Baseten reported "Kimi K3 Model API outage" on its status page at 2026-09-20 07:19 UTC.

Baseten lists these components: Model APIs.

When did the incident start and end?

It started at 2026-09-20 07:19 UTC and ended at 2026-09-20 08:13 UTC. It lasted 55 min.

How do I get alerts for Baseten?

Subscribe to the Baseten live feed over RSS or in Slack, or add the outages.live MCP server to your coding agent.

Where does this information come from?

From the official status page of Baseten. outages.live reads it every few minutes and keeps every update.

BasetenIncident · 2026-09-20 07:19 UTC

Kimi K3 Model API outage

ResolvedOfficial update

This incident has been resolved.

The latest update from Baseten.

State

Resolved

Started

42 d ago

2026-09-20 07:19 UTC

Lasted

55 min

until 2026-09-20 08:13 UTC

Worst impact

Partial outage

Timeline

5 updates

07:1907:3207:4608:0008:13

Partial outageUpdate postedTimes in UTC

Identified

46 min 83%

Monitoring

9 min 17%

Updates

Times in UTC

As posted by Baseten

Resolved2026-09-20 08:13 UTC

This incident has been resolved.

Monitoring2026-09-20 08:04 UTC

A fix has been implemented and we are monitoring the results.

Identified2026-09-20 07:59 UTC

Calls to the US-hosted endpoint are resulting in errors. A fix is in progress.

Identified2026-09-20 07:30 UTC

~20% of calls are resulting in errors. A fix is in progress.

Identified2026-09-20 07:19 UTC

The issue has been identified and a fix is being implemented.

Affected components

Model APIs

Baseten in the last 90 days

Full history

90 days agoToday

Incidents in 90 days

Days with an incident

Median duration

37 min

This incident

1.5× the median

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

1 h 22 min

median 37 min

90 days agoToday

Other Baseten incidents

All incidents

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

This incident has been resolved.

Resolvedresolved 9 d ago

Baseten·Elevated errors on DeepSeek V4 Flash on Model APIs

This incident has been resolved.

Resolvedresolved 11 d ago

Baseten·Elevated errors for image requests on multiple Model APIs

This incident has been resolved.

Resolvedresolved 11 d ago

Baseten·DeepSeek V4.1 Flash Fast Outage on Model APIs

This incident has been resolved.

Resolvedresolved 12 d ago

Baseten·Elevated errors on Model APIs

This incident has been resolved.

Resolvedresolved 12 d ago

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.cc/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.cc/feed.xml?providers=baseten

Slack

/feed subscribe https://outages.cc/feed.xml?providers=baseten

FAQ

Go from tracking outages to fixing production issues with Polylane.

Try Polylane