- —
Affected: Parsing
Timeline · 3 updates
-
investigating Oct 01, 2026, 07:07 PM UTC
Status: Investigating We are investigating degraded performance on the Parse API. Affected components Parsing (Degraded performance)
-
monitoring Oct 01, 2026, 08:02 PM UTC
Status: Monitoring An outage of our OCR service caused the degraded performance on the Parse API. The OCR service has recovered. We are monitoring the results. Affected components Parsing (Operational)
-
resolved Oct 01, 2026, 09:00 PM UTC
Status: Resolved The Parse API is fully recovered. This incident is resolved. Affected components Parsing (Operational)
Read the full incident report →
- Detected by Pingoru
- Sep 28, 2026, 08:09 PM UTC
- Resolved
- Sep 28, 2026, 08:09 PM UTC
- Duration
- —
Affected: Parsing
Timeline · 4 updates
-
investigating Sep 28, 2026, 03:05 AM UTC
Status: Investigating Parse requests are degraded. Only the /parse endpoint is affected. Extract, Split, and Edit are operating normally. We are investigating. Affected components Parsing (Degraded performance)
-
identified Sep 28, 2026, 03:22 AM UTC
Status: Identified 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. Affected components Parsing (Degraded performance)
-
monitoring Sep 28, 2026, 03:35 AM UTC
Status: Monitoring The GPU clusters are recovered, and Parse latency is back to normal. We are monitoring the results. Affected components Parsing (Operational)
-
resolved Sep 28, 2026, 08:09 PM UTC
Status: Resolved This incident is resolved. Parse latency has been normal since 8:35 PM PDT on September 27.
Read the full incident report →
- Detected by Pingoru
- Sep 16, 2026, 02:51 AM UTC
- Resolved
- Sep 16, 2026, 02:51 AM UTC
- Duration
- —
Timeline · 1 update
-
resolved Sep 16, 2026, 02:51 AM UTC
Status: Resolved This is resolved. Parse requests with embed_pdf_metadata set to true are operating normally.
Read the full incident report →
- Detected by Pingoru
- Sep 09, 2026, 11:33 PM UTC
- Resolved
- Sep 09, 2026, 11:33 PM UTC
- Duration
- —
Affected: Splitting
Timeline · 2 updates
-
investigating Sep 09, 2026, 11:22 PM UTC
Status: Investigating Deep Split experienced partial degradation beginning at 16:22 PDT on September 9. Impact was limited to Deep Split requests. Affected components Splitting (Degraded performance)
-
resolved Sep 09, 2026, 11:33 PM UTC
Status: Resolved 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. Affected components Splitting (Operational)
Read the full incident report →
- Detected by Pingoru
- Aug 18, 2026, 06:22 PM UTC
- Resolved
- Aug 18, 2026, 06:22 PM UTC
- Duration
- —
Affected: Parsing
Timeline · 2 updates
-
identified Aug 18, 2026, 04:52 PM UTC
Status: Identified Elevated latency for parse, due to an issue with one of our gpu clusters. We've identified the problem and are actively fixing it. Affected components Parsing (Degraded performance)
-
resolved Aug 18, 2026, 06:22 PM UTC
Status: Resolved 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. Affected components Parsing (Operational)
Read the full incident report →
- Detected by Pingoru
- Aug 18, 2026, 06:22 PM UTC
- Resolved
- Aug 18, 2026, 06:22 PM UTC
- Duration
- —
Affected: Extraction
Timeline · 3 updates
-
identified Aug 18, 2026, 04:13 PM UTC
Status: Identified Extract requests that use citations or confidence scores are seeing elevated latency. The cause is an issue with one of our GPU clusters. Affected components Extraction (Degraded performance)
-
monitoring Aug 18, 2026, 04:13 PM UTC
Status: Monitoring 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
Status: Resolved 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. Affected components Extraction (Operational)
Read the full incident report →
- Detected by Pingoru
- Aug 13, 2026, 06:10 PM UTC
- Resolved
- Aug 13, 2026, 06:10 PM UTC
- Duration
- —
Affected: Parsing
Timeline · 2 updates
-
investigating Aug 13, 2026, 05:40 PM UTC
Status: Investigating We are investigating elevated latency on the parse API. Some parse jobs take longer than normal to complete. Affected components Parsing (Degraded performance)
-
resolved Aug 13, 2026, 06:10 PM UTC
Status: Resolved We corrected a misconfiguration in our GPU inference fleet. Parse latency returned to normal levels. Affected components Parsing (Operational)
Read the full incident report →
- Detected by Pingoru
- Aug 13, 2026, 04:54 PM UTC
- Resolved
- Aug 13, 2026, 04:54 PM UTC
- Duration
- —
Affected: ExtractionSplitting
Timeline · 2 updates
-
