Cerebras

Affected: GPT-OSS-120B, Qwen-3.8-27b

Failure mode: The text does not say enough to tell. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with low confidence (taxonomy v0.2).

1. investigating 2026-09-25 12:16 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.

2. monitoring 2026-09-25 13:41 UTC

   Services are back up. We are still investigating the root cause.

3. resolved 2026-09-25 17:14 UTC

   The incident has been resolved

Excerpts are shortened. Read the full incident on Cerebras's status page.

Affected: GPT-OSS-120B

Failure mode: The text does not say enough to tell. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with low confidence (taxonomy v0.2).

1. resolved 2026-08-27 12:05 UTC

   Between 11:00 and 11:15 UTC users experienced partial degradation with Gemma-4-31B. Service has been restored.

Excerpts are shortened. Read the full incident on Cerebras's status page.

Affected: GPT-OSS-120B

Failure mode: The text does not say enough to tell. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with low confidence (taxonomy v0.2).

1. resolved 2026-07-29 14:14 UTC

   GPT-OSS-120B was having partial service disruption between 18:20 UTC to 18:45 UTC. This is resolved now.

Excerpts are shortened. Read the full incident on Cerebras's status page.

Affected: GPT-OSS-120B

Failure mode: A provider or third-party service this vendor depends on failed. Root cause: A failure at a provider or vendor they depend on. Tagged by claude-haiku-5-5 with medium confidence (taxonomy v0.2).

Names an upstream provider: AWS.

1. investigating 2026-06-03 14:09 UTC

   Customer using AWS billing may experience availability issues. Exact reason is being investigated.

2. resolved 2026-06-03 15:39 UTC

   AWS billing issue is fixed now.

Excerpts are shortened. Read the full incident on Cerebras's status page.

Failure mode: The text does not say enough to tell. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with medium confidence (taxonomy v0.2).

1. investigating 2026-05-01 07:59 UTC

   The service is currently inaccessible. We are currently working urgently to restore service capabilities. We will provide further updates as we make progress.

2. resolved 2026-05-01 08:57 UTC

   This incident has been resolved.

Excerpts are shortened. Read the full incident on Cerebras's status page.

Failure mode: The text does not say enough to tell. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with low confidence (taxonomy v0.2).

1. resolved 2026-04-03 09:00 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.

Excerpts are shortened. Read the full incident on Cerebras's status page.

Failure mode: The text does not say enough to tell. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with low confidence (taxonomy v0.2).

1. resolved 2026-04-03 09:00 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.

Excerpts are shortened. Read the full incident on Cerebras's status page.

Failure mode: The text does not say enough to tell. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with low confidence (taxonomy v0.2).

1. resolved 2026-03-18 05:30 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.

Excerpts are shortened. Read the full incident on Cerebras's status page.

Failure mode: The text does not say enough to tell. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with low confidence (taxonomy v0.2).

1. identified 2026-03-17 12:21 UTC

   The service is currently inaccessible. We are currently working urgently to restore service capabilities. We will provide further updates as we make progress.

2. resolved 2026-03-17 18:31 UTC

   This incident has been resolved.

Excerpts are shortened. Read the full incident on Cerebras's status page.

Failure mode: A code release introduced the failure. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with low confidence (taxonomy v0.2).

1. investigating 2026-03-17 11:14 UTC

   The service is currently inaccessible. We are currently working urgently to restore service capabilities. We will provide further updates as we make progress.

2. investigating 2026-03-17 12:10 UTC

   Between 03/16 02:29 PM PST and 03/17 05:00 AM PST users experienced service disruption with glm-4.7. We have deployed a fix and the issue is now resolved.

3. resolved 2026-03-17 12:11 UTC

   We have deployed a fix and the issue is now resolved.

Excerpts are shortened. Read the full incident on Cerebras's status page.

