coniferSTATUS · PARTNER ACCESS

passkeys are issued per partner — ping us in Slack
coniferSTATUS

Conifer gateway

api.conifer.build
model response time · daily medianp95
requests per day · 30d
reachability · round-trip · 24h

Model providers

upstream
providerlast 45 daysuptime 30dprobertt · 24h

Incidents & deploys

auto-recorded

Alerts

confirmed outages & recoveries only
One click. Outage and recovery alerts for every provider land in your macOS or Windows notification center.
more options · Slack, webhooks, or only certain providers
providers
or pick the ones you route through:
destinations

method · every provider's API is probed each 5 min · a failed attempt is retried once before it counts · down = 2 consecutive failed cycles · recovery is announced

honesty · faults on our monitor's own network are discarded, never shown as provider downtime · providers without a probeable API show as unmonitored, never as up · gaps render as gaps

latency · response-time charts are measured on real requests from accounts that share telemetry (about a tenth of traffic) and include full streaming time — long agent turns are counted, so p95 reflects workload length, not queueing · days with few measured requests can swing widely (hover a point for its sample size) · probe rtt is API reachability only