investigating Aug 13, 2026, 04:31 PM UTC
Status: Investigating 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. Affected components Extraction (Degraded performance) Splitting (Degraded performance)
-
resolved Aug 13, 2026, 04:54 PM UTC
Status: Resolved 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. Affected components Extraction (Operational) Splitting (Operational)
Read the full incident report →
- Detected by Pingoru
- Jul 28, 2026, 03:18 PM UTC
- Resolved
- Jul 28, 2026, 03:18 PM UTC
- Duration
- —
Affected: Extraction
Timeline · 2 updates
-
investigating Jul 28, 2026, 01:46 PM UTC
Status: Investigating We are investigating increased latency for jobs hitting our EU endpoint Affected components Extraction (Degraded performance)
-
resolved Jul 28, 2026, 03:18 PM UTC
Status: Resolved We identified all related bottlenecks and have deployed a hardened version of our API. We are seeing recovery on our end. Affected components Extraction (Operational)
Read the full incident report →
- Detected by Pingoru
- Jul 23, 2026, 05:43 PM UTC
- Resolved
- Jul 23, 2026, 05:43 PM UTC
- Duration
- —
Affected: ParsingExtraction
Timeline · 5 updates
-
identified Jul 23, 2026, 12:34 PM UTC
Status: Identified We are seeing elevated failures on a subset of parse and extraction requests which touch an upstream cloud depednency and are actively mitigating. Affected components Parsing (Degraded performance) Extraction (Degraded performance)
-
identified Jul 23, 2026, 01:29 PM UTC
Status: Identified 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. Affected components Parsing (Degraded performance) Extraction (Degraded performance)
-
identified Jul 23, 2026, 03:39 PM UTC
Status: Identified 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. Affected components Extraction (Degraded performance) Parsing (Degraded performance)
-
monitoring Jul 23, 2026, 04:58 PM UTC
Status: Monitoring 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. Affected components Parsing (Operational) Extraction (Operational)
-
resolved Jul 23, 2026, 05:43 PM UTC
Status: Resolved 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. Affected components Parsing (Operational) Extraction (Operational)
Read the full incident report →
- Detected by Pingoru
- Jun 26, 2026, 04:01 AM UTC
- Resolved
- Jun 26, 2026, 04:01 AM UTC
- Duration
- —
Affected: Parsing
Timeline · 3 updates
-
investigating Jun 26, 2026, 01:44 AM UTC
Status: Investigating Parse jobs might experience higher latency and degradation. We are actively investigating. Affected components Parsing (Degraded performance)
-
monitoring Jun 26, 2026, 02:53 AM UTC
Status: Monitoring The issue looks like it's resolved and we are monitoring it. Affected components Parsing (Operational)
-
resolved Jun 26, 2026, 04:01 AM UTC
Status: Resolved all systems operational Affected components Parsing (Operational)
Read the full incident report →
- Detected by Pingoru
- Jun 24, 2026, 09:57 PM UTC
- Resolved
- Jun 24, 2026, 09:57 PM UTC
- Duration
- —
Affected: ParsingExtraction
Timeline · 4 updates
-
investigating Jun 24, 2026, 05:42 PM UTC
Status: Investigating Investigating elevated latency on API Affected components Parsing (Degraded performance) Extraction (Degraded performance)
-
monitoring Jun 24, 2026, 06:06 PM UTC
Status: Monitoring We are seeing services fully recovered, will continue to monitor for a short period to verify. Affected components Parsing (Operational) Extraction (Operational)
-
monitoring Jun 24, 2026, 08:33 PM UTC
Status: Monitoring all systems operational Affected components Parsing (Operational) Extraction (Operational)
-
resolved Jun 24, 2026, 09:57 PM UTC
Status: Resolved all systems operational Affected components Parsing (Operational) Extraction (Operational)
Read the full incident report →
- Detected by Pingoru
- Jun 23, 2026, 06:18 PM UTC
- Resolved
- Jun 23, 2026, 06:18 PM UTC
- Duration
- —
Affected: Studio
Timeline · 3 updates
-
investigating Jun 23, 2026, 06:07 PM UTC
Status: Investigating 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. Affected components Studio (Partial outage)
-
investigating Jun 23, 2026, 06:11 PM UTC
Status: Investigating Studio is currently impacted due to an upstream vendor outage (Convex) Affected components Studio (Full outage)
-
resolved Jun 23, 2026, 06:18 PM UTC
Status: Resolved Resolved - Convex service is restored Affected components Studio (Operational)
Read the full incident report →
- Detected by Pingoru
- Jun 23, 2026, 01:10 PM UTC
