Cerebras Outage History
Cerebras is up right nowPingoru has recorded 48 incidents for Cerebras: 27 in the last 12 months and 3 in the last 90 days.
Show as a table
| Month | Incidents | Hours with an open incident |
|---|---|---|
| April 2026 | 2 | 1 of 720 (0%) |
| May 2026 | 1 | 1 of 744 (0%) |
| June 2026 | 1 | 2 of 720 (0%) |
| July 2026 | 1 | 5 of 744 (1%) |
| August 2026 | 1 | 0 of 744 (0%) |
| September 2026 | 1 | 5 of 720 (1%) |
| October 2026 | 0 | 0 of 524 (0%) |
Incidents, newest first
Major September 25, 2026 Partial Service Disruption 4h 58m GPT-OSS-120B, Qwen-3.8-27b
Started Sep 25, 2026, 12:16 PM UTC· resolved Sep 25, 2026, 05:14 PM UTC
- investigating Sep 25, 2026, 12:16 PM UTC
Some features may be temporarily unavailable since UTC 10:54. We are currently working to resume normal service performance. We will provide further updates as we make progress.
- monitoring Sep 25, 2026, 01:41 PM UTC
Issue has beed resolved. We are monitoring the status.
- resolved Sep 25, 2026, 05:14 PM UTC
The incident has been resolved
Minor August 27, 2026 Resolved 15m GPT-OSS-120B
Started Aug 27, 2026, 11:00 AM UTC· resolved Aug 27, 2026, 11:15 AM UTC
- resolved Aug 27, 2026, 12:05 PM UTC
Between 11:00 and 11:15 UTC users experienced partial degradation with Gemma-4-31B. Service has been restored.
Critical May 1, 2026 qwen-3-235b-a22b-instruct-2507 Service Unavailable 57m Qwen-3-235B-Instruct-2507
Started May 01, 2026, 07:59 AM UTC· resolved May 01, 2026, 08:57 AM UTC
- investigating May 01, 2026, 07:59 AM UTC
The service is currently inaccessible. We are currently working urgently to restore service capabilities. We will provide further updates as we make progress.
- resolved May 01, 2026, 08:57 AM UTC
This incident has been resolved.
Notice April 3, 2026 Partial service disruption with GPT-OSS-120B 18m
Started Apr 03, 2026, 09:00 AM UTC· resolved Apr 03, 2026, 09:18 AM UTC
- resolved Apr 03, 2026, 10:38 AM UTC
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.
Notice April 3, 2026 Service disruption with qwen-3-235b-a22b-instruct-2507 27m
Started Apr 03, 2026, 09:00 AM UTC· resolved Apr 03, 2026, 09:27 AM UTC
- resolved Apr 03, 2026, 10:42 AM UTC
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.
Notice March 18, 2026 GLM 4.7 Partial Service Disruption 2h 12m
Started Mar 18, 2026, 05:30 AM UTC· resolved Mar 18, 2026, 07:42 AM UTC
- resolved Mar 18, 2026, 09:40 AM UTC
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.
Major March 17, 2026 Z.ai GLM 4.7 Service Unavailable 6h 10m ZAI-GLM-4.7
Started Mar 17, 2026, 12:21 PM UTC· resolved Mar 17, 2026, 06:31 PM UTC
- identified Mar 17, 2026, 12:21 PM UTC
The service is currently inaccessible. We are currently working urgently to restore service capabilities. We will provide further updates as we make progress.
- resolved Mar 17, 2026, 06:31 PM UTC
This incident has been resolved.
Minor February 10, 2026 Partial Service Disruption on zai-glm-4.7 8h 36m ZAI-GLM-4.7
Started Feb 10, 2026, 09:37 PM UTC· resolved Feb 11, 2026, 06:14 AM UTC
- investigating Feb 10, 2026, 09:37 PM UTC
We are currently investigating an issue with zai-glm-4.7 where users are seeing an elevated number of 503 errors. Engineering is working on a resolution.
- identified Feb 11, 2026, 12:12 AM UTC
We've identified a fix and our engineering team is deploying this now.