Failure mode: A zone, region or data center became unavailable. Root cause: Hardware or facility. Tagged by claude-haiku-5-5 with medium confidence (taxonomy v0.2).

1. resolved 2026-03-16 01:30 UTC

   Between 02:29 PM PT and 02:20 AM PT users experienced service unavailability with GLM-4.7, caused by a datacenter issue.

Excerpts are shortened. Read the full incident on Cerebras's status page.

Failure mode: Network, DNS, routing or connectivity failure. Root cause: Network or DNS. Tagged by claude-haiku-5-5 with high confidence (taxonomy v0.2).

1. investigating 2026-03-06 05:29 UTC

   Qwen 235B is facing partial service disruption. We are currently working to resume normal service performance. We will provide further updates as we make progress.

2. monitoring 2026-03-06 05:47 UTC

   We identified the issue, applied a fix and are monitoring the endpoint.

3. resolved 2026-03-06 05:51 UTC

   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.

Excerpts are shortened. Read the full incident on Cerebras's status page.

Failure mode: The text does not say enough to tell. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with low confidence (taxonomy v0.2).

1. investigating 2026-02-10 21:37 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.

2. identified 2026-02-11 00:12 UTC

   We've identified a fix and our engineering team is deploying this now.

3. resolved 2026-02-11 06:14 UTC

   This incident has been resolved.

Excerpts are shortened. Read the full incident on Cerebras's status page.

Failure mode: The text does not say enough to tell. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with low confidence (taxonomy v0.2).

1. investigating 2026-02-10 19:52 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.

2. investigating 2026-02-10 21:09 UTC

   We've identified a fix and our engineering team is deploying this now.

3. investigating 2026-02-10 22:47 UTC

   Our engineering team has resolved the issue.

4. resolved 2026-02-10 22:47 UTC

   This incident has been resolved.

Excerpts are shortened. Read the full incident on Cerebras's status page.

Affected: GPT-OSS-120B, Developer Console

Failure mode: Orchestration, control plane, service discovery or load balancing failed. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with medium confidence (taxonomy v0.2).

1. investigating 2026-02-05 06:42 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.

2. resolved 2026-02-05 08:04 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.

Excerpts are shortened. Read the full incident on Cerebras's status page.

Failure mode: Exhausted memory, disk, CPU, queues, connection pools or quotas. Root cause: Not enough capacity for the load. Tagged by claude-haiku-5-5 with medium confidence (taxonomy v0.2).

1. investigating 2026-02-04 16:59 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.

2. monitoring 2026-02-04 18:53 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...

3. investigating 2026-02-05 02:07 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...

4. resolved 2026-02-05 02:07 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...

Excerpts are shortened. Read the full incident on Cerebras's status page.

Failure mode: The text does not say enough to tell. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with low confidence (taxonomy v0.2).

1. investigating 2026-01-27 17:18 UTC

   Qwen 32b is currently inaccessible. We are currently working urgently to restore service capabilities. We will provide further updates as we make progress.

2. identified 2026-01-27 17:46 UTC

   Partial of the service has been restored, and we are currently working to resume normal service performance

3. resolved 2026-01-27 21:05 UTC

   This incident has been resolved.

Excerpts are shortened. Read the full incident on Cerebras's status page.

Failure mode: A code release introduced the failure. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with low confidence (taxonomy v0.2).

1. investigating 2026-01-26 20:51 UTC

   The service is currently inaccessible. We are currently working urgently to restore service capabilities. We will provide further updates as we make progress.

2. investigating 2026-01-26 21:19 UTC

   Partial of the service has been restored, and we are currently working to resume normal service performance.

3. monitoring 2026-01-26 21:47 UTC

   A fix has been rolled out, and we are actively monitoring the situation.

4. investigating 2026-01-26 22:08 UTC

   Between 20:51 and 21:47 UTC users experienced service disruption with GLM 4.7. We have deployed a fix and the issue is now resolved.

