Kimi Code K3 TTFT 响应延迟升高
Moonshot AI reports higher TTFT latency for some requests on the K3 and Kimi Code - K3 components. Moonshot AI resolved the incident. The outage lasted about 1 hour and 35 minutes.
State
Resolved
Started
Lasted
1 h 35 min
Worst impact
Major outage
Timeline
2 updatesInvestigating
1 h 35 min 100%
Updates
Times in UTCAs posted by Moonshot AI
This incident has been resolved.
K3 部分请求的 TTFT 延迟可能升高
Affected components
2Moonshot AI in the last 90 days
Full historyIncidents in 90 days
86
Days with an incident
31
Median duration
22 min
This incident
4.3× the median
Other Moonshot AI incidents
All incidentsMoonshot AI·Minor Service Outage
Moonshot AI reports that the K3 component had a minor service outage. Moonshot AI reports that the outage is resolved. The outage lasted 6 minutes.
Moonshot AI·Kimi Code K3 TTFT 响应延迟升高
Moonshot AI reports that some requests to the K3 and Kimi Code - K3 components had higher TTFT latency. The incident is resolved and lasted 34 minutes.
Moonshot AI·Kimi Code K2.8 Preview TTFT 响应延迟升高
Moonshot AI reports that some requests to K2.8 Preview and Kimi Code - K2.8 Preview had higher TTFT latency. Moonshot AI investigated the problem. The incident is resolved and lasted 55 minutes.
Moonshot AI·Minor Service Outage
Moonshot AI reports that the K3.1 Pro Highspeed, K3, and K2.8 Preview components worked at a degraded level during a minor service outage. Moonshot AI resolved the outage. It lasted 78 minutes.
Moonshot AI·Minor Service Outage
Moonshot AI reports that the K3 component did not work correctly. Moonshot AI reports that the outage is resolved. The outage lasted 600 minutes.
Follow Moonshot AI
Your coding agent knows when Moonshot AI is down, and tells you when a failure is theirs, not yours. You can also get Moonshot 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 "moonshot" and tell me if Moonshot 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=moonshot/feed subscribe https://outages.live/feed.xml?providers=moonshotFAQ
Go from tracking outages to fixing production issues with Polylane.
Try Polylane