- resolved Feb 11, 2026, 06:14 AM UTC
This incident has been resolved.
Minor February 10, 2026 Partial Service Disruption on Llama-3.3-70B 2h 55m
Started Feb 10, 2026, 07:52 PM UTC· resolved Feb 10, 2026, 10:47 PM UTC
- investigating Feb 10, 2026, 07:52 PM UTC
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.
- investigating Feb 10, 2026, 09:09 PM UTC
We've identified a fix and our engineering team is deploying this now.
- investigating Feb 10, 2026, 10:47 PM UTC
Our engineering team has resolved the issue.
- resolved Feb 10, 2026, 10:47 PM UTC
This incident has been resolved.
Minor February 5, 2026 Partial Service Disruption on Cerebras Endpoints 1h 22m Llama3.1-8B, Qwen-3-235B-Instruct-2507, GPT-OSS-120B, ZAI-GLM-4.7 and 1 more
Started Feb 05, 2026, 06:42 AM UTC· resolved Feb 05, 2026, 08:04 AM UTC
- investigating Feb 05, 2026, 06:42 AM UTC
We are investigating 502 Gateway errors on Cerebras endpoints. We are currently working to resume normal service performance. We will provide further updates as we make progress.
- resolved Feb 05, 2026, 08:04 AM UTC
Between 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 operational across all endpoints.
Major February 4, 2026 Partial Service Disruption Qwen 235B 9h 7m Qwen-3-235B-Instruct-2507
Started Feb 04, 2026, 04:59 PM UTC· resolved Feb 05, 2026, 02:07 AM UTC
- investigating Feb 04, 2026, 04:59 PM UTC
Qwen 235B performance is degraded and temporarily unavailable for some service tiers. We are currently working to resume normal service performance. We will provide further updates as we make progress.
- monitoring Feb 04, 2026, 06:53 PM UTC
As part of recent changes in traffic patterns and capacity, we are temporarily turning down rate limits for Pay-go users to help maintain a positive experience across the board. We understand the challenges this may create for you and your users, and we sincerely apologize for the inconvenience. We plan to monitor this endpoint and evaluate restoring rate limits in the next week. Thank you for your continued partnership and understanding, please reach out to our support team for any other questions.
- investigating Feb 05, 2026, 02:07 AM UTC
Between 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 monitor this endpoint and evaluate restoring rate limits in the next week for Pay Go users.
- resolved Feb 05, 2026, 02:07 AM UTC
Between 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 monitor this endpoint and evaluate restoring rate limits in the next week for Pay Go users.
Notice January 27, 2026 Qwen-32B Service Experiencing Degraded Performance 3h 46m
Started Jan 27, 2026, 05:18 PM UTC· resolved Jan 27, 2026, 09:05 PM UTC
- investigating Jan 27, 2026, 05:18 PM UTC
Qwen 32b is currently inaccessible. We are currently working urgently to restore service capabilities. We will provide further updates as we make progress.
- identified Jan 27, 2026, 05:46 PM UTC
Partial of the service has been restored, and we are currently working to resume normal service performance
- resolved Jan 27, 2026, 09:05 PM UTC
This incident has been resolved.
Major January 18, 2026 Llama 3.3 70B Service Unavailable 2h 56m
Started Jan 18, 2026, 09:40 PM UTC· resolved Jan 19, 2026, 12:36 AM UTC
- investigating Jan 18, 2026, 09:40 PM UTC
The service is currently inaccessible. We are currently working urgently to restore service capabilities. We will provide further updates as we make progress.
- identified Jan 18, 2026, 11:52 PM UTC
The issue has been root caused and fix is being implemented to bring the service backup.
- monitoring Jan 19, 2026, 12:03 AM UTC
The fix has been rolled out and the service has resumed consuming traffic and being monitored.
- investigating Jan 19, 2026, 12:35 AM UTC
Between 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.
- resolved Jan 19, 2026, 12:36 AM UTC
Between 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.