5. resolved 2026-01-26 22:08 UTC

   This incident has been resolved.

Excerpts are shortened. Read the full incident on Cerebras's status page.

Failure mode: A zone, region or data center became unavailable. Root cause: Hardware or facility. Tagged by claude-haiku-5-5 with medium confidence (taxonomy v0.2).

1. investigating 2026-01-18 21:40 UTC

   The service is currently inaccessible. We are currently working urgently to restore service capabilities. We will provide further updates as we make progress.

2. identified 2026-01-18 23:52 UTC

   The issue has been root caused and fix is being implemented to bring the service backup.

3. monitoring 2026-01-19 00:03 UTC

   The fix has been rolled out and the service has resumed consuming traffic and being monitored.

4. investigating 2026-01-19 00:35 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.

5. resolved 2026-01-19 00:36 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.

Excerpts are shortened. Read the full incident on Cerebras's status page.

Affected: GPT-OSS-120B

Failure mode: Login, tokens, certificates or credentials failed. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with medium confidence (taxonomy v0.2).

1. investigating 2026-01-17 01:47 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.

2. investigating 2026-01-17 01:53 UTC

   This issue is caused by an internal system dependency, and we are currently working to restore system performance.

3. resolved 2026-01-17 02:01 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.

Excerpts are shortened. Read the full incident on Cerebras's status page.

Failure mode: AI model returned degraded, wrong or empty output (not errors or timeouts). Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with medium confidence (taxonomy v0.2).

1. investigating 2025-12-12 15:33 UTC

   We are currently working to resume normal service performance. We will provide further updates as we make progress.

2. investigating 2025-12-12 15:36 UTC

   We are continuing to investigate this issue.

3. investigating 2025-12-12 15:37 UTC

   We are continuing to investigate this issue.

4. monitoring 2025-12-12 15:58 UTC

   We've deployed the fix and affected service is now recovering. We are actively monitoring service performance.

5. investigating 2025-12-12 17:47 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.

6. investigating 2025-12-12 17:48 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.

7. resolved 2025-12-12 18:04 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.

Excerpts are shortened. Read the full incident on Cerebras's status page.

Failure mode: AI model returned degraded, wrong or empty output (not errors or timeouts). Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with medium confidence (taxonomy v0.2).

1. resolved 2025-12-11 09:30 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.

Excerpts are shortened. Read the full incident on Cerebras's status page.

Affected: GPT-OSS-120B, Developer Console

Failure mode: A provider or third-party service this vendor depends on failed. Root cause: A failure at a provider or vendor they depend on. Tagged by claude-haiku-5-5 with high confidence (taxonomy v0.2).

1. investigating 2025-11-18 12:30 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.

2. investigating 2025-11-18 12:54 UTC

   We are continuing to investigate this issue.

3. investigating 2025-11-18 14:24 UTC

   We are continuing to investigate this issue.

4. identified 2025-11-18 14:41 UTC

   The issue has been identified and a fix is being implemented.

5. monitoring 2025-11-18 14:55 UTC

   A fix has been implemented and we are monitoring the results.

6. monitoring 2025-11-18 14:57 UTC

   The platform is accessible now. We are monitoring to ensure stability.

7. resolved 2025-11-18 15:36 UTC

   This incident has been resolved.

Excerpts are shortened. Read the full incident on Cerebras's status page.

Failure mode: The text does not say enough to tell. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with low confidence (taxonomy v0.2).

1. investigating 2025-11-14 15:48 UTC

   From 06:05 AM some features may be temporarily unavailable with Llama-3.3-70B. We are currently working to resume normal service performance. We will provide further updates as we make progress.

2. monitoring 2025-11-14 16:34 UTC

   We've deployed the fix and Llama-3.3-70B is now recovering. We are actively monitoring service performance.

3. investigating 2025-11-14 17:11 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.

4. resolved 2025-11-14 18:08 UTC

   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.

