outages.live
Live
RunPodIncident · 2026-09-17 14:04 UTC

Elevated errors on the GraphQL and REST v2 APIs

ResolvedOfficial update

We've resolved the issue and services are operating normally.

The latest update from RunPod.

State

Resolved

Started

46 d ago

2026-09-17 14:04 UTC

Lasted

1 h

until 2026-09-17 15:04 UTC

Worst impact

Degraded

Timeline

2 updates
14:0414:1914:3414:4915:04
DegradedUpdate postedTimes in UTC

Degraded

1 h 100%

Updates

Times in UTC

As posted by RunPod

Resolved2026-09-17 15:04 UTC

We've resolved the issue and services are operating normally.

Degraded2026-09-17 14:04 UTC

Error rates on the GraphQL API (api.runpod.io/graphql) and REST v2 API (api.runpod.io/v2) have returned to normal as of 14:10 UTC. Requests are no longer being rejected. We are continuing to monitor while we complete the underlying fix.

Affected components

1
graphql: api.runpod.io

RunPod in the last 90 days

Full history
90 days agoToday

Incidents in 90 days

23

Days with an incident

26

Median duration

1 h 31 min

This incident

34% shorter than the median

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

38 h 9 min
median 1 h 31 min
90 days agoToday

Other RunPod incidents

All incidents

RunPod·CA-MTL-1 and EU-SE-1 DC is Unavailable

RunPod reports that CA-MTL-1 and EU-SE-1 are unavailable. RunPod is working to resolve the issue. The outage started on 31 October 2026 and continues.

Major outageupdated 1 d ago

RunPod·US-KS-2 Network Issue

Issue has been resolved and the network in US-KS-2 DC is operating normally.

Resolvedresolved 4 d ago

RunPod·US-WA-1 Network Issue

Issue has been resolved and the network in US-WA-1 DC is operating normally.

Resolvedresolved 4 d ago

RunPod·EUR-IS-3 Network Issue

Issue has been resolved and the network in EUR-IS-3 DC is operating normally.

Resolvedresolved 8 d ago

RunPod·Increased errors for S3 API

We've resolved the issue and services are operating normally.

Resolvedresolved 10 d ago

Follow RunPod

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

FAQ

Go from tracking outages to fixing production issues with Polylane.

Try Polylane