outages.live
Live
BasetenIncident ·

Elevated errors for multiple models on Model APIs

DegradedOfficial update
0

Baseten reports elevated errors for GLM 5.3 and DeepSeek V4.1 Flash on Model APIs. DeepSeek V4.1 Flash and GLM 5.3 have recovered. Baseten continues to monitor the Model APIs.

State

Monitoring

Started

Ongoing for

31 min

Worst impact

Degraded

Timeline

3 updates
06:2206:2906:3706:4506:53
DegradedUpdate postedTimes in UTC

Investigating

14 min 46%

Identified

12 min 39%

Monitoring

5 min 15%

Updates

Times in UTC

As posted by Baseten

Monitoring

GLM 5.3 has recovered and we are continuing to monitor

Identified

DeepSeek V4.1 Flash is fully recovered. We expect GLM 5.3 to recover in the next 10 minutes

Investigating

We are seeing elevated errors on GLM 5.3 and DeepSeek V4.1 Flash

Affected components

1
Model APIs

Baseten in the last 90 days

Full history
90 days agoToday

Incidents in 90 days

31

Days with an incident

23

Median duration

37 min

This incident

16% shorter than the median

How long each incident lasted, on the day it started. The outlined bar is this incident.

5 h 9 min
median 37 min
90 days agoToday

Other Baseten incidents

All incidents

Baseten·Degraded Performance on DSV 4.1 Flash 1017-Fast on Model APIs

This incident has been resolved.

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.

Resolved · 1 affected

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.

Resolved

Baseten·Elevated errors for US-only GLM 5.3 Flash on Model APIs

This incident has been resolved.

Resolved

Baseten·Elevated errors on DeepSeek V4 Flash on Model APIs

This incident has been resolved.

Resolved

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.

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 "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.

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

FAQ

Go from tracking outages to fixing production issues with Polylane.

Try Polylane