Excerpts are shortened. Read the full incident on Cerebras's status page.

Failure mode: The text does not say enough to tell. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with low confidence (taxonomy v0.2).

1. investigating 2025-11-08 16:10 UTC

   Some features may be temporarily unavailable with ZAI-GLM-4.6. We are currently working to resume normal service performance. We will provide further updates as we make progress.

2. monitoring 2025-11-08 19:08 UTC

   We are continuing to investigate the issue with ZAI-GLM-4.6. A fix has been deployed, and we are actively monitoring the situation.

3. resolved 2025-11-08 19:40 UTC

   We’ve mitigated the issue impacting ZAI-GLM-4.6, and normal performance has been restored.

Excerpts are shortened. Read the full incident on Cerebras's status page.

Failure mode: The text does not say enough to tell. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with low confidence (taxonomy v0.2).

1. resolved 2025-11-08 09:30 UTC

   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.

Excerpts are shortened. Read the full incident on Cerebras's status page.

Failure mode: The text does not say enough to tell. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with low confidence (taxonomy v0.2).

1. investigating 2025-11-05 23:46 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.

2. investigating 2025-11-05 23:57 UTC

   We are continuing to investigate this issue.

3. resolved 2025-11-06 00:01 UTC

   This incident has been resolved.

Excerpts are shortened. Read the full incident on Cerebras's status page.

Affected: GPT-OSS-120B

Failure mode: Network, DNS, routing or connectivity failure. Root cause: Network or DNS. Tagged by claude-haiku-5-5 with medium confidence (taxonomy v0.2).

1. investigating 2025-10-22 16:18 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.

2. identified 2025-10-22 17:01 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.

3. identified 2025-10-22 18:01 UTC

   Our teams are continuing to work to resolve this issue. We appreciate your patience.

4. monitoring 2025-10-22 19:44 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.

5. resolved 2025-10-22 21:13 UTC

   This incident has been resolved.

Excerpts are shortened. Read the full incident on Cerebras's status page.

Affected: GPT-OSS-120B

Failure mode: A zone, region or data center became unavailable. Root cause: Hardware or facility. Tagged by claude-haiku-5-5 with high confidence (taxonomy v0.2).

1. investigating 2025-10-19 02:37 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...

2. investigating 2025-10-19 02:37 UTC

   We are continuing to investigate this issue.

3. identified 2025-10-19 02:41 UTC

   Update: The issue has been root caused to a city water supply disruption. We are actively working on mitigation.

4. resolved 2025-10-19 14:38 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.

Excerpts are shortened. Read the full incident on Cerebras's status page.

Failure mode: A provider or third-party service this vendor depends on failed. Root cause: A failure at a provider or vendor they depend on. Tagged by claude-haiku-5-5 with low confidence (taxonomy v0.2).

1. investigating 2025-10-16 22:14 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.

2. investigating 2025-10-16 22:59 UTC

   We are continuing to investigate this issue.

3. investigating 2025-10-16 23:00 UTC

   This issue is caused by an internal system dependency, and we are currently working to restore system performance.

4. resolved 2025-10-16 23:04 UTC

   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.

Excerpts are shortened. Read the full incident on Cerebras's status page.

Failure mode: Network, DNS, routing or connectivity failure. Root cause: Network or DNS. Tagged by claude-haiku-5-5 with high confidence (taxonomy v0.2).

1. resolved 2025-10-08 18:30 UTC

   A temporary network issue caused partial degradation for the Qwen-3-480B-Coder from 10:36 AM - 11:09 AM PT. The problem has been mitigated and normal performance has been restored.

Excerpts are shortened. Read the full incident on Cerebras's status page.

Affected: GPT-OSS-120B

Failure mode: Network, DNS, routing or connectivity failure. Root cause: Network or DNS. Tagged by claude-haiku-5-5 with medium confidence (taxonomy v0.2).

