Kling video generations failing or delayed
Kling video generations fail or take much longer than usual in the Runway App and Backend. The affected models are Kling 4.0, Kling 3.0 and Kling O3. Runway has identified an issue with its upstream provider and works on a fix. Runway recommends that you use a different video model until then.
State
Identified
Started
2 h ago
2026-11-02 16:53 UTC
Ongoing for
1 h 51 min
Worst impact
Degraded
Timeline
2 updatesInvestigating
46 min 41%
Identified
1 h 5 min 59%
Updates
Times in UTCAs posted by Runway
Since about 15:00 UTC, most video generations with Kling models are failing or taking much longer than usual. This affects Kling 4.0, Kling 3.0 (Standard, Pro, Turbo, 4K and Motion Control) and Kling O3 (Standard, Pro and 4K). Other video models are not affected. The cause is an issue with our upstream provider. We're working with them on a fix. Some generations have started completing again, but we don't expect normal performance yet. Until then, we recommend using a different video model. Generations that are still pending may complete late or fail.
We're seeing degraded performance for Kling 4.0 and 3.0 tasks.
Affected components
2Runway in the last 90 days
Full historyIncidents in 90 days
11
Days with an incident
10
Median duration
1 h 15 min
This incident
1.5× the median
Other Runway incidents
All incidentsRunway·We've identified a problem and are working on a fix
This incident has been resolved.
Runway·Magnific upscalers unavailable
This incident has been resolved. Magnific upscaling is working normally again
Runway·Scheduled Maintenance
Scheduled maintenance is complete, and all systems are operating normally.
Runway·We've identified a problem and are working on a fix
This incident has now been resolved.
Runway·Elevated Seedance moderation errors
We've spotted that something has gone wrong. We're currently investigating the issue, and will provide an update soon.
Follow Runway
Your coding agent knows when Runway is down, and tells you when a failure is theirs, not yours. You can also get Runway incidents in a feed reader or in Slack.
Install the outages.live MCP server, so that when something breaks you can tell if the cause is a provider we depend on and not my code. It reads the official status pages of cloud, AI, payment and developer providers and gives you their incidents as MCP tools.
Add it as a remote MCP server named "outages" at https://outages.cc/mcp (Streamable HTTP, no authentication), with your CLI command or your MCP config file.
Then:
1. Make sure it connects and shows the tools get_provider, list_feed and send_feedback.
2. Call get_provider with "runway" and tell me if Runway has a problem right now.
3. From now on, when a call to a third-party service fails or becomes slow, call get_provider for that service before you change my code.Paste this into any coding agent. It adds the server with its own MCP setup.
https://outages.cc/feed.xml?providers=runway/feed subscribe https://outages.cc/feed.xml?providers=runwayFAQ
Go from tracking outages to fixing production issues with Polylane.
Try Polylane