Cerebras
Live monitoring · checked every 2 minutes · last check 17s ago

Is Cerebras Inference down? Cerebras status right now

OperationalCurrent status
100%Uptime 24h
100%Uptime 30 days
131 msAPI response time

Last 24 hours

24h agonow

API response time (24h)

0145290p50 101 ms · p95 232 ms

Cerebras Inference reliability, last 50 days

Over the last 50 days ModelBank measured 100% uptime for Cerebras Inference (100% over the last 30 days); no check failed. In the same period the official status page posted 3 incidents (1 in the last 30 days), 1 of them major or critical; the median time from posting to resolution was about 5 h. The most recent official incident was “Partial Service Disruption” on 2026-11-03, which lasted 2.6 h. The current status has held since 16d ago.

Recent major incidents:

Model availability on Cerebras Inference

1 models · all healthy

Success rate of real API traffic routed to this platform (not our probe), refreshed every 10 minutes.

ModelDaily successStability24 h30 minIn / out
Qwen3.8 27BOccasional issues (1 d)100%100%$0.99 / $1.49

Each daily bar is the average success rate of that day: green ≥ 99.5 %, yellow ≥ 97 %, orange ≥ 90 %, red < 90 %, grey = no data (collected since v12).

90-day uptime history

90 days ago100% uptimetoday

Incident history Outage calendar →

Partial Service Disruption

Cerebras · Details · · impact: none · lasted 2.6 h

Partial Service Disruption

Cerebras · Details · · impact: major · lasted 5 h

Resolved

Cerebras · Details · · impact: minor · lasted 1 min

Partial Service Disruption

Cerebras · Details · · impact: minor · lasted 1 min

Partial Service Disruption

Cerebras · Details · · impact: minor · lasted 1.5 h

qwen-3-235b-a22b-instruct-2507 Service Unavailable

Cerebras · Details · · impact: critical · lasted 58 min

Partial service disruption with GPT-OSS-120B

Cerebras · Details · · impact: none · lasted 1 min

Service disruption with qwen-3-235b-a22b-instruct-2507

Cerebras · Details · · impact: none · lasted 1 min

GLM 4.7 Partial Service Disruption

Cerebras · Details · · impact: none · lasted 1 min

Z.ai GLM 4.7 Service Unavailable

Cerebras · Details · · impact: major · lasted 6.2 h

Z.ai GLM 4.7 Service Unavailable

Cerebras · Details · · impact: major · lasted 57 min

Z.ai GLM 4.7 Service Unavailable

Cerebras · Details · · impact: none · lasted 1 min

Partial Service Disruption

Cerebras · Details · · impact: minor · lasted 22 min

Partial Service Disruption on zai-glm-4.7

Cerebras · Details · · impact: minor · lasted 8.6 h

Partial Service Disruption on Llama-3.3-70B

Cerebras · Details · · impact: minor · lasted 2.9 h

Partial Service Disruption on Cerebras Endpoints

Cerebras · Details · · impact: minor · lasted 1.4 h

Partial Service Disruption Qwen 235B

Cerebras · Details · · impact: major · lasted 9.1 h

Qwen-32B Service Experiencing Degraded Performance

Cerebras · Details · · impact: none · lasted 3.8 h

Z.ai GLM 4.7 Service Unavailable

Cerebras · Details · · impact: critical · lasted 1.3 h

Llama 3.3 70B Service Unavailable

Cerebras · Details · · impact: major · lasted 2.9 h

Partial Service Disruption- API Key Error

Cerebras · Details · · impact: minor · lasted 14 min

Partial Degradation of Qwen3 235B Instruct

Cerebras · Details · · impact: minor · lasted 1 min

Identified - Caused by External Depencency

Cerebras · Details · · impact: critical · lasted 3.1 h

Partial Service Disruption

Cerebras · Details · · impact: minor · lasted 2.3 h

FAQ

Is Cerebras Inference down?

No, Cerebras Inference is up and working normally. ModelBank checks Cerebras every 2 minutes from our global monitoring network and also reads the official status page. Last check: 17s ago.

What is Cerebras Inference’s uptime?

Measured by ModelBank: 100% in the last 24 hours, 100% over 30 days and 100% over 90 days.

What should I do if Cerebras Inference is not working?

First check this page and the official status page. If Cerebras Inference is up for everyone else, try clearing cache, logging out and in, switching network, or checking your API key and rate limits (HTTP 429). If it is a real outage, switch to an alternative model — see the alternatives on this page — or use a router with automatic failover.

Get notified when Cerebras Inference goes down

We’ll notify you the moment ModelBank detects a Cerebras Inference outage, and again when it recovers.

Email · Browser push · Slack / Discord · Feishu / DingTalk / WeCom · RSS — free, no sign-up