AI APIs / Inference API / Groq

Groq

OPERATIONAL

Since Sep 2025 · 25 incidents · groqstatus.com · checked just now

CompareStatus page
GradeBLast 90 days
BPRODA+SHIP

Overview

30d90d1y
Admitted uptimeTime not covered by a Sev 1 the provider posted itself. A best case.
100.000%Grade B
IncidentsEverything posted on the status page except scheduled maintenance.
30 Sev 1
Sev 1 downtimeTotal minutes of Sev 1 incidents, as posted.
0m
Median fixMedian time to resolve. Half of incidents were fixed faster.
23m
LongestLongest single incident, start to resolved.
6h 05m
Since lastTime since the last counted incident was resolved.
10d 1h

By area

BProduction
2INCIDENTS
6h 24mAFFECTED
Your users are hit: apps, APIs, databases, inference
Worst, 30d
SEV 2Oct 10, 2026 · 6h 05mModel Performance or Availability Issue - minimaxai/minimax-m2.7
SEV 2Oct 12, 2026 · 18mModel Performance or Availability Issue
Better. 3 in the last 6 months, 12 in the 6 before.
A+Shipping
1INCIDENTS
23mAFFECTED
You can't deploy, build or manage: CI, CLI, dashboard, auth, billing
Worst, 30d
SEV 3Oct 12, 2026 · 23mGroqCloud Console Errors Affecting Multiple Regions
Worse. 1 in the last 6 months, 0 in the 6 before.
CleanSev 3–4Sev 1–2No data

Trend, last 12 months

Better. 4 in the last 6 months, 13 in the 6 before.

Severity mix

Sev 1 · Lights outProd site, API or database down, or data loss0
Sev 2 · BleedingProd degraded or partly down2
Sev 3 · Can't shipCan't deploy, build or manage it1
Sev 4 · PapercutDocs, status page, slow dashboard0

When it breaks

Start times, last 12 months, UTC.

What breaks

No components named in the last 12 months.

Communication

Updates eachStatus page updates per incident, on average.
5.5Last 12 months
Update gapMedian time between status page updates during an incident.
22mLast 12 months
PostmortemsSev 1–2 incidents with a published write-up.
0 of 15Sev 1–2

