Outage history

Runway Outage History

Recent incidents Runway has published, newest first, with how long each one lasted.

3in the last 30 days
6in the last 90 days
23h 5mlongest outage
28 Aug 2026most recent

Showing 40 published incidents back to 20 Oct 2025.

  1. Minor28 Aug 20261h 24m

    Aleph delayed generations

  2. Minor19 Aug 20261h

    Gen4.5 Image to Video is Degraded

  3. Minor19 Aug 20261h 7m

    Increased ratio of Seedance safety system false positives

  4. Minor13 Aug 202613 min

    We've identified a problem and are working on a fix

  5. Critical10 Jul 20261h

    We've identified a problem and are working on a fix

  6. Informational8 Jul 202623 min

    Aleph 2.0 delayed generations

  7. Minor5 Jun 20264h

    We've identified a problem with Nano Banana generations and are working on a fix

  8. Minor3 Jun 20261h 31m

    We've identified a problem with generations and are working on a fix

  9. Major3 Jun 202619 min

    Issues with Seedance and Seedream generations

  10. Minor1 Jun 202621 min

    We've identified an issue with Veo 3.1 generations and are working on fixing it

  11. Minor28 May 202639 min

    We've identified a problem with Veo 3.1 generations and are working on a fix

  12. Minor27 May 202633 min

    We've identified a problem with Seedance and working on a fix

  13. Minor25 May 202630 min

    Issues with GPT Image 2 image generation

  14. Minor25 May 20262h 48m

    We are aware of issues affecting video generation with Veo 3.1

  15. Major13 May 20264h 21m

    We've identified a problem and are working on a fix

  16. Minor13 May 202655 min

    We've identified a problem and are working on a fix

  17. Informational11 May 20265h 57m

    Seedance 2 and Kling generations are delayed

  18. Major22 Apr 20261h 42m

    Issues with Seedance 2.0 generations

  19. Major21 Apr 202641 min

    We have released a fix.

  20. Minor14 Apr 20262h 43m

    We've identified a problem and are working on a fix

  21. Minor13 Apr 20261h 30m

    We've identified a problem and are working on a fix

  22. Minor3 Apr 20261h 33m

    We've spotted an issue with the Gemini Nano Banana Pro image model

  23. Minor17 Mar 20262h 20m

    High queue wait times for Gen 4.5 image-to-video

  24. Minor26 Feb 202614 min

    Gen3 Alpha Turbo generations are taking longer than normal

  25. Minor25 Feb 202642 min

    We've identified a problem and are working on a fix

  26. Major25 Feb 202633 min

    We've identified a problem and are working on a fix

  27. Minor18 Feb 20265h 5m

    Issues with Gemini 3 Pro (Nano Banana Pro) generations

  28. Critical16 Feb 202647 min

    Tasks cannot be created

  29. Major10 Feb 20262h 20m

    Issues with Nano Banana Pro generations

  30. Major9 Feb 20262h 17m

    Issues with Nano Banana Pro generations

  31. Major28 Jan 202653 min

    Increased error rate in Veo 3 and Veo 3,.1 generations

  32. Major21 Jan 20262h 33m

    Issues with Gemini 3 Pro image generations

  33. Minor18 Jan 20261h 49m

    Increased Gen 4.5 wait times

  34. Minor2 Jan 202610h 52m

    Video upscale tasks cannot be started

  35. Critical23 Dec 202511 min

    Unable to start new tasks

  36. Major12 Dec 20252h 38m

    Issues affecting Aleph generations

  37. Major5 Dec 20251h 15m

    Significant delays in asset generation

  38. Minor20 Nov 202523h 5m

    Intermittent issues with Veo 3.1 generations.

  39. Minor12 Nov 20253h 19m

    Image generation model performance is degraded

  40. Major20 Oct 20252h 18m

    We've identified a problem and are working on a fix

What this record shows

Runway reports separately on the app, the backend that runs generations, billing and the public API, so an entry below usually names one of those rather than describing a total outage.

As with any generative video tool, this list will not capture the complaint users have most often. A generation stuck in the queue is capacity doing its job, not a fault, and it is never recorded as downtime.

Billing entries are worth reading separately from the rest. Credit problems do not resolve when an outage clears, because nothing was broken in the first place.

How to read the durations

Each entry runs from when Video AI opened the incident to when it was marked resolved. That is a generous measure: an incident is usually opened once the problem is confirmed and closed after it has been stable for a while, so the window is wider than the period in which most people were actually affected.

Severity comes from the provider. Only major and critical entries count against the uptime figure on the Runway status page, because a minor incident normally means degraded performance for some users rather than the service being unavailable.

This list is limited to what the provider has published and still exposes. Providers cap how far their public feed reaches, so an empty stretch further back means the record has aged out, not that nothing happened.

🔗 Keep checking