Reducto Outage History

Reducto is up right now

Reducto had 36 outages in the last 2 years totaling 48h 29m of downtime — averaging 1.5 incidents per month.

There were 36 Reducto outages since August 7, 2025 totaling 48h 29m of downtime. Each is summarised below — incident details, duration, and resolution information.

Source: https://status.reducto.ai

Minor June 16, 2026

Elevated endpoint latency

Detected by Pingoru
Jun 16, 2026, 05:54 PM UTC
Resolved
Jun 16, 2026, 05:54 PM UTC
Duration
Affected: ParsingExtraction
Timeline · 4 updates
  1. 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)

  2. 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)

  3. 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)

  4. 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 →

Minor June 11, 2026

Degraded performance on parse with use_checkboxes

Detected by Pingoru
Jun 11, 2026, 08:47 PM UTC
Resolved
Jun 11, 2026, 08:47 PM UTC
Duration
Affected: Parsing
Timeline · 4 updates
  1. 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)

  2. identified Jun 11, 2026, 08:43 PM UTC

    Status: Identified identified and reverting deploy Affected components Parsing (Degraded performance)

  3. monitoring Jun 11, 2026, 08:44 PM UTC

    Status: Monitoring monitoring fix Affected components Parsing (Degraded performance)

  4. 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 →

Minor June 9, 2026

Degraded performance on ocr_system = legacy

Detected by Pingoru
Jun 09, 2026, 11:41 PM UTC
Resolved
Jun 09, 2026, 11:41 PM UTC
Duration
Affected: Parsing
Timeline · 3 updates
  1. 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)

  2. monitoring Jun 09, 2026, 10:33 PM UTC

    Status: Monitoring Latency back to normal for legacy ocr service, monitoring Affected components Parsing (Degraded performance)

  3. resolved Jun 09, 2026, 11:41 PM UTC

    Status: Resolved All services functional Affected components Parsing (Operational)

Read the full incident report →

Minor June 5, 2026

Queue saturation in US processing

Detected by Pingoru
Jun 05, 2026, 03:25 PM UTC
Resolved
Jun 05, 2026, 03:25 PM UTC
Duration
Affected: ParsingStudioExtraction
Timeline · 2 updates
  1. 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)

  2. 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 →

Minor June 3, 2026

Elevated failure rate with upstream inference provider

Detected by Pingoru
Jun 03, 2026, 03:53 PM UTC
Resolved
Jun 03, 2026, 03:53 PM UTC
Duration
Affected: ParsingExtraction
Timeline · 5 updates
  1. 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)

  2. 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)

  3. 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)

  4. 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)

  5. 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 →

Minor May 21, 2026

Elevated Failure Rate

Detected by Pingoru
May 21, 2026, 05:15 PM UTC
Resolved
May 21, 2026, 05:15 PM UTC
Duration
Affected: ParsingStudioExtraction
Timeline · 2 updates
  1. identified May 21, 2026, 05:07 PM UTC

    Status: Identified Investigating elevated failure rates. Affected components Parsing (Degraded performance) Extraction (Degraded performance) Studio (Operational)

  2. 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 →

Minor May 20, 2026

Rolling deploy caused transient failures

Detected by Pingoru
May 20, 2026, 08:38 PM UTC
Resolved
May 20, 2026, 08:38 PM UTC
Duration
Affected: ParsingStudioExtraction
Timeline · 2 updates
  1. 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)

  2. 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 →

Minor May 19, 2026

Degraded Split and Extract Endpoints

Detected by Pingoru
May 19, 2026, 03:38 PM UTC
Resolved
May 19, 2026, 03:38 PM UTC
Duration
Affected: ParsingExtraction
Timeline · 4 updates
  1. 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)

  2. 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)

  3. 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)

  4. resolved May 19, 2026, 03:38 PM UTC

    Status: Resolved all systems operational Affected components Parsing (Operational) Extraction (Operational)

Read the full incident report →

Minor May 8, 2026

Investigating degraded performance on Reducto's API

Detected by Pingoru
May 08, 2026, 04:03 AM UTC
Resolved
May 08, 2026, 04:03 AM UTC
Duration
Affected: ParsingExtraction
Timeline · 4 updates
  1. 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)

  2. 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)

  3. 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)

  4. 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 →

Minor May 6, 2026

Investigating Elevated Error Rates

Detected by Pingoru
May 06, 2026, 11:24 PM UTC
Resolved
May 06, 2026, 11:24 PM UTC
Duration
Affected: ParsingExtraction
Timeline · 3 updates
  1. 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)

  2. 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)

  3. resolved May 06, 2026, 11:24 PM UTC

    Status: Resolved Resolved. Affected components Parsing (Operational) Extraction (Operational)

Read the full incident report →

Minor May 6, 2026

Rolling deploy caused transient errors

Detected by Pingoru
May 06, 2026, 10:00 PM UTC
Resolved
May 06, 2026, 10:00 PM UTC
Duration
Affected: ParsingStudioExtraction
Timeline · 2 updates
  1. identified May 06, 2026, 09:41 PM UTC

    Status: Identified Rolling deployment started. We started observing transient failures during the deploy process. Affected components Extraction (Partial outage) Studio (Operational) Parsing (Partial outage)