1. investigating 2025-09-12 19:13 UTC

   Some users are seeing intermittent 404 errors starting around 8 AM PT on 9/12/2025 due to an API gateway routing issue. Engineering is investigating and is working on a prompt resolution.

2. resolved 2025-09-12 20:38 UTC

   This incident has been resolved.

Excerpts are shortened. Read the full incident on Cerebras's status page.

Affected: GPT-OSS-120B

Failure mode: A zone, region or data center became unavailable. Root cause: Hardware or facility. Tagged by claude-haiku-5-5 with medium confidence (taxonomy v0.2).

1. identified 2025-09-03 06:32 UTC

   Notice: Since approximately 10:40 PM Pacific Time on September 2, 2025, we’ve observed degraded performance due to a datacenter outage. Impact appears limited due to redundancy across other data centers. We will provide further updates as we make progress.

2. resolved 2025-09-03 10:30 UTC

   This incident has been resolved.

Excerpts are shortened. Read the full incident on Cerebras's status page.

Failure mode: Exhausted memory, disk, CPU, queues, connection pools or quotas. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with low confidence (taxonomy v0.2).

1. resolved 2025-08-22 16:46 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.

Excerpts are shortened. Read the full incident on Cerebras's status page.

Failure mode: Exhausted memory, disk, CPU, queues, connection pools or quotas. Root cause: A human mistake during operations. Tagged by claude-haiku-5-5 with medium confidence (taxonomy v0.2).

1. resolved 2025-07-31 18:00 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...

Excerpts are shortened. Read the full incident on Cerebras's status page.

Failure mode: The text does not say enough to tell. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with low confidence (taxonomy v0.2).

1. resolved 2025-07-25 20:00 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.

Excerpts are shortened. Read the full incident on Cerebras's status page.

Failure mode: The text does not say enough to tell. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with low confidence (taxonomy v0.2).

1. resolved 2025-06-25 14:30 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.

Excerpts are shortened. Read the full incident on Cerebras's status page.

Failure mode: The text does not say enough to tell. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with low confidence (taxonomy v0.2).

1. resolved 2025-06-19 19:30 UTC

   Some Llama 3.3-70B requests failed due to 5xx errors. We restored normal service performance at 3:54 PM EST on June 19th.

Excerpts are shortened. Read the full incident on Cerebras's status page.

Failure mode: The text does not say enough to tell. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with low confidence (taxonomy v0.2).

1. resolved 2025-06-19 18:30 UTC

   Llama3.1-8B was unavailable. We restored normal service performance at 3:21 PM EST on June 19th.

Excerpts are shortened. Read the full incident on Cerebras's status page.

Failure mode: AI model returned degraded, wrong or empty output (not errors or timeouts). Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with medium confidence (taxonomy v0.2).

1. resolved 2025-06-08 03:30 UTC

   Some Llama 3.3-70B prompts contained corrupt responses. We restored normal service performance at 1 AM PST on June 9th.

Excerpts are shortened. Read the full incident on Cerebras's status page.

Failure mode: The text does not say enough to tell. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with low confidence (taxonomy v0.2).

1. investigating 2025-05-23 03:54 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.

2. identified 2025-05-23 05:29 UTC

   The issue has been identified and a fix is being implemented.

3. identified 2025-05-23 05:51 UTC

   Service back to normal

4. resolved 2025-05-23 13:42 UTC

   This issue is now resolved.

Excerpts are shortened. Read the full incident on Cerebras's status page.

Failure mode: Orchestration, control plane, service discovery or load balancing failed. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with low confidence (taxonomy v0.2).

1. investigating 2025-04-30 23:20 UTC

   This issue is caused by an internal system dependency, and we are currently working to restore system performance.

2. identified 2025-05-01 02:09 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.

3. resolved 2025-05-01 03:32 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.

Excerpts are shortened. Read the full incident on Cerebras's status page.

