Skip to content

Status

Venom Cloud status

All systems operational

Computed from this cloud's request log at Nov 20, 2026, 4:25 PM UTC; refreshed every 5 minutes.

Daemons online
1
Of them in the public pool
0
Distinct models they serve
7

Cloud

ComponentLast 24 hoursLast 7 days
Cloud APIOperational

Every request through /v1 that reached a model: share that did not end in a 5xx or a lost stream, and the time to the last byte.

100.00%
p50 1.18s · 45 req
100.00%
p50 3.48s · 562 req
RouterOperational

Share of routed requests a daemon or provider took in time, and the time the routing decision took.

100.00%
- · 45 req
100.00%
- · 562 req
DaemonsNot enough traffic

Requests served by daemons, relayed or direct, across every organisation.

-
- · 0 req
-
- · 0 req

Providers

ComponentLast 24 hoursLast 7 days
Alibaba Cloud Model Studio (Qwen)Operational

Requests the cloud served from this provider.

100.00%
p50 1.18s · 45 req
100.00%
p50 1.18s · 45 req
AnthropicNot enough traffic

Requests the cloud served from this provider.

-
- · 0 req
100.00%
p50 4.01s · 361 req
OpenAINot enough traffic

Requests the cloud served from this provider.

-
- · 0 req
100.00%
p50 2.42s · 156 req

Daemon uptime

Target: 99 % of minutes online over 30 days, per daemon. Sampled once a minute from heartbeats.

GroupLast 24 hoursLast 7 daysLast 30 daysMeeting the target
All daemons

Minutes every connected daemon (not revoked or retired) had a live lease, pooled.

50.00 %
45.25 %
57.46 %
0 of 2
Public nodes

The same, for the daemons in the public pool that anyone's requests can reach.

-
-
-
-

How these numbers are made

  • Every request through the cloud's /v1 writes one metadata row when it ends. This page counts those rows across all organisations; it never reads prompts, responses, keys or names.
  • Available means the request did not end in a 5xx status or a lost stream (daemon_lost, dispatch_timeout, no_ack, no_lease). A 4xx, such as a bad key or a spent budget, is the caller's and counts as available.
  • Latency is the median time from the request to its last byte. The router's is the median time its routing decision took.
  • A request the router refused before any daemon or provider was picked (no daemon available, unknown model) writes no row, so it is not counted here.
  • Fewer than 20 requests in a window shows no figures. A provider is listed only with at least 20 requests in the last 7 days.
  • Direct requests (sent by the client straight to a daemon) count once the daemon reports them.
  • Daemon uptime is sampled, not requested: once a minute the cloud checks whether each daemon's heartbeat lease is live. A daemon its owner turned off counts as down. A window with fewer than 30 sampled minutes shows no figure.