- Resolved
- Jun 23, 2026, 01:10 PM UTC
- Duration
- —
Affected: Parsing
Timeline · 2 updates
-
investigating Jun 23, 2026, 11:28 AM UTC
Status: Investigating API requests are 5xx’ing because containers are failing to spin up. Vendor is undergoing service degradation. Affected components Parsing (Partial outage)
-
resolved Jun 23, 2026, 01:10 PM UTC
Status: Resolved 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. Affected components Parsing (Operational)
Read the full incident report →
- Detected by Pingoru
- Jun 16, 2026, 05:54 PM UTC
- Resolved
- Jun 16, 2026, 05:54 PM UTC
- Duration
- —
Affected: ParsingExtraction
Timeline · 4 updates
-
investigating Jun 16, 2026, 05:16 PM UTC
Status: Investigating Upstream inference provider is experiencing partial outage leading to elevated latency Affected components Parsing (Degraded performance) Extraction (Degraded performance)
-
identified Jun 16, 2026, 05:28 PM UTC
Status: Identified The upstream inference provider is showing initial signs of recovery. We continue to process the backlog of jobs submitted. Affected components Parsing (Degraded performance) Extraction (Degraded performance)
-
monitoring Jun 16, 2026, 05:32 PM UTC
Status: Monitoring Backlog of jobs should now be processed. We continue to monitor the queue to ensure optimal latency with inference. Affected components Parsing (Operational) Extraction (Operational)
-
resolved Jun 16, 2026, 05:54 PM UTC
Status: Resolved Services should now be fully restored. Affected components Parsing (Operational) Extraction (Operational)
Read the full incident report →
- Detected by Pingoru
- Jun 11, 2026, 08:47 PM UTC
- Resolved
- Jun 11, 2026, 08:47 PM UTC
- Duration
- —
Affected: Parsing
Timeline · 4 updates
-
investigating Jun 11, 2026, 08:43 PM UTC
Status: Investigating /parse with config use_checkboxes set to true are failing Affected components Parsing (Degraded performance)
-
identified Jun 11, 2026, 08:43 PM UTC
Status: Identified identified and reverting deploy Affected components Parsing (Degraded performance)
-
monitoring Jun 11, 2026, 08:44 PM UTC
Status: Monitoring monitoring fix Affected components Parsing (Degraded performance)
-
resolved Jun 11, 2026, 08:47 PM UTC
Status: Resolved recovered - a portion of parse requests from 1330-1343 PST failed, all operational now Affected components Parsing (Operational)
Read the full incident report →
- Detected by Pingoru
- Jun 09, 2026, 11:41 PM UTC
- Resolved
- Jun 09, 2026, 11:41 PM UTC
- Duration
- —
Affected: Parsing
Timeline · 3 updates
-
investigating Jun 09, 2026, 10:10 PM UTC
Status: Investigating Requests that set ocr_system = legacy in the v3 config, or ocr_system = highres in the v2 config are experiencing increased latency / transient errors Affected components Parsing (Degraded performance)
-
monitoring Jun 09, 2026, 10:33 PM UTC
Status: Monitoring Latency back to normal for legacy ocr service, monitoring Affected components Parsing (Degraded performance)
-
resolved Jun 09, 2026, 11:41 PM UTC
Status: Resolved All services functional Affected components Parsing (Operational)
Read the full incident report →
- Detected by Pingoru
- Jun 05, 2026, 03:25 PM UTC
- Resolved
- Jun 05, 2026, 03:25 PM UTC
- Duration
- —
Affected: ParsingStudioExtraction
Timeline · 2 updates
-
identified Jun 05, 2026, 02:24 PM UTC
Status: Identified Degraded performance due to queue saturation on US processing. Affected components Parsing (Degraded performance) Extraction (Degraded performance) Studio (Operational)
-
resolved Jun 05, 2026, 03:25 PM UTC
Status: Resolved Resolved queue saturation incident. Affected components Parsing (Operational) Extraction (Operational) Studio (Operational)
Read the full incident report →
- Detected by Pingoru
- Jun 03, 2026, 03:53 PM UTC
- Resolved
- Jun 03, 2026, 03:53 PM UTC
- Duration
- —
Affected: ParsingExtraction
Timeline · 5 updates
-
investigating Jun 03, 2026, 01:12 PM UTC
Status: Investigating We’re seeing an increase in failures and latency. Investigating now. Affected components Parsing (Degraded performance) Extraction (Degraded performance)
-
identified Jun 03, 2026, 01:32 PM UTC
Status: Identified 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. Affected components Parsing (Degraded performance) Extraction (Degraded performance)
-
monitoring Jun 03, 2026, 03:40 PM UTC
Status: Monitoring Inference provider fallbacks were put in place for short-term mitigation. We're seeing complete recovery across all endpoints Affected components Extraction (Degraded performance) Parsing (Degraded performance)
