Is Qdrant Down?

No — Qdrant is up

Qdrant's status page: Not available · we could not read it
FlareWarden checks: Website reachable · 8 of 8 regions · 488 ms

Right now

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

FlareWarden checks

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

Reachable

Regions up: 8 of 8
Response: 488 ms
Checked: 2 hours ago

By region

Ashburn reachable, 139 ms
Chicago reachable, 208 ms
Johannesburg reachable, 1766 ms
London reachable, 182 ms
Los Angeles reachable, 121 ms
San Jose reachable, 196 ms
Singapore reachable, 431 ms
Tokyo reachable, 867 ms

Timing by region

Connection timing for each region that loaded the page
Region	DNS	TCP	TLS	TTFB
Ashburn	70 ms	2 ms	9 ms	118 ms
Chicago	37 ms	20 ms	22 ms	101 ms
Johannesburg	203 ms	1 ms	355 ms	857 ms
London	30 ms	19 ms	21 ms	88 ms
Los Angeles	33 ms	2 ms	22 ms	71 ms
San Jose	66 ms	2 ms	10 ms	161 ms
Singapore	74 ms	4 ms	9 ms	325 ms
Tokyo	39 ms	1 ms	140 ms	466 ms

We check that qdrant.tech loads, not every feature behind it. Test it yourself

History

Qdrant website availability

Measured by FlareWarden · qdrant.tech

Last 7 days: —
Last 30 days: —
Last 90 days: —
Avg response, 30 days: —

Last 30 days

Oct 7 Today

No downtime Partial Downtime Not measurable No data

Measured by FlareWarden's own checks of qdrant.tech from multiple regions every 6 hours. Qdrant's status page sets the verdict above when it reports trouble, but never these figures. Percentages count only checks that returned an availability answer — 2 days measured so far. A dash means that window does not yet hold enough measured days to publish a figure.

What Qdrant does

Qdrant is an open source vector search engine written in Rust. Teams building RAG, recommendation systems and AI search either run it on their own servers or use Qdrant Cloud, the managed service, with clusters in AWS, Google Cloud and Azure regions plus a Hybrid Cloud option. Its status page lists the website and documentation, the Cloud UI, the Cloud API and one row per cluster region.

What an outage looks like

Most incidents hit one part of Qdrant Cloud. On November 2, 2026 users could not sign in or use the Cloud UI while existing clusters kept working. On October 17 cluster metrics and the /sys_metrics endpoint were unavailable in AWS us-east-1, with reads and writes unaffected. On October 8 some clusters in Azure Germany West Central were unavailable and others ran with fewer replicas than usual.

What to do about it

Check status.qdrant.io and find the row for your cluster's region: a Cloud UI incident does not mean your clusters are down. During the October 8 regional incident Qdrant said customers did not need to take any action and asked them not to delete or recreate their clusters. Paying customers open tickets through the support portal linked in the Qdrant Cloud console; everyone else can ask in Qdrant's Discord community.

Is it down for everyone, or just you?

If this page says Qdrant 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

Qdrant outage FAQ

Is Qdrant down or just my cluster?

Check the row for your cluster's region on status.qdrant.io. Each AWS, Google Cloud and Azure region and Hybrid Cloud has its own row, separate from the Cloud UI and the Cloud API, so a regional problem shows on one row only. If every row is green and only your cluster fails, open a ticket; Qdrant asks for the cluster ID and the collections affected.

Can I still use my clusters when the Qdrant Cloud UI is down?

In the November 2, 2026 incident, yes. Qdrant said users might be unable to sign in or use the Cloud UI, but that existing clusters and database operations were not affected and continued to work normally. If you cannot sign in, check the Cloud UI and Cloud API rows to see which one the incident names.

Does a Qdrant Cloud outage affect self-hosted Qdrant?

The status page does not cover it. status.qdrant.io lists the website and documentation, the Cloud UI, the Cloud API, Hybrid Cloud and the managed cluster regions; an open source Qdrant instance you run on your own servers appears nowhere on it. If your self-hosted instance fails, the page will not show it; look at your own deployment and logs.

Were the October 2026 metrics outage and the logging maintenance data problems?

No. During the October 17, 2026 incident in AWS us-east-1, clusters kept running and reads and writes were not affected; only monitoring metrics, including the /sys_metrics endpoint, were missing. The September 21 maintenance of the logging infrastructure delayed or left gaps in cluster logs in the console for about two hours, and Qdrant said no data stored in clusters was affected.

What does the check on this page measure?

It loads qdrant.tech, Qdrant's website and documentation. It does not reach the Cloud UI, the Cloud API or any cluster, in Qdrant Cloud or on your own servers. A green result means the website answers. For console, API and cluster faults, read the matching rows on status.qdrant.io, which this page shows beside our checks.

How we measure this

We request Qdrant'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 Qdrant 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 Qdrant 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 Qdrant goes down

We check Qdrant 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