Skip to main content
Runpod logo

Is Runpod Down?

No — Runpod is up
Runpod's status page
Not available · we could not read it
FlareWarden checks
Website reachable · 8 of 8 regions · 270 ms

Right now

We could not read Runpod's status page, so the verdict rests on our checks. Check it yourself How we decide

FlareWarden checks

runpod.io from 8 regions · when you open this page (at most every 30 minutes), otherwise every 6 hours

Reachable
Regions up
8 of 8
Response
270 ms
Checked

By region

  • Ashburn reachable, 194 ms
  • Frankfurt reachable, 275 ms
  • Johannesburg reachable, 311 ms
  • London reachable, 134 ms
  • Los Angeles reachable, 183 ms
  • Newark reachable, 157 ms
  • São Paulo reachable, 87 ms
  • Tokyo reachable, 821 ms
Timing by region
Connection timing for each region that loaded the page
RegionDNSTCPTLSTTFB
Ashburn136 ms1 ms7 ms188 ms
Frankfurt164 ms2 ms12 ms267 ms
Johannesburg246 ms0 ms6 ms307 ms
London66 ms2 ms8 ms126 ms
Los Angeles124 ms2 ms8 ms175 ms
Newark93 ms1 ms9 ms152 ms
São Paulo31 ms2 ms8 ms77 ms
Tokyo174 ms103 ms111 ms535 ms
We check that runpod.io loads, not every feature behind it. Test it yourself

History

Runpod website availability

Measured by FlareWarden · runpod.io

Last 7 days
100%
Last 30 days
100%
Last 90 days
100%
Avg response, 30 days
249ms

Last 30 days

19-day clean streak
Sep 25: no data
Sep 26: no data
Sep 27: no data
Sep 28: no data
Sep 29: no data
Sep 30: no data
Oct 1: no data
Oct 2: no data
Oct 3: no data
Oct 4: no data
Oct 5: no data
Oct 6: 100.00% uptime, 16 checks
Oct 7: 100.00% uptime, 32 checks
Oct 8: 100.00% uptime, 32 checks
Oct 9: 100.00% uptime, 32 checks
Oct 10: 100.00% uptime, 32 checks
Oct 11: 100.00% uptime, 32 checks
Oct 12: 100.00% uptime, 32 checks
Oct 13: 100.00% uptime, 32 checks
Oct 14: 100.00% uptime, 32 checks
Oct 15: 100.00% uptime, 32 checks
Oct 16: 100.00% uptime, 30 checks
Oct 17: 100.00% uptime, 31 checks
Oct 18: 100.00% uptime, 32 checks
Oct 19: 100.00% uptime, 32 checks
Oct 20: 100.00% uptime, 32 checks
Oct 21: 100.00% uptime, 32 checks
Oct 22: 100.00% uptime, 32 checks
Oct 23: 100.00% uptime, 32 checks
Oct 24: 100.00% uptime, 24 checks
Sep 25 Today
No downtime Partial Downtime Not measurable No data

Measured by FlareWarden's own checks of runpod.io from multiple regions every 6 hours. Runpod's status page sets the verdict above when it reports trouble, but never these figures. Percentages count only checks that returned an availability answer — 19 days measured so far. A dash means that window does not yet hold enough measured days to publish a figure.

What Runpod does

Runpod, styled RunPod until 2025, is a GPU cloud for AI work. Developers rent Pods, which are GPU or CPU containers on a specific machine, deploy Serverless endpoints whose workers start on demand to process queued inference jobs, and launch Instant Clusters for multi-node training. Capacity is spread over more than 30 data centers with IDs such as US-TX-4, EUR-IS-1 and CA-MTL-3.

What an outage looks like

Most Runpod incidents hit a single data center: Pods there lose network connectivity, network volumes in that data center stop responding, or machines go offline after a power fault, while other data centers keep running. Platform-wide incidents show up as error spikes on the GraphQL and REST APIs at api.runpod.io, failing SSH proxy connections, Serverless requests erroring, or the runpod.io console not loading.