Failure mode: The text does not say enough to tell. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with low confidence (taxonomy v0.2).

1. investigating 2025-04-08 00:28 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.

2. monitoring 2025-04-08 03:48 UTC

   We've deployed the fix and Llama3.1-8B is now recovering. We are actively monitoring service performance.

3. investigating 2025-04-08 04:18 UTC

   Between 00:28 UTC and 02:58 UTC users experienced partial degradation with Llama3.1-8B. We have deployed a fix and the issue is now resolved.

4. resolved 2025-04-08 04:19 UTC

   Between 00:28 UTC and 02:58 UTC users experienced partial degradation with Llama3.1-8B. We have deployed a fix and the issue is now resolved.

Excerpts are shortened. Read the full incident on Cerebras's status page.

Failure mode: The text does not say enough to tell. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with low confidence (taxonomy v0.2).

1. investigating 2025-04-08 00:27 UTC

   The service is currently inaccessible. We are currently working urgently to restore service capabilities. We will provide further updates as we make progress.

2. investigating 2025-04-08 01:34 UTC

   Between 23:10 UTC and 00:15 UTC users experienced service disruption with DeepSeek-R1-Distill-Llama-70B. We have deployed a fix and the issue is now resolved.

3. investigating 2025-04-08 01:34 UTC

   We are continuing to investigate this issue.

4. resolved 2025-04-08 01:35 UTC

   This incident has been resolved.

Excerpts are shortened. Read the full incident on Cerebras's status page.

Failure mode: A code release introduced the failure. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with low confidence (taxonomy v0.2).

1. identified 2025-03-09 14:03 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.

2. monitoring 2025-03-09 19:14 UTC

   We've deployed the fix and Llama-3.3-70B and DeepSeek-R1-Distill-Llama-70B are now recovering. We are actively monitoring service performance.

3. investigating 2025-03-09 19:38 UTC

   Between March 9th 14:03 UTC and March 10th 16:03 UTC users experienced a minor performance degradation with Llama-3.3-70B and DeepSeek-R1-Distill-Llama-70B. The issue is now resolved.

4. investigating 2025-03-09 19:38 UTC

   Resolved

5. resolved 2025-03-09 19:38 UTC

   This incident has been resolved.

Excerpts are shortened. Read the full incident on Cerebras's status page.

Failure mode: The text does not say enough to tell. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with low confidence (taxonomy v0.2).

1. investigating 2025-02-11 19:56 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.

2. investigating 2025-02-11 20:06 UTC

   We are continuing to investigate this issue.

3. resolved 2025-02-11 20:07 UTC

   Between 7:30 PM UTC and 8:00 PM UTC users experienced service disruption with Llama 3.3 70b and Llama 3.1 8b. We have deployed a fix and the issue is now resolved.

Excerpts are shortened. Read the full incident on Cerebras's status page.

Failure mode: The text does not say enough to tell. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with low confidence (taxonomy v0.2).

1. monitoring 2025-01-12 14:42 UTC

   We've deployed the fix and is now recovering. We are actively monitoring service performance.

2. investigating 2025-01-12 14:59 UTC

   Between 6:15 AM PST and 6:35 AM PST users experienced service disruption with Llama 3.3 70b. We have deployed a fix and the issue is now resolved.

3. resolved 2025-01-12 15:00 UTC

   Between 6:15 AM PST and 6:35 AM PST users experienced service disruption with Llama 3.3 70b. We have deployed a fix and the issue is now resolved.

Excerpts are shortened. Read the full incident on Cerebras's status page.

Failure mode: The text does not say enough to tell. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with low confidence (taxonomy v0.2).

1. monitoring 2025-01-11 02:00 UTC

   We've deployed a fix and the service is now recovering. We are actively monitoring service performance.

2. resolved 2025-01-11 03:12 UTC

   This incident has been resolved.

Excerpts are shortened. Read the full incident on Cerebras's status page.