Incident history

Show all 23
Oct 12, 202618mSEV 2
Model Performance or Availability IssueAPI failures for one model, minimax-m2.7, for about 18 minutes due to hardware connectivity issues; other models not described as affected.AI-graded · some customers
Why this grade
  1. RULES · SEV 1
    Sev 1 from the incident title (no components listed)
  2. CLAUDE · SEV 2 · SUBSET · HIGH CONFIDENCE
    API failures for one model, minimax-m2.7, for about 18 minutes due to hardware connectivity issues; other models not described as affected.
  3. Claude Haiku 5.5 · prompt v5 · Oct 22, 2026 · Raw record
2 updates
  1. 18:17 UTC · identified
    We have **identified the problem** affecting the **minimaxai/minimax-m2.7** service. The issue was traced to **hardware connectivity issues**. A fix is in progress. Users may still see **API failures** until the fix completes.
  2. 18:36 UTC · resolved
    The issues affecting **minimaxai/minimax-m2.7** have been **resolved**. The model is operating normally. Root cause: **hardware connectivity issues**. We apologize for the disruption and thank you for your patience.
Source
Oct 12, 202623mSEV 3
GroqCloud Console Errors Affecting Multiple RegionsGroqCloud console showed increased 500 errors on metrics, the /models endpoint, and API key creation, starting 03:37 UTC. Inference API requests were not affected. Groq mitigated the errors by 03:47 and resolved the issue at 04:00 UTC.AI-graded
Why this grade
  1. RULES · SEV 4
    Sev 4 from the incident title (no components listed)
  2. CLAUDE · SEV 3 · UNCLEAR · MEDIUM CONFIDENCE
    GroqCloud console errors, including API key creation, lasted about 23 minutes; inference APIs were not affected.
  3. Claude Haiku 5.5 · prompt v5 · Oct 22, 2026 · Raw record
3 updates
  1. 03:37 UTC · investigating
    We are currently investigating **increased error rates** on our GroqCloud console (including metrics, /models API endpoints, and API key creation). **Users may receive 500 errors** when making requests to **console.groq.com**. Our engineers are isolating the issue.
  2. 03:47 UTC · monitoring
    We've **mitigated the errors** on the GroqCloud console and functionality has been restored. Inference API requests are not affected, and we will provide additional updates here.
  3. 04:00 UTC · resolved
    The **Groqcloud console issue has been resolved**. All services are operating normally. We apologize for the disruption and **appreciate your patience**.
Source
Oct 10, 20266h 05mSEV 2
Model Performance or Availability Issue - minimaxai/minimax-m2.7Requests to one enterprise-only model failed for about six hours due to data center hardware issues; other models were not described as affected.AI-graded · some customers
Why this grade
  1. RULES · SEV 2
    Sev 2 from the incident title (no components listed)
  2. CLAUDE · SEV 2 · SUBSET · HIGH CONFIDENCE
    Requests to one enterprise-only model failed for about six hours due to data center hardware issues; other models were not described as affected.
  3. Claude Haiku 5.5 · prompt v5 · Oct 22, 2026 · Raw record
2 updates
  1. 10:09 UTC · identified
    We have **identified the problem** affecting the enterprise-only **minimaxai/minimax-m2.7** model. The issue was traced to **hardware issues in our data center**. A fix is in progress. Users may still see **failed requests** until the fix completes.
  2. 16:14 UTC · resolved
    The issues affecting **minimaxai/minimax-m2.7** have been **resolved**. The model is operating normally. Root cause: **Data center hardware issues**. We apologize for the disruption and thank you for your patience.
Source
Jul 1, 20261h 34mSEV 2
Data Center Failure Impacting CapacityA power loss led to a cooling failure at one US Central data center, reducing capacity and raising latency, mainly for openai/gpt-oss-20b. Capacity was reallocated to production models and the incident was resolved after about 95 minutes.AI-graded · regional
Why this grade
  1. RULES · SEV 2
    Sev 2 from the incident title (no components listed)
  2. CLAUDE · SEV 2 · REGIONAL · HIGH CONFIDENCE
    Elevated latencies and reduced capacity in US Central, mainly for gpt-oss-20b, after a cooling failure; other regions were unaffected.
  3. Claude Haiku 5.5 · prompt v5 · Oct 22, 2026 · Raw record
5 updates
  1. 23:01 UTC · investigating
    We are currently investigating a potential issue at one of our US Central data centers that is impacting system capacity. Users **may experience higher latencies** due to reduced resources. Our engineering team is working to identify the root cause and remediate the problem.
  2. 23:11 UTC · identified
    We have **identified a cooling system failure** at one of our **US Central** data centers that is causing **reduced capacity**. The team is **working on restoring capacity**. Users **continue to see elevated latencies for specific models**.
