Is Cerebras Inference down? › Outage history
Cerebras Inference outage history
Cerebras Inference published 30 incidents on its official status page since Oct 16, 2025, 3 of them rated at the highest impact level. 5 were major or long incidents with their own pages; the biggest are listed first. Below them is every smaller incident, then our own 90 day check history.
Biggest Cerebras Inference outages
Ranked by the official impact level, then by how long they lasted. Each has its own page with the cause, the fix time and every official update.
- Nov 18, 2025: Identified - Caused by External Depencency 3 hours 6 min · rated "Critical"
- Jan 26, 2026: Z.ai GLM 4.7 Service Unavailable 1 hour 17 min · rated "Critical"
- Feb 4, 2026: Partial Service Disruption Qwen 235B 9 hours 8 min · rated "Major"
- Mar 17, 2026: Z.ai GLM 4.7 Service Unavailable 6 hours 10 min · rated "Major"
- Sep 25, 2026: Partial Service Disruption 4 hours 58 min · rated "Major"
Every smaller Cerebras Inference incident
Minor and short incidents from the Cerebras Inference status page, newest first, each with a line from the official updates. Times are UTC.
August 2026
Aug 27, 2026, 12:05 UTC · Resolved
duration not stated · rated "Minor"
"Between 11:00 and 11:15 UTC users experienced partial degradation with Gemma-4-31B. Service has been restored."
July 2026
Jul 29, 2026, 14:14 UTC · Partial Service Disruption
duration not stated · rated "Minor"
"GPT-OSS-120B was having partial service disruption between 18:20 UTC to 18:45 UTC. This is resolved now."
June 2026
Jun 3, 2026, 14:09 UTC · Partial Service Disruption
1 hour 30 min · rated "Minor"
"AWS billing issue is fixed now."
May 2026
April 2026
Apr 3, 2026, 10:42 UTC · Service disruption with qwen-3-235b-a22b-instruct-2507
duration not stated · marked as no impact
"Between 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."
Apr 3, 2026, 10:38 UTC · Partial service disruption with GPT-OSS-120B
duration not stated · marked as no impact
"Between 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."
March 2026
Mar 18, 2026, 09:40 UTC · GLM 4.7 Partial Service Disruption
duration not stated · marked as no impact
"Between 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."
Mar 6, 2026, 05:29 UTC · Partial Service Disruption
22 minutes · rated "Minor"
"Between 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."
February 2026
Feb 10, 2026, 21:37 UTC · Partial Service Disruption on zai-glm-4.7
8 hours 37 min · rated "Minor"
"We've identified a fix and our engineering team is deploying this now."
Feb 10, 2026, 19:52 UTC · Partial Service Disruption on Llama-3.3-70B
2 hours 56 min · rated "Minor"
"We are currently investigating an issue with Llama-3.3-70B where users are seeing an elevated number of 503 errors. Engineering is working on a resolution."
Feb 5, 2026, 06:42 UTC · Partial Service Disruption on Cerebras Endpoints
1 hour 22 min · rated "Minor"
"Between 7.30 PM PT and 11 PM PT, the inference service was partially disrupted by 502 Gateway errors across all endpoints."
January 2026
Jan 27, 2026, 17:18 UTC · Qwen-32B Service Experiencing Degraded Performance
3 hours 47 min · marked as no impact
"Partial of the service has been restored, and we are currently working to resume normal service performance"
Jan 17, 2026, 01:47 UTC · Partial Service Disruption- API Key Error
14 minutes · rated "Minor"
"Between 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."
December 2025
Dec 12, 2025, 15:33 UTC · Partial Degradation of Qwen3 32B, Llama 3.1 8B, Llama 3.3 70B, and Qwen-3-235B-Instruct-2507
2 hours 30 min · rated "Minor"
"Between 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."
Dec 12, 2025, 04:20 UTC · Partial Degradation of Qwen3 235B Instruct
duration not stated · rated "Minor"
"Between 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."
November 2025
Nov 14, 2025, 15:48 UTC · Partial Service Disruption
2 hours 20 min · rated "Minor"
"Between 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."