What to do about it

Open uptime.runpod.io and find your data center under Regional Health; the Serverless and GPU Cloud sections cover the APIs, queue engine, pod proxy and console. If one data center is down, deploy a new Pod elsewhere, but a network volume stays in its own data center. Queued Serverless jobs wait for a worker until their TTL, 24 hours by default, so resubmitting them duplicates work.

Is it down for everyone, or just you?

If this page says Runpod is up but it is not loading for you, the problem is between you and them. Run a check against any URL from up to 17 cities across three regions to find out where it breaks.

Test it yourself

Related services

Replicate
Replicate
Together AI
Together AI
Baseten
Baseten
H
Hugging Face

Runpod outage FAQ

Is Runpod down for everyone or just me?
Usually it is down for one data center rather than everyone. Most incidents on uptime.runpod.io name a single data center, such as a network issue in EUR-IS-2 or a power outage in US-IL-1, so check the Regional Health row for the data center your Pod runs in. The checks on this page probe www.runpod.io, the company website, so they do not cover the console, the API or any particular data center.
Will I lose data if my Runpod Pod stops or restarts?
You lose the container disk but not /workspace. Runpod clears the container disk when a Pod stops or restarts, while files in /workspace on the volume disk survive until the Pod is terminated, and network volumes exist independently of any Pod. Editing a running Pod resets it and erases everything outside /workspace. Runpod says it is not designed for long-term storage and recommends backing up critical data elsewhere.
Why does my Runpod Pod restart with zero GPUs?
Because someone else rented the GPU on your Pod's machine while it was stopped. A Pod stays tied to the physical machine that holds its volume disk, so it cannot move to free hardware. You can start it with zero GPUs to copy data off, wait and retry, or terminate it and deploy a new Pod. Runpod recommends network volumes, which a new Pod on another machine can attach.
Do Runpod Serverless jobs retry automatically during an outage?
Queued jobs wait rather than fail, but a job that already failed or timed out needs a manual retry. Queue-based endpoints hold each job until a worker picks it up or its TTL, 24 hours by default, expires, and the /retry operation requeues a failed or timed-out job under the same job ID. Completion webhooks are retried up to two more times, 10 seconds apart. Async /run results are kept for only 30 minutes.
Does a Runpod data center outage affect my Serverless endpoint?
Only if the endpoint is pinned to that data center. Attaching a single network volume restricts an endpoint's workers to the volume's data center, which Runpod says limits failover. It suggests attaching network volumes from several data centers, though data does not sync between them, or allowing all data centers. For help, Runpod takes support requests at contact.runpod.io and runs a community Discord.

How we measure this

  • We request Runpod's public endpoint every 6 hours from Fly.io regions across six continents — the most recent check ran from 8 of them. When you open this page and our last check is more than 30 minutes old, we check again on the spot; those checks update the verdict, never the availability figures.
  • A region counts as down only when it gets no usable HTTP response. A 403 or 429 means the origin answered and refused us, which we report as blocked, never as an outage.
  • A single failing region is treated as probe noise. Our checks only change their verdict when two consecutive cycles agree.
  • Response times average only the regions that actually served the page, so a timeout never inflates the number.
  • Where Runpod publishes an official status feed we read it too, and the verdict is the worse of what it reports and what our checks see: a major outage of Runpod itself is Down, trouble with one part of it is Degraded, problems at a few of a provider's many locations change nothing, and a security notice that marks nothing down is shown but changes nothing either. A reading counts for 45 minutes; we read the feed again within minutes of any change to its incidents. The availability figures above are our measurement alone.

Get alerted when Runpod goes down

We check Runpod every 6 hours, and again when you open this page if that was more than 30 minutes ago. Your own monitors run as often as every 30 seconds, from up to 17 cities across three regions, and tell you the moment something breaks.

Start Free Monitoring
Free plan available No credit card required