Cerebras Inference Outage History

29 incidents recorded over the last 365 days, 28 of them resolved. Durations are measured from when PulsAPI first saw the problem to when it cleared, which is usually longer than the vendor's own figure.

Live Cerebras Inference status100.00% uptime history

Every Recorded Cerebras Inference Incident

Cerebras Inference incidents, newest first, with date, duration and status.
DateIncidentDurationStatus
Nov 3, 2026Partial Service DisruptionThis incident has been resolved.2h 33mResolved
Sep 25, 2026Partial Service DisruptionThe incident has been resolved4h 58mResolved
Aug 30, 2026Scheduled firewall maintenanceThe scheduled maintenance has been completed.3h 0mScheduled
Aug 27, 2026ResolvedBetween 11:00 and 11:15 UTC users experienced partial degradation with Gemma-4-31B. Service has been restored.0 minResolved
Jul 29, 2026Partial Service DisruptionGPT-OSS-120B was having partial service disruption between 18:20 UTC to 18:45 UTC. This is resolved now.0 minResolved
Jun 3, 2026Partial Service DisruptionAWS billing issue is fixed now.1h 29mResolved
May 1, 2026qwen-3-235b-a22b-instruct-2507 Service UnavailableThis incident has been resolved.57 minResolved
Apr 3, 2026Service disruption with qwen-3-235b-a22b-instruct-2507Between 9:07 AM UTC and 9:27 AM UTC users experienced service disruption with qwen-3-235b-a22b-instruct-2507. We have deployed a fix and the issue is now resolved.-102 minResolved
Apr 3, 2026Partial service disruption with GPT-OSS-120BBetween 9:07 AM UTC and 9:18 AM UTC users experienced partial service disruption with gpt-oss-120b. We have deployed a fix and the issue is now resolved.-98 minResolved
Mar 18, 2026GLM 4.7 Partial Service DisruptionBetween 10:30 PM PST and 11:42 PM PST 03/17 users experienced partial degradation with glm-4.7. We have deployed a fix and the issue is now resolved.-250 minResolved
Mar 17, 2026Z.ai GLM 4.7 Service UnavailableThis incident has been resolved.6h 10mResolved
Mar 17, 2026Z.ai GLM 4.7 Service UnavailableWe have deployed a fix and the issue is now resolved.57 minResolved
Mar 17, 2026Z.ai GLM 4.7 Service UnavailableBetween 02:29 PM PT and 02:20 AM PT users experienced service unavailability with GLM-4.7, caused by a datacenter issue.-1991 minResolved
Mar 6, 2026Partial Service DisruptionBetween 4:53 UTC ending 5:38 UTC, Qwen 3 235B endpoint experienced a partial service disruption due to a transient network issue. The issue has been identified and fixed, the endpoint is operational.22 minResolved
Feb 10, 2026Partial Service Disruption on zai-glm-4.7This incident has been resolved.8h 36mResolved
Feb 10, 2026Partial Service Disruption on Llama-3.3-70BThis incident has been resolved.2h 55mResolved
Feb 5, 2026Partial Service Disruption on Cerebras EndpointsBetween 7.30 PM PT and 11 PM PT, the inference service was partially disrupted by 502 Gateway errors across all endpoints. This issue is caused by an internal system dependency, the fix was rolled out and the service is…1h 22mResolved
Feb 4, 2026Partial Service Disruption Qwen 235BBetween 06:00 AM PT and 06:00 PM PT users experienced service disruption with Qwen 3 235B Instruct. We have taken action to address recent changes in traffic patterns and capacity, reducing the disruption. We plan to…9h 7mResolved
Jan 27, 2026Qwen-32B Service Experiencing Degraded PerformanceThis incident has been resolved.3h 46mResolved
Jan 26, 2026Z.ai GLM 4.7 Service UnavailableThis incident has been resolved.1h 17mResolved
Jan 18, 2026Llama 3.3 70B Service UnavailableBetween 12.45 PM PT and 4.00 PM PT users experienced service unavailability with Llama 3.3 70B, caused by a datacenter issue. We have deployed a fix and the issue is now resolved, model endpoint is operational.2h 56mResolved
Jan 17, 2026Partial Service Disruption- API Key ErrorBetween 4.25 PM PT and 5.45 PM PT, developers experienced minor service disruption due to API Key Error. The issue has been identified and resolved, normal service operation is restored.14 minResolved
Dec 12, 2025Partial Degradation of Qwen3 32B, Llama 3.1 8B, Llama 3.3 70B, and Qwen-3-235B-Instruct-2507Between 06:50 AM PST and 07:45 AM PST users experienced partial degradation with llama3.1-8b, llama-3.3-70b, qwen-3-32b, qwen-3-235b-instruct-2507 models. We have deployed a fix and the issue is now resolved.2h 30mResolved
Dec 12, 2025Partial Degradation of Qwen3 235B InstructBetween 01:30 AM PT and 2:30 PM PT users experienced partial degradation with Qwen 3 235B Instruct. We have deployed a fix and the issue is now resolved.-1130 minResolved
Nov 18, 2025Identified - Caused by External DepencencyThis incident has been resolved.3h 5mResolved
Nov 14, 2025Partial Service DisruptionBetween 06:05 AM PST and 09:25 AM PST users experienced partial degradation with Llama-3.3-70B. We have deployed a fix and the issue is now resolved.2h 19mResolved
Nov 8, 2025Partial Service DisruptionWe’ve mitigated the issue impacting ZAI-GLM-4.6, and normal performance has been restored.3h 29mResolved
Nov 8, 2025ResolvedBetween 1:30 AM PST and 2:30 AM PST users experienced service disruption with ZAI-GLM-4.6. We have deployed a fix and the issue is now resolved.-399 minResolved
Nov 5, 2025Partial Service DisruptionThis incident has been resolved.14 minResolved

Hear about the next one while it is open

Everything above is a record written after the fact. We can email you when the next Cerebras Inference incident opens instead, at the point where knowing still changes what you do.

Free, no password, no card. Unsubscribe in one click.

How to Read This Cerebras Inference Incident Log

Each row is an incident PulsAPI observed, not a summary written afterwards. The duration is wall-clock time between the first failing check and the first clean one, so it includes the window before Cerebras Inference acknowledged anything. Vendor post-mortems typically measure from acknowledgement, which is why their numbers are usually shorter.

Incidents still open have no duration yet and are listed as ongoing rather than being given a running total. The archive covers the last 365 days; anything older has aged out of the window rather than never having happened.

The longest single Cerebras Inference outage in this window ran 9h 7m, against a mean recovery of 2h 42m. If you depend on Cerebras Inference in a customer-facing path, the longest figure is the one to design around. The mean is what happens on a normal bad day; the maximum is what happens on the worst one.