Minor January 17, 2026 Partial Service Disruption- API Key Error 14m Llama3.1-8B, Qwen-3-235B-Instruct-2507, GPT-OSS-120B, ZAI-GLM-4.7
Started Jan 17, 2026, 01:47 AM UTC· resolved Jan 17, 2026, 02:01 AM UTC
- investigating Jan 17, 2026, 01:47 AM UTC
Partial service disruption due to 401 Error with Unauthorized API Key. We are currently working to resume normal service performance. We will provide further updates as we make progress.
- investigating Jan 17, 2026, 01:53 AM UTC
This issue is caused by an internal system dependency, and we are currently working to restore system performance.
- resolved Jan 17, 2026, 02:01 AM UTC
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.
Minor December 12, 2025 Partial Degradation of Qwen3 32B, Llama 3.1 8B, Llama 3.3 70B, and Qwen-3-235B-Instruct-2507 2h 30m Llama3.1-8B, Qwen-3-235B-Instruct-2507
Started Dec 12, 2025, 03:33 PM UTC· resolved Dec 12, 2025, 06:04 PM UTC
- investigating Dec 12, 2025, 03:33 PM UTC
We are currently working to resume normal service performance. We will provide further updates as we make progress.
- investigating Dec 12, 2025, 03:36 PM UTC
We are continuing to investigate this issue.
- investigating Dec 12, 2025, 03:37 PM UTC
We are continuing to investigate this issue.
- monitoring Dec 12, 2025, 03:58 PM UTC
We've deployed the fix and affected service is now recovering. We are actively monitoring service performance.
- investigating Dec 12, 2025, 05:47 PM UTC
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.
- investigating Dec 12, 2025, 05:48 PM UTC
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.
- resolved Dec 12, 2025, 06:04 PM UTC
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.
Minor December 11, 2025 Partial Degradation of Qwen3 235B Instruct –
Started Dec 11, 2025, 09:30 AM UTC· resolved Dec 11, 2025, 09:30 AM UTC
- resolved Dec 12, 2025, 04:20 AM UTC
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.
Critical November 18, 2025 Identified - Caused by External Depencency 3h 5m Llama3.1-8B, Qwen-3-235B-Instruct-2507, GPT-OSS-120B, Developer Console
Started Nov 18, 2025, 12:30 PM UTC· resolved Nov 18, 2025, 03:36 PM UTC
- investigating Nov 18, 2025, 12:30 PM UTC
Around 4:09 AM PT, Inference Platform went down causing 500 Internal Server Errors. This issue is caused by a third-party system, and we are currently monitoring.
- investigating Nov 18, 2025, 12:54 PM UTC
We are continuing to investigate this issue.
- investigating Nov 18, 2025, 02:24 PM UTC
We are continuing to investigate this issue.
- identified Nov 18, 2025, 02:41 PM UTC
The issue has been identified and a fix is being implemented.
- monitoring Nov 18, 2025, 02:55 PM UTC
A fix has been implemented and we are monitoring the results.
- monitoring Nov 18, 2025, 02:57 PM UTC
The platform is accessible now. We are monitoring to ensure stability.
- resolved Nov 18, 2025, 03:36 PM UTC
This incident has been resolved.
Notice October 22, 2025 Service Degradation 4h 54m Qwen-3-235B-Instruct-2507, GPT-OSS-120B
Started Oct 22, 2025, 04:18 PM UTC· resolved Oct 22, 2025, 09:13 PM UTC
- investigating Oct 22, 2025, 04:18 PM UTC
We are experiencing degradation of service across several of our models. Our engineering team is working to identify the root cause and restore stability to our systems.
- identified Oct 22, 2025, 05:01 PM UTC
We've identified that the combination of high load and a network routing issue resulted in higher queue times and rejection rates. ETA on resolution is a few hours.
- identified Oct 22, 2025, 06:01 PM UTC
Our teams are continuing to work to resolve this issue. We appreciate your patience.
- monitoring Oct 22, 2025, 07:44 PM UTC
A fix has been implemented, availability is returning to 100%, and latency times are improving. We will continue to monitor over the next few hours.
