outages.live
Live
ModalIncident ·

Kimi K3 shared endpoint is degraded

ResolvedOfficial update

We identified the issue affecting the Kimi K3 shared endpoint and applied a mitigation. The endpoint is now fully operational.

The latest update from Modal.

State

Resolved

Started

Lasted

34 min

Worst impact

Degraded

Timeline

2 updates
06:3306:4106:5006:5807:07
DegradedUpdate postedTimes in UTC

Degraded

34 min 100%

Updates

Times in UTC

As posted by Modal

Resolved

We identified the issue affecting the Kimi K3 shared endpoint and applied a mitigation. The endpoint is now fully operational.

Degraded

We are actively investigating an issue with the Kimi K3 shared endpoint which is returning an elevated level of 5xx errors.

Affected components

1
Kimi K3 Shared Endpoint

Modal in the last 90 days

Full history
90 days agoToday

Incidents in 90 days

7

Days with an incident

6

Median duration

7 min

This incident

4.9× the median

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

2 h 8 min
median 7 min
90 days agoToday

Other Modal incidents

All incidents

Modal·Major outage

Modal reports that the Inkling Shared Endpoint does not work. Modal resolved this outage after 3 minutes.

Resolved

Modal·Web functions degraded

The degradation is resolved and web functions are operating normally. We will be implementing mechanisms to protect against a recurrence of this issue in future.

Resolved

Modal·Kimi K3 shared endpoint downtime

We identified the issue affecting the Kimi K3 shared endpoint and applied a mitigation. The endpoint is now fully operational.

Resolved

Modal·Function and Sandbox execution degraded

We're seeing recovery for function and sandbox execution, worker networking has been restored

Resolved

Modal·Dashboard and sandbox outage

We're observing recovery of impacted services and will continue to monitor.

Resolved

Follow Modal

Your coding agent knows when Modal is down, and tells you when a failure is theirs, not yours. You can also get Modal 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 "modal" and tell me if Modal 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=modal
Slack
/feed subscribe https://outages.live/feed.xml?providers=modal

FAQ

Go from tracking outages to fixing production issues with Polylane.

Try Polylane