Runware Outage History

Runware is up right now

Pingoru has recorded 19 incidents for Runware: 19 in the last 12 months and 18 in the last 90 days.

Source: status.runware.ai

19incidents recorded
19last 12 months
18last 90 days
5 hourstypical duration

Incidents, newest first

Minor October 19, 2026 Increased traffic on Z-Image Turbo Models 1h 4m

Started Oct 19, 2026, 03:46 PM UTC· resolved Oct 19, 2026, 04:51 PM UTC

  1. monitoring Oct 19, 2026, 03:46 PM UTC

    Increased load and slower than normal response times on Z-Image Turbo family of models.

  2. resolved Oct 19, 2026, 04:51 PM UTC

    Queue wait times have been resolved. Some requests may return HTTP Error 429, but that is temporary and should self-resolve.

Read the full incident report →

Minor October 7, 2026 Compute Capacity Degradation Due to Vendor Network Issue 1h 38m Official Models

Started Oct 07, 2026, 07:14 PM UTC· resolved Oct 07, 2026, 08:52 PM UTC

  1. identified Oct 07, 2026, 07:14 PM UTC

    One of our infrastructure vendors is currently experiencing network issues, which has caused some of our compute capacity to become unavailable. We are actively migrating affected workloads to alternative infrastructure to restore full capacity as quickly as possible. We apologise for the disruption and appreciate your patience while we work to fully resolve the issue.

  2. identified Oct 07, 2026, 07:16 PM UTC

    One of our infrastructure vendors is currently experiencing network issues, which has caused some of our compute capacity to become unavailable. We are actively migrating affected workloads to alternative infrastructure to restore full capacity as quickly as possible. We apologise for the disruption and appreciate your patience while we work to fully resolve the issue.

  3. monitoring Oct 07, 2026, 07:59 PM UTC

    Network issue has been resolved, we are monitoring the queues until they are drained

  4. resolved Oct 07, 2026, 08:52 PM UTC

    Incident has been resolved, thank you for your patience.

Read the full incident report →

Minor September 28, 2026 Degraded performance of FLUX.1 [dev] 3h 32m

Started Sep 28, 2026, 04:30 PM UTC· resolved Sep 28, 2026, 08:03 PM UTC

  1. identified Sep 28, 2026, 04:30 PM UTC

    We are experiencing high load and slower than normal response times on FLUX.1 [dev] models.

  2. resolved Sep 28, 2026, 08:03 PM UTC

    Degraded service resolved for FLUX.1 [dev]

Read the full incident report →

Minor September 22, 2026 Fast-flux increased traffic 29m Official Models

Started Sep 22, 2026, 12:47 PM UTC· resolved Sep 22, 2026, 01:17 PM UTC

  1. identified Sep 22, 2026, 12:47 PM UTC

    We have increased traffic towards the flux.1-dev model. We' are adjusting the consumers to satisfy the demand.

  2. monitoring Sep 22, 2026, 12:59 PM UTC

    Additional consumers joined the queue. The queue is stabilising; we will continue to monitor it a little longer.

  3. resolved Sep 22, 2026, 01:17 PM UTC

    Incident has been resolved

Read the full incident report →

Minor September 13, 2026 Flux2Klein models increased response times 10m Official Models

Started Sep 13, 2026, 07:31 AM UTC· resolved Sep 13, 2026, 07:42 AM UTC

  1. identified Sep 13, 2026, 07:31 AM UTC

    We've identified the source of the problem, and we are working on a fix. We'll keep you posted as soon as possible.

  2. resolved Sep 13, 2026, 07:42 AM UTC

    The issue has been resolved. Queues are back to normal; requests are being processed.

Read the full incident report →

Minor September 10, 2026 Seedance 2.5 – Elevated Generation Latency 2d 19h API, API

Started Sep 10, 2026, 07:21 PM UTC· resolved Sep 13, 2026, 03:20 PM UTC

  1. identified Sep 10, 2026, 07:21 PM UTC

    We’re aware of elevated latency on Seedance 2.5 due to capacity constraints with our upstream video generation provider. This is affecting generation times. We’re actively working with the provider to get this resolved and will share updates as we have them..

  2. monitoring Sep 11, 2026, 11:33 AM UTC

    We've seen a meaningful improvement in Seedance 2.5 generation latency over the past several hours as we continue working with our upstream provider. Performance is trending back toward normal levels.

  3. resolved Sep 13, 2026, 03:20 PM UTC

    We're continuing to monitor Seedance 2.5 performance. Generation times have improved and we'll keep watching closely.

Read the full incident report →

Minor September 9, 2026 Google Omni Flash 1.1 experiencing failures 55m Third-party Models

Started Sep 09, 2026, 04:35 PM UTC· resolved Sep 09, 2026, 05:30 PM UTC

  1. identified Sep 09, 2026, 04:35 PM UTC

    Google Omni Flash 1.1 is currently experiencing failures via up-stream Google services.