  3. 23:27 UTC · identified
    A power loss issue at approximately 22:20pm UTC led to a subsequent **cooling system failure** at one of our **US Central** data centers that is causing **reduced capacity**, primarily for the `openai/gpt-oss-20b` model. The team is **working on restoring capacity**.
  4. 23:48 UTC · monitoring
    We have **redistributed and allocated more capacity to production models** in **the US Central region.** Users should **see performance return to normal**. We’re now **monitoring** the infrastructure to ensure stability.
  5. 00:35 UTC · resolved
    The **capacity issue has been resolved**. All services are operating at normal capacity. The incident was caused by a **power loss issue that led to a cooling system failure at one of our US Central data centers**. We apologize for any disruption and **appreciate your patience**.
Source
Mar 19, 202659mSEV 1 · SECURITY
openai/gpt-oss-120b Performance IssueSev 2 from the incident title (no components listed), raised to Sev 1 for security
3 updates
  1. 12:51 UTC · identified
    We have identified the problem affecting the openai/gpt-oss-120b model. The issue has been traced to malicious traffic patterns. A fix is in progress, we are working to block the source of these requests. Users may still see degraded performance from requests made to openai/gpt-oss-120b as we identify and block the orgs from which this traffic is originating.
  2. 13:23 UTC · monitoring
    We have implemented a fix for openai/gpt-oss-120b and performance is improving. We’re now monitoring the model to ensure stability persists. If all remains normal, we will resolve the incident in the next update.
  3. 13:50 UTC · resolved
    The issues affecting openai/gpt-oss-120b have been **resolved**. The model is operating normally. Actions were taken to cancel billing plans and restrict verification status of organizations engaged in coordinated abuse. We apologize for the disruption and thank you for your patience.
Source
Feb 7, 20261h 33mSEV 2
meta-llama/llama-4-scout-17b-16e-instruct Degraded PerformanceSev 2 from the incident title (no components listed)
5 updates
  1. 10:02 UTC · investigating
    We are currently investigating reports of an issue with meta-llama/llama-4-scout-17b-16e-instruct. Users may be experiencing **elevated error rates and or slow responses**. Other models remain operational. Our team is analyzing logs and infrastructure to identify the cause.
  2. 10:36 UTC · investigating
    We are continuing to investigating an issue with meta-llama/llama-4-scout-17b-16e-instruct. Users may be experiencing elevated error rates or slow response time. Other models remain operational. Our team is continuing to analyze logs and infrastructure to identify the cause.
  3. 10:59 UTC · identified
    We have implemented a fix for meta-llama/llama-4-scout-17b-16e-instruct however performance is still degraded. We’re continuing to investigate the models to determine the cause of the issues.
  4. 11:13 UTC · monitoring
    We have implemented a new fix for meta-llama/llama-4-scout-17b-16e-instruct & groq/compound and performance has improved. We’re continuing monitor the models to ensure stability persists. If all remains normal, we will resolve the incident in the next update.
  5. 11:34 UTC · resolved
    This incident has been resolved. Thank you for your patience.
Source
Feb 5, 202623mSEV 2
meta-llama/llama-4-scout-17b-16e-instruct Degraded PerformanceSev 2 from the incident title (no components listed)
3 updates
  1. 18:09 UTC · investigating
    We are currently investigating reports of an issue with meta-llama/llama-4-scout-17b-16e-instruct. Users may be experiencing **elevated error rates and or slow responses**. Other models remain operational. Our team is analyzing logs and infrastructure to identify the cause.
  2. 18:21 UTC · monitoring
    meta-llama/llama-4-scout-17b-16e-instruct and performance is improving. We’re now **monitoring** the model to ensure stability. If all remains normal, we will resolve the incident in the next update.
  3. 18:32 UTC · resolved
    The issues affecting meta-llama/llama-4-scout-17b-16e-instruct have been **resolved**. The model is once again operating normally. We apologize for the disruption and thank you for your patience.
Source
Feb 5, 20261h 44mSEV 2
meta-llama/llama-4-scout-17b-16e-instruct Degraded PerformanceSev 2 from the incident title (no components listed)
5 updates
  1. 13:23 UTC · investigating
    We are currently investigating reports of an issue with meta-llama/llama-4-scout-17b-16e-instruct. Users may be experiencing **elevated error rates and or slow responses**. Other models remain operational. Our team is analyzing logs and infrastructure to identify the cause.
