outages.live
Live

Factory

Factory is operational

Checked 55 s ago Operational

History

90 days agoToday

Incidents in 90 days

5

Days with an incident

5

Median duration

28 min

Longest incident

5 h 2 min

Components

14
api.factory.ai Operational
90 days ago1 day with an incidentToday
Web App Operational
90 days ago1 day with an incidentToday
CLI Operational
90 days agoNo incidentsToday
Desktop Operational
90 days ago1 day with an incidentToday
Droid Computers Operational
90 days agoNo incidentsToday

Models

Anthropic Operational
90 days agoNo incidentsToday
OpenAI Operational
90 days ago1 day with an incidentToday
Gemini Operational
90 days agoNo incidentsToday
Nemotron Operational
90 days agoNo incidentsToday
Grok Operational
90 days agoNo incidentsToday
GLM Operational
90 days ago1 day with an incidentToday
Kimi Operational
90 days agoNo incidentsToday
DeepSeek Operational
90 days ago1 day with an incidentToday
MiniMax Operational
90 days ago1 day with an incidentToday

Past incidents

Provider status pageTimes in UTC

Sep 18, 2026

Duration12 min22:58 to 23:10Service Disruption: User AuthenticationMajor outage

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

Aug 25, 2026

Duration6 min16:06 to 16:11GLM 5.2 unavailable in our EU deploymentPartial outage

GLM 5.2 is available again in EU.

Aug 19, 2026

Duration28 min07:37 to 08:05DeepSeek V4 Flash DegradedPartial outage

Response times have recovered to baseline levels.

Aug 11, 2026

Duration1 h 58 min19:24 to 21:22Degraded Minimax M3 availabilityDegraded

Minimax M3 serving is fully restored.

Aug 7, 2026

Duration5 h 2 min16:12 to 21:14OpenAI Models Returning 431 ErrorsDegraded

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.

Prompt
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.

RSS
https://outages.live/feed.xml?providers=factory
Slack
/feed subscribe https://outages.live/feed.xml?providers=factory

Go from tracking outages to fixing production issues with Polylane.

Try Polylane