  2. resolved Sep 09, 2026, 05:30 PM UTC

    Google service looks to have restored back to normal.

Read the full incident report →

Minor August 25, 2026 High load for flux1-dev model 1h 5m Official Models

Started Aug 25, 2026, 01:36 PM UTC· resolved Aug 25, 2026, 02:41 PM UTC

  1. identified Aug 25, 2026, 01:36 PM UTC

    We are experiencing high load for flux1-dev model. Currently we are adding more servers to handle the load.

  2. monitoring Aug 25, 2026, 02:07 PM UTC

    The load is processing, should be resolved soon.

  3. resolved Aug 25, 2026, 02:41 PM UTC

    New consumers added, backlog resolved

Read the full incident report →

Minor August 24, 2026 GLM 5.2 experiencing degraded performance 2h 18m Official Models

Started Aug 24, 2026, 05:34 PM UTC· resolved Aug 24, 2026, 07:52 PM UTC

  1. monitoring Aug 24, 2026, 05:34 PM UTC

    GLM 5.2 is currently experiencing degraded performance due to increased demand.

  2. resolved Aug 24, 2026, 07:52 PM UTC

    "We updated routing to move Vercel traffic to our self-hosted capacity. The routing change is now working correctly, and Doubleword and our VLLM capacity are operating normally. "

Read the full incident report →

Minor August 10, 2026 Issue impacting Google, Byteplus and OpenAI models 1h Third-party Models

Started Aug 10, 2026, 01:30 AM UTC· resolved Aug 10, 2026, 02:31 AM UTC

  1. investigating Aug 10, 2026, 01:30 AM UTC

    We are investigating an issue impacting Google, Byteplus and OpenAI models at the moment.

  2. identified Aug 10, 2026, 02:05 AM UTC

    We've identified the root cause and a fix is being rolled out. Google, OpenAI and Byteplus models are stating to process inference.

  3. monitoring Aug 10, 2026, 02:10 AM UTC

    Fixed rolled out and inference confirmed as working. We are monitoring.

  4. resolved Aug 10, 2026, 02:31 AM UTC

    We've monitored for the last 30 minutes and the service has resumed with no further issues.

Read the full incident report →

Minor August 5, 2026 Some models may be slow in processing 51m Official Models

Started Aug 05, 2026, 09:08 PM UTC· resolved Aug 05, 2026, 09:59 PM UTC

  1. identified Aug 05, 2026, 09:08 PM UTC

    We're currently experiencing issues with models. Expect delays in processing

  2. monitoring Aug 05, 2026, 09:23 PM UTC

    The model performance is under monitoring right now. Team is working to be sure everything runs as it should.

  3. resolved Aug 05, 2026, 09:59 PM UTC

    Models performance has been stabilized.

Read the full incident report →

Minor August 5, 2026 Some of the models has degraded performance or timeouts 5h 7m Official Models

Started Aug 05, 2026, 01:19 PM UTC· resolved Aug 05, 2026, 06:26 PM UTC

  1. investigating Aug 05, 2026, 01:19 PM UTC

    We're currently experiencing issues with some of the models. Issue sits on the infrastructure side, so team now is investigating.

  2. identified Aug 05, 2026, 01:46 PM UTC

    The team is still investigating

  3. identified Aug 05, 2026, 02:36 PM UTC

    We've identified the issue with our third-party provider and now preparing the remediation.

  4. monitoring Aug 05, 2026, 03:26 PM UTC

    We’ve migrated some of the consumers to a stable location. Queues are back to normal, we will keep monitoring this incident for a while

  5. monitoring Aug 05, 2026, 03:51 PM UTC

    Some models are intermittently slow or timing out due to a network issue at one of our infrastructure providers. The issue comes in short bursts, and affected requests recover automatically once each burst passes. We are working with the provider on a fix and will post updates here.

  6. resolved Aug 05, 2026, 06:26 PM UTC

    The issue has been resolved. Thank you for the patience.

Read the full incident report →

Minor August 4, 2026 DeepSeek-V4-Pro vLLM issue 2h 5m Official Models

Started Aug 04, 2026, 03:58 PM UTC· resolved Aug 04, 2026, 06:04 PM UTC

  1. investigating Aug 04, 2026, 03:58 PM UTC

    We are experiencing a timeouts with DeepSeek-V4-Pro vLLM model. The team are investigating. Updates will follow.

  2. identified Aug 04, 2026, 04:28 PM UTC

    We've identified the issue and it is associated with an up-stream DC provider. The team now is working with to bring the GPU node back online.

