outages.live
Live

OpenRouter

OpenRouter is operational

Checked 2 min ago Operational

History

90 days agoToday

Incidents in 90 days

10

Days with an incident

13

Median duration

1 h 54 min

Longest incident

37 h 53 min

Components

7

API - Gateway

Chat (/api/v1/chat/completions) Operational
90 days ago5 days with an incidentToday
Video (/api/v1/videos) Operational
90 days ago3 days with an incidentToday
Image (/api/v1/image) Operational
90 days agoNo incidentsToday
TTS (/api/v1/audio/speech) Operational
90 days ago2 days with an incidentToday
STT (/api/v1/audio/transcriptions) Operational
90 days ago2 days with an incidentToday
Embeddings (/api/v1/embeddings) Operational
90 days agoNo incidentsToday
Web & Application Services Operational
90 days ago7 days with an incidentToday

Past incidents

Provider status pageTimes in UTC

Oct 26, 2026

Duration12 min16:59 to 17:11Failing inference requestsPartial outage

The issue is now resolved.

Oct 25, 2026

Duration2 h 10 min21:57 to 00:07Video webhooks are not being calledMajor outage

Video webhooks are firing correctly again, and all backlogged video webhooks have been replayed.

Oct 15, 2026

Duration37 h 53 min14:50 to 04:43Activity logs, usage metrics reporting are experiencing delaysDegraded

The issue is now resolved.

Oct 14, 2026

Duration42 min04:12 to 04:54Increased errors and latency on API requests in the US Pacific NorthwestDegraded

The issue is now resolved. Cloudflare moved traffic to nearby locations. Other locations were not affected, and no change on our side caused it.

Oct 8, 2026

Duration6 h 38 min18:55 to 01:33Usage Reporting Delays in Web AppDegraded

The issue is now resolved.

Sep 24, 2026

Duration1 h 38 min22:55 to 00:33Meta Provider API calls are failing on OpenRouter with error 401.Degraded

The issue is now resolved. Root cause was identified as an authentication issue on the Meta Developer API Platform impacting all Managed Meta Accounts including OpenRouter's.

Sep 23, 2026

Duration27 min17:11 to 17:38Sign-in and sign-up failures on openrouter.aiDegraded

This incident is resolved. Between approximately 11:50 and 17:11 UTC, a portion of sign-in and sign-up attempts on openrouter.ai were incorrectly blocked with the message "This action was detected as suspicious and has been blocked." The cause was an infrastructure issue at our authentication provider that made one of its bot-protection checks fail, which in turn triggered a blocking rule. The provider disabled the rule at 17:11 UTC and sign-ins have succeeded normally since then. Existing sessions and API keys were not affected at any point, and there was no security breach or exposure of account data. If you were unable to sign in earlier, please try again. We apologize for the disruption.

Sep 4, 2026

Duration2 h 45 min18:27 to 21:12Degraded video generation APIDegraded

This incident has been resolved.

Aug 28, 2026

Duration15 h 28 min07:05 to 22:33Web application degradedDegraded

This incident has been resolved.

Duration4 min02:15 to 02:19Elevated 429s on Anthropic and OpenAIDegraded

Issue is resolved

Maintenance

Scheduled site maintenance

We will be conducting site maintenance. Certain dashboard functionality (eg adding credits, creating or modifying API keys, or updating user settings) will not available during this period. Inference is not affected.

Maintenancestarts in 4 min

Follow OpenRouter

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

Go from tracking outages to fixing production issues with Polylane.

Try Polylane