-
resolved Jun 03, 2026, 03:53 PM UTC
Status: Resolved All endpoints should now be working as expected. All upstream provider issues are now resolved. Affected components Parsing (Operational) Extraction (Operational)
-
resolved Jun 03, 2026, 03:53 PM UTC
Status: Resolved All endpoints should now be working as expected. All upstream provider issues are now resolved. Affected components Extraction (Operational) Parsing (Operational)
Read the full incident report →
- Detected by Pingoru
- May 21, 2026, 05:15 PM UTC
- Resolved
- May 21, 2026, 05:15 PM UTC
- Duration
- —
Affected: ParsingStudioExtraction
Timeline · 2 updates
-
identified May 21, 2026, 05:07 PM UTC
Status: Identified Investigating elevated failure rates. Affected components Parsing (Degraded performance) Extraction (Degraded performance) Studio (Operational)
-
resolved May 21, 2026, 05:15 PM UTC
Status: Resolved Fully mitigated. Affected components Parsing (Operational) Extraction (Operational) Studio (Operational)
Read the full incident report →
- Detected by Pingoru
- May 20, 2026, 08:38 PM UTC
- Resolved
- May 20, 2026, 08:38 PM UTC
- Duration
- —
Affected: ParsingStudioExtraction
Timeline · 2 updates
-
identified May 20, 2026, 08:30 PM UTC
Status: Identified Rolling deploy started causing transient failures due to a change in contract boundary between two systems. Affected components Parsing (Degraded performance) Extraction (Degraded performance) Studio (Operational)
-
resolved May 20, 2026, 08:38 PM UTC
Status: Resolved Fully resolved. Affected components Parsing (Operational) Extraction (Operational) Studio (Operational)
Read the full incident report →
- Detected by Pingoru
- May 19, 2026, 03:38 PM UTC
- Resolved
- May 19, 2026, 03:38 PM UTC
- Duration
- —
Affected: ParsingExtraction
Timeline · 4 updates
-
investigating May 19, 2026, 01:50 PM UTC
Status: Investigating We’ve seen an uptick in errors for our /split endpoints and are looking into upstream service errors Affected components Extraction (Degraded performance)
-
identified May 19, 2026, 01:52 PM UTC
Status: Identified We’ve identified downtime from our upstream cloud provider and are working with their team for prompt mitigations. Affected components Extraction (Degraded performance)
-
identified May 19, 2026, 02:00 PM UTC
Status: Identified Degraded parse latency due to issues with an infrastructure provider Affected components Parsing (Degraded performance) Extraction (Operational)
-
resolved May 19, 2026, 03:38 PM UTC
Status: Resolved all systems operational Affected components Parsing (Operational) Extraction (Operational)
Read the full incident report →
- Detected by Pingoru
- May 08, 2026, 04:03 AM UTC
- Resolved
- May 08, 2026, 04:03 AM UTC
- Duration
- —
Affected: ParsingExtraction
Timeline · 4 updates
-
investigating May 08, 2026, 12:02 AM UTC
Status: Investigating Reducto's API is experiencing latency degradation due to a downstream cloud provider issue (https://status.modal.com/). We are investigating actively. Affected components Parsing (Degraded performance) Extraction (Degraded performance)
-
monitoring May 08, 2026, 12:07 AM UTC
Status: Monitoring The cloud provider remediated the issue and we are monitoring. https://status.modal.com/incident/890522 Affected components Parsing (Operational) Extraction (Operational)
-
monitoring May 08, 2026, 12:48 AM UTC
Status: Monitoring Degraded performance, affected by AWS outage, monitoring. Affected components Parsing (Degraded performance) Extraction (Degraded performance)
-
resolved May 08, 2026, 04:03 AM UTC
Status: Resolved We are seeing full recovery. Affected components Extraction (Operational) Parsing (Operational)
Read the full incident report →
- Detected by Pingoru
- May 06, 2026, 11:24 PM UTC
- Resolved
- May 06, 2026, 11:24 PM UTC
- Duration
- —
Affected: ParsingExtraction
Timeline · 3 updates
-
investigating May 06, 2026, 10:43 PM UTC
Status: Investigating Investigating elevated error rates in EU region. Affected components Parsing (Partial outage) Extraction (Partial outage)
-
monitoring May 06, 2026, 10:54 PM UTC
Status: Monitoring Errors have subsided. We're continuing to monitor to verify. Affected components Parsing (Operational) Extraction (Operational)
-
resolved May 06, 2026, 11:24 PM UTC
Status: Resolved Resolved. Affected components Parsing (Operational) Extraction (Operational)
Read the full incident report →
