Elevated errors on GLM-5.3-Flash on Model APIs
We are currently investigating this issue.
The latest update from Baseten.
State
Investigating
Started
Ongoing for
17 min
Worst impact
Degraded
Timeline
5 updatesInvestigating
11 min 66%
Resolved
6 min 34%
Updates
Times in UTCAs posted by Baseten
We are currently investigating this issue.
We are currently investigating this issue.
We are currently investigating this issue.
Affected components
1Baseten in the last 90 days
Full historyIncidents in 90 days
27
Days with an incident
21
Median duration
37 min
This incident
52% shorter than the median
Other Baseten incidents
All incidentsBaseten·Elevated TTFT on Kimi K3 on MAPIs
Baseten reported elevated time to first token on Kimi K3 on the Model APIs. Baseten implemented a fix and monitored the results. The incident is resolved and lasted about 38 minutes.
Baseten·Elevated errors for multiple models on Model APIs
Baseten reported elevated errors for GLM 5.3 and DeepSeek V4.1 Flash on Model APIs. Baseten later confirmed that both models recovered. Baseten resolved the incident after 36 minutes.
Baseten·Degraded Performance on DSV 4.1 Flash 1017-Fast on Model APIs
This incident has been resolved.
Baseten·Model APIs are down for all models
Baseten Model APIs were down for all models. Baseten reports that the incident is resolved. The outage lasted 21 minutes.
Baseten·Elevated errors for Kimi-K3 on Model APIs. **Dedicated Inference is not affected**
Baseten reports elevated errors for Kimi-K3 on Model APIs. Dedicated Inference is not affected. The incident is resolved and lasted 5 hours and 9 minutes.
Follow Baseten
Your coding agent knows when Baseten is down, and tells you when a failure is theirs, not yours. You can also get Baseten 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 "baseten" and tell me if Baseten 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=baseten/feed subscribe https://outages.live/feed.xml?providers=basetenFAQ
Go from tracking outages to fixing production issues with Polylane.
Try Polylane