  2. 13:33 UTC · identified
    We have **identified the problem** affecting the meta-llama/llama-4-scout-17b-16e-instruct. A fix is in progress, users may still see delayed responses and errors from Scout until the fix completes.
  3. 13:43 UTC · monitoring
    We have **implemented a fix** for meta-llama/llama-4-scout-17b-16e-instruct and performance is improving. We’re now **monitoring** the model to ensure stability. If all remains normal, we will resolve the incident in the next update.
  4. 14:47 UTC · monitoring
    We’re continuing to **monitor** the scout model to ensure stability persists. If all remains normal, we will resolve the incident in the next update.
  5. 15:07 UTC · resolved
    The issues affecting meta-llama/llama-4-scout-17b-16e-instruct have been fully **resolved**. The model is operating normally. We apologize for the disruption and thank you for your patience.
Source
Jan 26, 20261h 54mSEV 2
meta-llama/llama-4-scout-17b-16e-instruct Degraded PerformanceSev 2 from the incident title (no components listed)
4 updates
  1. 23:17 UTC · investigating
    We are currently investigating an issue with meta-llama/llama-4-scout-17b-16e-instruct. Users may be experiencing elevated error rates or slow response time. Other models remain operational. Our team is analyzing logs and infrastructure to identify the cause.
  2. 00:06 UTC · identified
    We have implemented a fix for meta-llama/llama-4-scout-17b-16e-instruct however performance is still degraded. We’re continuing to investigate the models to determine the cause of the issues.
  3. 00:29 UTC · monitoring
    We have implemented a new fix for meta-llama/llama-4-scout-17b-16e-instruct & groq/compound and performance has improved. We’re continuing monitor the models to ensure stability persists. If all remains normal, we will resolve the incident in the next update.
  4. 01:11 UTC · resolved
    This incident has been resolved. Thank you for your patience.
Source
Jan 24, 20262h 31mSEV 2
Data Center Failure Impacting Model Latency - SYDSev 2 from the incident title (no components listed)
5 updates
  1. 04:53 UTC · identified
    We have **identified an issue in our Sydney, AUS data center** that may be causing some latency for customers in this region. The issue was traced to **a network issue**. Users may still see latency until the fix completes.
  2. 05:26 UTC · identified
    The team is still working to resolve the issue at our SYD Data Center. Customers in the area may still be experiencing some model latency. We will provide further updates at they are available.
  3. 07:06 UTC · monitoring
    The issue impacting our SYD data center has been fixed. Users should gradually see performance return to normal as we continue to recover all models. We will continue to monitor.
  4. 07:14 UTC · monitoring
    This issue is now resolved. All services are operating normally. We will continue to monitor for stability and resolve this incident shortly. Thank you for your patience.
  5. 07:23 UTC · resolved
    This incident is now resolved.
Source
Dec 24, 20251h 15mSEV 2
Model Performance or Availability Issue: llama-3.3-70b-versatileSev 2 from the incident title (no components listed)
3 updates
  1. 23:01 UTC · identified
    We’ve identified an issue causing 503s for the `llama-3.3-70b-versatile` production model. We’ve started mitigation. Error rates are improving, but some requests may still fail while we continue tuning and monitoring.
  2. 00:04 UTC · monitoring
    We have **implemented a fix** for **llama-3.3-70b-versatile** and performance is improving. The team is continuing to work the issue and we hope to have it resolved shortly.
  3. 00:16 UTC · resolved
    The issues affecting **llama-3.3-70b-versatile** have been **resolved**. The model is operating normally. We apologize for the disruption and thank you for your patience.
Source
Dec 17, 20250mSEV 2
Data Center Failure Impacting Capacity - DMM1Sev 2 from the incident title (no components listed)
4 updates
  1. 09:46 UTC · investigating
    We are currently investigating a potential network issue at our DMM1 that is impacting system capacity. Users may experience slower response times or intermittent failures due to reduced resources. Our engineering team is working to identify the root cause and remediate the problem.
  2. 10:12 UTC · identified
    We have identified a failure in our DMM1 infrastructure that is causing reduced capacity and network latency. The team has isolated the cause to the Salam link confirmed down and the Mobily link operating at full capacity, resulting in significant packet loss and is working on restoring capacity. Users continue to see Network latency.
  3. 10:30 UTC · monitoring