  2. resolved May 06, 2026, 10:00 PM UTC

    Status: Resolved Changes were rolled back and error rate dropped to normal rates. Affected components Studio (Operational) Parsing (Operational) Extraction (Operational)

Read the full incident report →

Minor April 8, 2026

Partially degraded Studio inferences

Detected by Pingoru
Apr 08, 2026, 06:28 PM UTC
Resolved
Apr 08, 2026, 06:28 PM UTC
Duration
Affected: Studio
Timeline · 3 updates
  1. identified Apr 08, 2026, 06:18 PM UTC

    Status: Identified We've identified an issue that is impacting fetching inference results on Studio. Affected components Studio (Degraded performance)

  2. monitoring Apr 08, 2026, 06:22 PM UTC

    Status: Monitoring We've deployed a fix for runs and are continuing to monitor. Affected components Studio (Degraded performance)

  3. resolved Apr 08, 2026, 06:28 PM UTC

    Status: Resolved All Studio runs should now be successful. Affected components Studio (Operational)

Read the full incident report →

Minor March 4, 2026

Backend Vendor reporting major outage

Detected by Pingoru
Mar 04, 2026, 06:36 PM UTC
Resolved
Mar 04, 2026, 06:36 PM UTC
Duration
Affected: ParsingStudioExtraction
Timeline · 3 updates
  1. monitoring Mar 04, 2026, 05:33 PM UTC

    Status: Monitoring Our Backend vendor is reporting high error rates, impacting our Studio experience. We are monitoring the situation, and will update when resolved Affected components Studio (Full outage)

  2. monitoring Mar 04, 2026, 05:42 PM UTC

    Status: Monitoring /pipeline invocation and Studio severely impacted - Backend vendor reporting major outage Affected components Parsing (Degraded performance) Extraction (Degraded performance) Studio (Full outage)

  3. resolved Mar 04, 2026, 06:36 PM UTC

    Status: Resolved backend incident no longer affecting product experience or /pipeline invocation Affected components Parsing (Operational) Extraction (Operational) Studio (Operational)

Read the full incident report →

Minor February 13, 2026

temporary outage

Detected by Pingoru
Feb 13, 2026, 10:40 PM UTC
Resolved
Feb 13, 2026, 10:40 PM UTC
Duration
Timeline · 2 updates
  1. monitoring Feb 13, 2026, 10:38 PM UTC

    Status: Monitoring a portion of jobs between 14:27-14:32 PST failed. All services are operational now

  2. resolved Feb 13, 2026, 10:40 PM UTC

    Status: Resolved all services are operational now

Read the full incident report →

Minor February 12, 2026

degraded latency

Detected by Pingoru
Feb 12, 2026, 08:31 PM UTC
Resolved
Feb 12, 2026, 08:31 PM UTC
Duration
Affected: ParsingExtraction
Timeline · 3 updates
  1. investigating Feb 12, 2026, 05:17 PM UTC

    Status: Investigating increased latency, unknown cause for now Affected components Parsing (Degraded performance) Extraction (Degraded performance)

  2. monitoring Feb 12, 2026, 06:47 PM UTC

    Status: Monitoring We are monitoring the resolution. Affected components Extraction (Degraded performance) Parsing (Degraded performance)

  3. resolved Feb 12, 2026, 08:31 PM UTC

    Status: Resolved We've root caused and resolved database issues. Services are fully operational. Affected components Parsing (Operational) Extraction (Operational)

Read the full incident report →

Minor January 30, 2026

elevated timeouts on a subset of jobs

Detected by Pingoru
Jan 30, 2026, 11:00 PM UTC
Resolved
Jan 30, 2026, 11:00 PM UTC
Duration
Affected: ParsingExtraction
Timeline · 3 updates
  1. investigating Jan 30, 2026, 10:07 PM UTC

    Status: Investigating The team is investigating timeouts Affected components Parsing (Degraded performance) Extraction (Degraded performance)

  2. monitoring Jan 30, 2026, 10:48 PM UTC

    Status: Monitoring All services back up, the team will continue monitoring Affected components Parsing (Operational) Extraction (Operational)

  3. resolved Jan 30, 2026, 11:00 PM UTC

    Status: Resolved All services back to normal Affected components Parsing (Operational) Extraction (Operational)

Read the full incident report →

Minor January 30, 2026

Investigating elevated failure rates on the API

Detected by Pingoru
Jan 30, 2026, 08:10 PM UTC
Resolved
Jan 30, 2026, 08:10 PM UTC
Duration
Affected: ParsingExtraction
Timeline · 3 updates
  1. investigating Jan 30, 2026, 03:04 AM UTC

    Status: Investigating Investigating elevated failure rates. Affected components Parsing (Partial outage) Extraction (Partial outage)

  2. monitoring Jan 30, 2026, 03:13 AM UTC

    Status: Monitoring We've identified the issue and deployed a fix. We are monitoring to ensure systems are healthy. Affected components Extraction (Operational) Parsing (Operational)

  3. resolved Jan 30, 2026, 08:10 PM UTC

    Status: Resolved We haven't observed any additional failures. Affected components Parsing (Operational) Extraction (Operational)

Read the full incident report →