Home / Status

🕒 Not connected to a monitoring source

Status.

The endpoints, regions and worker records DCS operates. This page is static and reads no monitoring source, so every figure on it shows — rather than a number. Live endpoint health is published at status.dcsai.ai.

Live endpoints

Every critical surface, in one list

The surfaces that are monitored in production. Uptime and response time are shown as — here because no monitoring source is wired to this page.

ENDPOINTUPTIME · RESPONSE TIME — NOT CONNECTED

Main backendapi.dcsai.ai · Railway us-east-1

—

EU passive failoverapi-eu.dcsai.ai · Railway europe-west4

—

Compute laneapi.compute.dcsai.ai · Railway asia-southeast1

—

Storage backendapi.storage.dcsai.ai · Lighthouse-backed

—

Primary IPFS gatewaygateway.dcsai.ai · Cloudflare Worker

—

Gateway standbygateway-standby.dcsai.ai · separate CF account

—

Inference Tier 0 (own-GPU)RunPod H200 · weight 0.5-0.7

—

Public verifierverify.dcsai.ai · Cloudflare Pages

—

Region health summary

Five regions watched in parallel

Synthetic builds run once a minute from each region; the green tag is the result of the last 60 checks.

🇺🇸

North America

—

build · —

🇪🇺

Europe

—

build · —

🇪🇰

Asia-Pacific

—

build · —

🇦🇪

Middle East

—

build · —

🇧🇷

Latin America

—

build · —

Incident history · last 30 days

Named, dated, resolved

Every incident gets a postmortem note. No "minor issues" hand-waving.

These entries are author-recorded. They are not generated from a connected monitoring source and have not been independently verified from this page.

21 MAY17:42 UTC

Inference Tier 0 intermittent 503s

RunPod H200 returned 503 on ~3% of requests for 14 minutes. Traffic auto-shed to Tier 1 (Cerebras) — zero impact on builds. Underlying capacity restored 17:56 UTC.

Resolved

18 MAY03:10 UTC

Scheduled maintenance · Storage backend

Lighthouse SDK upgrade to 0.4.5. 6-minute window. Read traffic served from cache; new mirrors queued and drained within the window.

Maintenance

14 MAY22:08 UTC

Middle East region latency > 3s

Upstream BGP path flap added 1.4-2.7s to ME-routed builds for 23 minutes. Cleared by route propagation; no requests dropped, only delayed.

Degraded

09 MAY14:32 UTC

Primary gateway free-tier quota approach

Cloudflare free-tier daily request budget reached 87%. Gateway standby pre-warmed; cutover not triggered. Daily budget upgrade applied 15:10 UTC.

Resolved

On-chain heartbeat · Reputation SBT

Last 5 worker reputation mints

Each mint is an on-chain attestation that a worker hit a reliability milestone. Live from the contract on Base mainnet.

TRUSTED

0xa4e7…9f31 · — jobs · — reliable

2 min ago Basescan →

VERIFIED

0xb3c2…4d18 · — jobs · — reliable

18 min ago Basescan →

VERIFIED

0xd1f8…7e02 · — jobs · — reliable

41 min ago Basescan →

TRUSTED

0x9a55…c074 · — jobs · — reliable

1 h ago Basescan →

VERIFIED

0x68bd…13af · — jobs · — reliable

2 h ago Basescan →

Contract 0xbDd1f5fC349D9a8EfCEb07Edbd491233b2540f5F on Base mainnet. Verify a chain →

Status FAQ

How this page actually works

Where does the data come from?

It does not, currently. This page is static and makes no network calls, so the endpoint list, region grid and mint rows show — rather than numbers. Live endpoint status is published at status.dcsai.ai; the Reputation SBT contract is public on Base mainnet and can be read directly on Basescan.

How quickly do you flip gateway if Cloudflare hits the free tier?

Design target, not a measured figure. ~2 minutes. DNS at gateway.dcsai.ai is pre-staged to swing to gateway-standby.dcsai.ai (separate Cloudflare account, separate worker). DNS propagation is typically under 5 minutes globally; client cache hits continue serving during the swing.

What's the EU failover RTO?

Design target, not a measured figure. The EU passive failover already mirrors api.dcsai.ai on every deploy. RTO is dominated by Cloudflare DNS swing — typically under 90 seconds to start serving from api-eu.dcsai.ai.

What counts as "degraded"?

This is the threshold policy, not a current reading. P95 response time more than 2× the 30-day baseline, or error rate above 1% sustained for 5 minutes. Both trigger a yellow status; sustained breach for 15+ minutes opens an incident.

Why is the 90-day uptime number blank?

Because this page has no monitoring source wired to it, and a number without a source is a guess. When it is connected, scheduled maintenance will not be subtracted from it — if something was down, it counts.

Can I get a webhook for incidents?

Yes — Slack and PagerDuty webhooks live, plus a generic JSON webhook. Email subscribers get a per-incident note within 60 seconds of an incident open.

Popular

Compute & Infrastructure

Build & Agents

AI & Workspace

Trust & Verification

DCS AI Technologies

DCS Labs Research

Developers

Solutions

Company

Status & trust

Compute & Infrastructure

Build & Agents

AI & Workspace

Trust & Verification

DCS Labs — research

Company

Status & trust

Status.

Live status is not connected

Every critical surface, in one list

Five regions watched in parallel

Named, dated, resolved

Inference Tier 0 intermittent 503s

Scheduled maintenance · Storage backend

Middle East region latency > 3s

Primary gateway free-tier quota approach

Last 5 worker reputation mints

How this page actually works

Status.

Live status is not connected

Every critical surface, in one list

Five regions watched in parallel

Named, dated, resolved

Inference Tier 0 intermittent 503s

Scheduled maintenance · Storage backend

Middle East region latency > 3s

Primary gateway free-tier quota approach

Last 5 worker reputation mints

Get pinged on incidents.

How this page actually works