Nov 8, 2025, 16:10 UTC · Partial Service Disruption
3 hours 29 min · rated "Minor"
"We've mitigated the issue impacting ZAI-GLM-4.6, and normal performance has been restored."
Nov 8, 2025, 16:09 UTC · Resolved
duration not stated · marked as no impact
"Between 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."
Nov 5, 2025, 23:46 UTC · Partial Service Disruption
14 minutes · rated "Major"
"Some features may be temporarily unavailable. We are currently working to resume normal service performance. We will provide further updates as we make progress."
October 2025
Oct 22, 2025, 16:18 UTC · Service Degradation
4 hours 55 min · marked as no impact
"Our teams are continuing to work to resolve this issue. We appreciate your patience."
Oct 19, 2025, 02:37 UTC · Datacenter Issue Causing Minimal Degredation
12 hours 2 min · rated "Minor"
"Between Oct 18th 7 PM PT and Oct 19th 6.30 AM PT users experienced minor service disruption with Llama 3.3 70B, Qwen 3 32B, GPT OSS 120B, Qwen 3 235B Thinking, Qwen 3 Coder 480B because of a datacenter issue."
Oct 16, 2025, 22:14 UTC · Partial Service Disruption
50 minutes · rated "Minor"
"Between 1:35 PM PT and 3:25 PM PT users experienced partial disruption with Qwen 235b Instruct model. We have deployed a fix and the issue is now resolved."
Cerebras Inference uptime, last 90 days
Tracked since Oct 7, 2026. Updated Oct 22, 2026, 12:35 UTC.
Every Cerebras Inference problem in the last 90 days
No outages, degraded periods or maintenance recorded since Oct 7, 2026.
Day by day
| Day (UTC) | Uptime | Avg response | Worst |
|---|---|---|---|
| Oct 22, 2026 | 100% | 78 ms | Up |
| Oct 21, 2026 | 100% | 131 ms | Up |
| Oct 20, 2026 | 100% | 125 ms | Up |
| Oct 19, 2026 | 100% | 126 ms | Up |
| Oct 18, 2026 | 100% | 126 ms | Up |
| Oct 17, 2026 | 100% | 130 ms | Up |
| Oct 16, 2026 | 100% | 232 ms | Up |
| Oct 15, 2026 | 100% | 285 ms | Up |
| Oct 14, 2026 | 100% | 270 ms | |
| Oct 13, 2026 | 100% | 275 ms | |
| Oct 12, 2026 | 100% | 268 ms | Up |
| Oct 11, 2026 | 100% | 189 ms | Up |
| Oct 10, 2026 | 100% | 127 ms | Up |
| Oct 9, 2026 | 100% | 119 ms | Up |
| Oct 8, 2026 | 100% | 120 ms | |
| Oct 7, 2026 | 100% | 116 ms | Up |
Cerebras Inference outage questions
Was Cerebras Inference down today?
No. We recorded no Cerebras Inference outage, degraded period or maintenance today (Oct 22, 2026, UTC).
Was Cerebras Inference down yesterday?
No. We recorded no Cerebras Inference outage, degraded period or maintenance yesterday (Oct 21, 2026, UTC).
When was Cerebras Inference last down?
The latest incident on the Cerebras Inference status page started Sep 25, 2026, 12:16 UTC: Partial Service Disruption (4 hours 58 min).
What was the biggest Cerebras Inference outage?
Of the incidents on record since Oct 16, 2025, the biggest was on Nov 18, 2025: Identified - Caused by External Depencency. The Cerebras Inference status page rated it "Critical" and it lasted 3 hours 6 min.
How often does Cerebras Inference go down?
Cerebras Inference's status page posted 30 incidents since Oct 16, 2025, 1 of them in the last 30 days. Most incidents affect part of the service, not all of it. Uptime from our own checks over the last 90 days: 100%.
Times are UTC. Official incidents are the company's own posts, quoted from the Cerebras Inference status page. Problem periods start when the official status page or our checks first show a problem and end when the service is next found working, so durations are accurate to within a few minutes. Recent outages across all services.