Live

Elevated errors for Gemini models

Devin reported elevated errors that made most requests to Gemini models fail on the Desktop Agent. Devin identified an issue with its upstream model provider. Devin stated that the provider restored access, and the incident is resolved after about 99 minutes.

State

Resolved

Started

Lasted

1 h 39 min

Worst impact

Degraded

Timeline

4 updates
00:2800:5301:1701:4202:07
DegradedUpdate postedTimes in UTC

Identified

59 min 59%

Monitoring

40 min 41%

Updates

Times in UTC

As posted by Devin

Resolved

This incident is resolved. Requests to Gemini models have been successful since approximately 5:19 PM PST.

Monitoring

We are continuing to monitor for any further issues.

Monitoring

Our upstream model provider restored access at approximately 5:19 PM PST. Requests to Gemini models are successful again. We are monitoring the results.

Identified

Since approximately 3:48 PM PST, most requests to Gemini models fail with an error. We identified an issue with our upstream model provider, and we are working with the provider to restore access. Other models are not affected. Please select a different model until we resolve this issue.

Affected components

1
Desktop Agent

Devin in the last 90 days

Full history
90 days agoToday

Incidents in 90 days

6

Days with an incident

6

Median duration

1 h 26 min

This incident

1.2× the median

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

2 h 3 min
median 1 h 26 min
90 days agoToday

Other Devin incidents

All incidents

Follow Devin

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

FAQ

Go from tracking outages to fixing production issues with Polylane.

Try Polylane