- resolved Oct 22, 2025, 09:13 PM UTC
This incident has been resolved.
Minor October 19, 2025 Datacenter Issue Causing Minimal Degredation 12h 1m GPT-OSS-120B
Started Oct 19, 2025, 02:37 AM UTC· resolved Oct 19, 2025, 02:38 PM UTC
- investigating Oct 19, 2025, 02:37 AM UTC
We are experiencing issues with one of our datacenters. We are actively working on mitigation. Seeing minimal degradation of service at this point. Fortunately, this only impacts one datacenter, the rest are operational, and redundancies are in place. ETA recovery time for datacenter: 8 hours. We will actively keep you updated on the progress.
- investigating Oct 19, 2025, 02:37 AM UTC
We are continuing to investigate this issue.
- identified Oct 19, 2025, 02:41 AM UTC
Update: The issue has been root caused to a city water supply disruption. We are actively working on mitigation.
- resolved Oct 19, 2025, 02:38 PM UTC
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. We have deployed the fix and the issue is now resolved.
Major August 22, 2025 Reduced availability for Llama-3.3-70B –
Started Aug 22, 2025, 04:46 PM UTC· resolved Aug 22, 2025, 04:46 PM UTC
- resolved Aug 22, 2025, 04:47 PM UTC
Llama-3.3-70B endpoint experienced reduced availability starting at approximately 7:45am PT. Endpoint went back to full availability starting 8:55am PT.
Minor July 31, 2025 Reduced Availability - Resolved –
Started Jul 31, 2025, 06:00 PM UTC· resolved Jul 31, 2025, 06:00 PM UTC
- resolved Jul 31, 2025, 09:42 PM UTC
We observed a temporary increase in latency and intermittent 503 errors for the Llama-3.3-70B model earlier today (between 10:59am Pacific to 11:09am Pacific on 7/31/2025). This was due to ongoing infrastructure operations, including system scaling and maintenance, which briefly reduced available capacity. Service availability and performance are now stabilized.
Notice July 25, 2025 Service Unavailable - Resolved –
Started Jul 25, 2025, 08:00 PM UTC· resolved Jul 25, 2025, 08:00 PM UTC
- resolved Jul 25, 2025, 10:23 PM UTC
Llama-3.3-70B, DeepSeek-R1-Distill-Llama-70B, Qwen-3-32B (7/25/2025 from 1:17 PM to 1:41 PM PT) were unavailable. We restored normal service performance at 1:41 PM PT on July 25th.
Major June 25, 2025 Qwen-3-32B API Incident – Resolved –
Started Jun 25, 2025, 02:30 PM UTC· resolved Jun 25, 2025, 02:30 PM UTC
- resolved Jun 25, 2025, 06:12 PM UTC
We had a brief issue this morning (6/25/2025 from 7:25 AM to 9:40 AM PT) affecting the Qwen-3-32B shared endpoint. Some users may have seen 404 or 503 errors during that time.
Major June 19, 2025 Service Unavailable –
Started Jun 19, 2025, 06:30 PM UTC· resolved Jun 19, 2025, 06:30 PM UTC
- resolved Jun 20, 2025, 01:53 PM UTC
Llama3.1-8B was unavailable. We restored normal service performance at 3:21 PM EST on June 19th.
Major April 30, 2025 Identified - Caused by Internal Depencency 4h 11m
Started Apr 30, 2025, 11:20 PM UTC· resolved May 01, 2025, 03:32 AM UTC
- investigating May 01, 2025, 02:05 AM UTC
This issue is caused by an internal system dependency, and we are currently working to restore system performance.
- identified May 01, 2025, 02:09 AM UTC
Some features may be temporarily unavailable. We are currently working to resume normal service performance. We will provide further updates as we make progress.
- resolved May 01, 2025, 03:32 AM UTC
Between 04/30 23:20 UTC and 05/01 01:35 UTC, users experienced partial degradation with Llama-3.3-70B. We have deployed a fix, and the issue is now resolved.