Service Degradation for Kimi K3 US
Fireworks AI reports degraded performance for Kimi K3 US. The service is now operational and Fireworks AI marks the incident resolved. The incident lasted about 11 minutes, from 12:39 to 12:50 UTC on 3 November 2026.
State
Resolved
Started
Lasted
11 min
Worst impact
Degraded
Timeline
2 updatesInvestigating
11 min 100%
Updates
Times in UTCAs posted by Fireworks AI
We've resolved the incident and the affected service is now operational.
We are seeing impacted performance for Kimi K3 US. We are actively investigating.
Fireworks AI in the last 90 days
Full historyIncidents in 90 days
33
Days with an incident
11
Median duration
10 min
This incident
About the median
Other Fireworks AI incidents
All incidentsFireworks AI·Service Degradation for Kimi K3 US
Kimi K3 US has degraded performance. Fireworks AI reports that it is investigating the problem. Fireworks AI started the investigation on 3 November 2026 at 13:32 UTC.
Fireworks AI·Service Degradation for Kimi K3 US
Kimi K3 US had degraded performance. Fireworks AI reports that the incident is resolved. The outage lasted 15 minutes.
Fireworks AI·Service Degradation for Kimi K3 US
Fireworks AI reported degraded performance for Kimi K3 US. Fireworks AI investigated the incident. The incident is resolved after 9 minutes, and the service is operational.
Fireworks AI·Service Degradation for Kimi K3
Fireworks AI reported degraded performance for Kimi K3. Fireworks AI resolved the incident, and the service is now operational. The outage lasted 14 minutes.
Fireworks AI·Service Degradation for GLM 5.3
Fireworks AI reports degraded performance for GLM 5.3. Fireworks AI is investigating the incident. The incident started at 08:47 UTC.
Follow Fireworks AI
Your coding agent knows when Fireworks AI is down, and tells you when a failure is theirs, not yours. You can also get Fireworks AI 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 "fireworks" and tell me if Fireworks AI 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=fireworks/feed subscribe https://outages.live/feed.xml?providers=fireworksFAQ
Go from tracking outages to fixing production issues with Polylane.
Try Polylane