outages.live
Live

Baseten

Baseten is operational

Checked 25 s ago Operational

History

90 days agoToday

Incidents in 90 days

27

Days with an incident

18

Median duration

37 min

Longest incident

1 h 22 min

Components

6
Dedicated Inference Operational
90 days ago7 days with an incidentToday
Model APIs Operational
90 days ago11 days with an incidentToday
Training Operational
90 days agoNo incidentsToday
Model Management API Operational
90 days ago4 days with an incidentToday
Web Application Operational
90 days ago2 days with an incidentToday
Homepage and Docs Operational
90 days agoNo incidentsToday

Past incidents

Provider status pageTimes in UTC

Oct 23, 2026

Duration56 min01:51 to 02:48Elevated errors for US-only GLM 5.3 Flash on Model APIsDegraded

This incident has been resolved.

Oct 21, 2026

Duration40 min01:48 to 02:28Elevated errors on DeepSeek V4 Flash on Model APIsDegraded

This incident has been resolved.

Duration21 min01:05 to 01:26Elevated errors for image requests on multiple Model APIsDegraded

This incident has been resolved.

Oct 20, 2026

Duration6 min19:04 to 19:10DeepSeek V4.1 Flash Fast Outage on Model APIsPartial outage

This incident has been resolved.

Duration8 min01:35 to 01:43Elevated errors on Model APIsDegraded

This incident has been resolved.

Oct 9, 2026

Duration37 min21:29 to 22:06Elevated errors on new model builds. Existing models are not affectedDegraded

This incident has been resolved.

Oct 6, 2026

Duration13 min04:35 to 04:48DeepSeek v4.1 outage on Model APIs. Dedicated Inference is not affectedPartial outage

This incident has been resolved.

Sep 29, 2026

Duration13 min19:44 to 19:57Elevated 500s in Single us-central RegionPartial outage

This incident has been resolved.

Duration21 min01:07 to 01:28Metrics degradation in UI and API. **Inference not affected**Degraded

This incident has been resolved.

Sep 24, 2026

Duration1 h 22 min18:35 to 19:57Intermittent 5xx for a subset of models in 1 US Central clusterDegraded

This incident has been resolved.

Duration42 min07:23 to 08:06Elevated inference 500s for a subset of models deployed in 1 US-East clusterPartial outage

This incident has been resolved.

Sep 21, 2026

Duration7 min18:34 to 18:41Elevated inference 500s for a subset of models deployed in GCP central1Partial outage

This incident has been resolved.

Duration11 min13:31 to 13:42Metrics degradation in UI and API. **Inference not affected**Degraded

This incident has been resolved.

Sep 20, 2026

Duration55 min07:19 to 08:13Kimi K3 Model API outagePartial outage

This incident has been resolved.

Sep 15, 2026

Duration45 min01:22 to 02:07Elevated errors for models in a single India-based clusterDegraded

This incident has been resolved.

Sep 14, 2026

Duration42 min16:21 to 17:03Partial outage on Kimi K3 model API inference (non-US only)Degraded

This incident has been resolved.

Sep 9, 2026

Duration6 min17:42 to 17:49Partial outage on Nemotron Ultra Model API. **Dedicated Inference is not affected**Degraded

This incident has been 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

Go from tracking outages to fixing production issues with Polylane.

Try Polylane