    We have restored capacity in DMM 1 and services are beginning to recover. Users should gradually see network performance return to normal. We’re now monitoring the infrastructure to ensure stability.
  4. 13:30 UTC · resolved
    **The data center capacity issue has been resolved. All services are operating at normal capacity. The incident was caused by a failed ARP entry on the network gateway device caused the Salam network link to go down in the DMM1 data center, which has been addressed. We apologize for the disruption and appreciate your patience.**
Source
Dec 6, 20251h 25mSEV 2
meta-llama/llama-4-scout-17b-16e-instruct Degraded PerformanceSev 2 from the incident title (no components listed)
5 updates
  1. 18:58 UTC · investigating
    We are currently investigating reports of an issue with our meta-llama/llama-4-scout-17b-16e-instruct & groq/compound models. Users may be experiencing elevated error rates and or slow responses. Other models remain operational. Our team is analyzing logs and infrastructure to identify the cause.
  2. 19:32 UTC · investigating
    We are now seeing similar degradation on meta-llama/llama-4-maverick-17b-128e-instruct. The team is still investigating the issue and working to resolve.
  3. 19:59 UTC · investigating
    We are no longer seeing issues on meta-llama/llama-4-maverick-17b-128e-instruct. However, the team is still troubleshooting errors and latency issues with meta-llama/llama-4-scout-17b-16e-instruct.
  4. 20:16 UTC · monitoring
    We have implemented a new fix for meta-llama/llama-4-scout-17b-16e-instruct and performance and have observed improvement over the last 15 minutes. We’re continuing monitor to ensure stability persists. If all remains normal, we will resolve the incident in the next update. In addition to meta-llama/llama-4-scout-17b-16e-instruct, we realized there also was some impact to groq/compound, which has also recovered.
  5. 20:23 UTC · resolved
    The issues affecting meta-llama/llama-4-scout-17b-16e-instruct , meta-llama/llama-4-maverick-17b-128e-instruct, & groq/compound have been **resolved**. The models are operating normally. We apologize for the disruption and thank you for your patience.
Source
Dec 2, 20252h 26mSEV 2
meta-llama/llama-4-scout-17b-16e-instruct & groq/compound Degraded PerformanceSev 2 from the incident title (no components listed)
5 updates
  1. 17:36 UTC · investigating
    We are currently investigating reports of an issue with our meta-llama/llama-4-scout-17b-16e-instruct & groq/compound models. Users may be experiencing **elevated error rates and or slow responses**. Other models remain operational. Our team is analyzing logs and infrastructure to identify the cause.
  2. 17:51 UTC · monitoring
    We have **implemented a fix** for meta-llama/llama-4-scout-17b-16e-instruct & groq/compound and performance is improving. We’re now **monitoring** the models to ensure stability. If all remains normal, we will resolve the incident in the next update.
  3. 18:06 UTC · investigating
    We have implemented a fix for meta-llama/llama-4-scout-17b-16e-instruct & groq/compound however performance is still degraded. We’re continuing to investigate the models to determine the cause of the issues.
  4. 18:31 UTC · monitoring
    We have **implemented a new fix** for meta-llama/llama-4-scout-17b-16e-instruct & groq/compound and performance has improved. We’re continuing **monitor** the models to ensure stability persists. If all remains normal, we will resolve the incident in the next update.
  5. 20:02 UTC · resolved
    The issues affecting meta-llama/llama-4-scout-17b-16e-instruct & groq/compound have been **resolved**. Both of the models are operating normally. We apologize for the disruption and thank you for your patience.
Source
Nov 18, 20253h 33mSEV 4
Console, Website, & API Availability Issues: Global Cloudflare OutageSev 4 from the incident title (no components listed)
8 updates
  1. 11:52 UTC · identified
    We are currently investigating an issue with our services that we believe is impacting customer experiences. Our team is has identified that is due to a [global cloudflare outage](https://www.cloudflarestatus.com/incidents/8gmgl950y3h7 "global cloudflare outage") and is working to remediate the problem and will follow up shortly with more details.
  2. 12:15 UTC · monitoring
    We are currently monitoring an issue with our services that is impacting customer experiences. Our team is has identified that is due to an ongoing [global cloudflare outage](https://www.cloudflarestatus.com/incidents/8gmgl950y3h7 "global cloudflare outage") and is working to remediate the problem and will follow up with more details as they become available from Cloudflare.
  3. 12:31 UTC · monitoring