  3. identified Aug 04, 2026, 04:44 PM UTC

    The provider still working on this issue Our team now is working to change the affected node

  4. identified Aug 04, 2026, 05:16 PM UTC

    The provider still hasn't fixed the node issue. Our team is finishing the node switch

  5. monitoring Aug 04, 2026, 05:30 PM UTC

    The node has been replaced. The model is currently starting. Expect delay 10-30 mins

  6. resolved Aug 04, 2026, 06:04 PM UTC

    The incident now has been resolved. The model DeepSeek-V4-Pro is now fully operational.

Read the full incident report →

Minor July 31, 2026 Flux2klein - degraded performance 27m Official Models

Started Jul 31, 2026, 05:38 PM UTC· resolved Jul 31, 2026, 06:06 PM UTC

  1. identified Jul 31, 2026, 05:38 PM UTC

    We have increased traffic towards flux-2-klein models. Adjusting the consumer capacity to match the traffic pattern.

  2. resolved Jul 31, 2026, 06:06 PM UTC

    queues are stable, we will continue to add consumers to the queue. Incident resolved.

Read the full incident report →

Minor July 30, 2026 performance degraded for qwen-2511 and flux2 model 48m Official Models

Started Jul 30, 2026, 02:36 PM UTC· resolved Jul 30, 2026, 03:25 PM UTC

  1. identified Jul 30, 2026, 02:36 PM UTC

    We've identified a spike in legitimate traffic towards these two models. We are working on adjusting the consumer capacity. Will provide another update shortly

  2. identified Jul 30, 2026, 03:12 PM UTC

    Qwen-2511 consumers are handling the increase traffic fine. We're still working on Flux2

  3. resolved Jul 30, 2026, 03:25 PM UTC

    Queue are green, consumers are processing tasks, incident resolved.

Read the full incident report →

Minor July 29, 2026 We are investigating increased timeout rates affecting Anthropic models 25m API, Website, Dashboard, Playground and 4 more

Started Jul 29, 2026, 09:20 PM UTC· resolved Jul 29, 2026, 09:45 PM UTC

  1. investigating Jul 29, 2026, 09:20 PM UTC

    We are investigating increased timeout rates affecting Anthropic models.

  2. identified Jul 29, 2026, 09:25 PM UTC

    The root cause has been identified and a fix is being implemented.

  3. monitoring Jul 29, 2026, 09:30 PM UTC

    We've implemented a fix and are monitoring.

  4. resolved Jul 29, 2026, 09:45 PM UTC

    The timeouts have been resolved.

Read the full incident report →

Minor July 29, 2026 Degraded performance on Klein models 46m Official Models

Started Jul 29, 2026, 06:41 AM UTC· resolved Jul 29, 2026, 07:27 AM UTC

  1. investigating Jul 29, 2026, 06:41 AM UTC

    We're seeing increased traffic aimed at Klein models. We are working on mitigating this

  2. monitoring Jul 29, 2026, 07:22 AM UTC

    Queues have been stabilized, consumers are handling the incoming traffic.

  3. resolved Jul 29, 2026, 07:27 AM UTC

    Additional consumers are managing the traffic, queues are clean, klein models are operational.

Read the full incident report →

Minor July 27, 2026 Degraded performance - klein models 17m Official Models

Started Jul 27, 2026, 03:49 PM UTC· resolved Jul 27, 2026, 04:06 PM UTC

  1. identified Jul 27, 2026, 03:49 PM UTC

    We're seeing increased traffic towards Klein models. Adjusting the consumer capacity to match the incoming traffic

  2. monitoring Jul 27, 2026, 03:54 PM UTC

    Queues have been stabilised, monitoring the Klein models, until the additional capacity finishes provisioning.

  3. resolved Jul 27, 2026, 04:06 PM UTC

    Consumers are healthy, queue is managing the traffic. Incident resolved.

Read the full incident report →

Minor July 23, 2026 Increased traffic affecting z-image-turbo model response times 38m Official Models

Started Jul 23, 2026, 08:07 AM UTC· resolved Jul 23, 2026, 08:45 AM UTC

  1. investigating Jul 23, 2026, 08:07 AM UTC

    We're seeing an increase in traffic towards z-image-turbo model. Adjusting the capacity

  2. identified Jul 23, 2026, 08:15 AM UTC

    We've identified that the traffic is legitim. Adjusting the consumer capacity at the moment. New consumers will join the queue shortly

  3. monitoring Jul 23, 2026, 08:37 AM UTC

    Consumer capacity has been adjusted to sustain the increase in traffic. Queue is stable, keep it under monitoring for a little longer. Service is operational

  4. resolved Jul 23, 2026, 08:45 AM UTC

    Traffic increase has been met with additional capacity. Queue is stable, service operational.

Read the full incident report →