Degraded Minimax M3 availability
Minimax M3 serving is fully restored.
The latest update from Factory.
State
Resolved
Started
82 d ago
2026-08-11 19:24 UTC
Lasted
1 h 58 min
until 2026-08-11 21:22 UTC
Worst impact
Degraded
Timeline
3 updatesIdentified
1 h 12 min 61%
Monitoring
46 min 39%
Updates
Times in UTCAs posted by Factory
Minimax M3 serving is fully restored.
We are observing improved Minimax M3 serving. We will keep monitoring the service quality to make sure it is fully recovered.
We have identified an issue with our Minimax M3 serving. We are in communication with our providers and awaiting resolution. We advise temporarily switching to other models in the meantime for uninterrupted workflow.
Affected components
2Factory in the last 90 days
Full historyIncidents in 90 days
5
Days with an incident
5
Median duration
28 min
This incident
4.2× the median
Other Factory incidents
All incidentsFactory·Service Disruption: User Authentication
The incident affecting our authentication provider, WorkOS, has been resolved. For full details regarding the resolution, please visit the WorkOS Status Page at https://status.workos.com/incidents/phs2prf38d75
Factory·GLM 5.2 unavailable in our EU deployment
GLM 5.2 is available again in EU.
Factory·DeepSeek V4 Flash Degraded
Response times have recovered to baseline levels.
Factory·OpenAI Models Returning 431 Errors
We deployed a backend fix for the errors affecting OpenAI models and have confirmed that error rates returned to normal. Users can resume normal usage; no Factory CLI or Desktop update or other action is required.
Follow Factory
Your coding agent knows when Factory is down, and tells you when a failure is theirs, not yours. You can also get Factory 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.live/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 "factory" and tell me if Factory 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.live/feed.xml?providers=factory/feed subscribe https://outages.live/feed.xml?providers=factoryFAQ
Go from tracking outages to fixing production issues with Polylane.
Try Polylane