Service Outage for Kimi K3.1 Pro
Kimi K3.1 Pro does not work and has a major outage. Fireworks AI says it is investigating. Fireworks AI reports that it has partially restored service to Kimi K3.1 Pro.
State
Investigating
Started
Ongoing for
41 min
Worst impact
Major outage
Timeline
2 updatesInvestigating
41 min 100%
Updates
Times in UTCAs posted by Fireworks AI
We’ve partially restored service to Kimi K3.1 Pro, and are still actively root causing the situation
We are actively investigating an outage for Kimi K3.1 Pro
Fireworks AI in the last 90 days
Full historyIncidents in 90 days
78
Days with an incident
25
Median duration
14 min
This incident
3.0× the median
Other Fireworks AI incidents
All incidentsFireworks AI·Service Degradation for GLM 5.3
GLM 5.3 had degraded performance. Fireworks AI reports that the incident is resolved. It lasted 19 minutes.
Fireworks AI·Service Degradation for DeepSeek V4.1 Flash 1017
Fireworks AI reports degraded performance for DeepSeek V4.1 Flash 1017. Fireworks AI resolved the incident. The service is operational. The outage lasted 17 minutes.
Fireworks AI·Service Degradation for GLM 5.3
Fireworks AI reports degraded performance for GLM 5.3. Fireworks AI investigated the incident. The incident is resolved and the service operated again after 43 minutes.
Fireworks AI·Service Degradation for GLM 5.3 Flash
Fireworks AI reports degraded performance for GLM 5.3 Flash. Fireworks AI resolved the incident. The service operated with degraded performance for about 85 minutes.
Fireworks AI·Service Degradation for GLM 5.3
Fireworks AI reported degraded performance for GLM 5.3. Fireworks AI investigated the issue and later stated that the service is operational again. The incident is resolved and lasted 14 minutes.
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