    We are continuing to monitor an issue with our services that is impacting customer experiences. Our team is has identified that is due to an ongoing [global cloudflare outage](https://www.cloudflarestatus.com/incidents/8gmgl950y3h7 "global cloudflare outage") and they've recently shared that "We are seeing services recover, but customers may continue to observe higher-than-normal error rates as we continue remediation efforts". This aligns with recent improvements observed in our request traffic but higher-than-normal error rates still persist.
  4. 13:04 UTC · monitoring
    We are continuing to monitor an issue with our services that is impacting customer experiences due to an ongoing [global cloudflare outage](https://www.cloudflarestatus.com/incidents/8gmgl950y3h7 "global cloudflare outage"). Cloudflare recently shared that "The are continuing to investigate the issue". We are continuing to observe higher-than-normal error rates despite Cloudflare's previous update stating that they were seeing services recover.
  5. 13:35 UTC · monitoring
    We are continuing to monitor an issue with our services that is impacting customer experiences due to an ongoing [global cloudflare outage](https://www.cloudflarestatus.com/incidents/8gmgl950y3h7 "global cloudflare outage"). Cloudflare recently shared that "We are continuing to work towards restoring other services" and "The issue has been identified and a fix is being implemented". We are continuing to observe higher-than-normal error rates and are monitoring for signs of recovery as Cloudflare works to implement a fix.
  6. 14:09 UTC · monitoring
    We are continuing to monitor an issue with our services that is impacting customer experiences due to an ongoing [global cloudflare outage](https://www.cloudflarestatus.com/incidents/8gmgl950y3h7 "global cloudflare outage"). Cloudflare previously shared that "We are continuing to work towards restoring other services" and "The issue has been identified and a fix is being implemented". We are continuing to observe higher-than-normal error rates and are continuing to monitor for signs of recovery as Cloudflare works to implement a fix.
  7. 14:48 UTC · monitoring
    We are continuing to monitor an issue with our services that is impacting customer experiences due to an ongoing [global cloudflare outage](https://www.cloudflarestatus.com/incidents/8gmgl950y3h7 "global cloudflare outage"). Cloudflare has just shared that "A fix has been implemented and we believe the incident is now resolved. We are continuing to monitor for errors to ensure all services are back to normal.". We are monitoring to confirm the restoration of service availability and successful requests and are continuing to monitor for signs of persistent recovery as Cloudflare now claims to have implemented a fix.
  8. 15:26 UTC · resolved
    We are resolving this incident as we have now observed ~30 minutes of normalized service availability and customer traffic. We will continue to closely monitor our systems for any signs of regression as [Cloudflare's statuspage incident remains active ](https://www.cloudflarestatus.com/incidents/8gmgl950y3h7)and in monitoring.
Source
Nov 5, 202535mSEV 2
Cloud API DegradationSev 2 from the incident title (no components listed)
4 updates
  1. 20:03 UTC · investigating
    We are currently investigating an issue resulting in a performance degradation of our Cloud API. Users may be experiencing **elevated error rates and or slow responses**. Our team is analyzing logs and infrastructure to identify the cause and implement a fix as soon as possible.
  2. 20:13 UTC · identified
    We have **identified the problem** causing performance degradation of our Cloud API. A fix is in progress, users may still see elevated error rates and or slow responses until the fix completes. Our team is working on getting this fix rolled out as soon as possible.
  3. 20:24 UTC · monitoring
    We have **implemented a fix** for the performance degradation of our Cloud API and performance is improving. We’re now **monitoring** the fix to ensure stability persists. If all remains normal, we will resolve the incident in the next update.
  4. 20:37 UTC · resolved
    The issues causing degraded performance have been **resolved**. All models are now operating normally. Upon investigation we learned the issue was scoped to an internal feature yet to be released that is still in development. At this time we don't believe there was any customer impact as a direct result of this issue. We apologize for the disruption and thank you for your patience.
Source
Nov 4, 202537mSEV 2
Model Performance Issue: llama-3.1-8b-instantSev 2 from the incident title (no components listed)
3 updates
  1. 02:11 UTC · identified
    We have **identified an issue** affecting the lama-3.1-8b-instant service. A fix is in progress. Users may still experience latency until the fix completes.
  2. 02:33 UTC · monitoring
    We have **implemented a fix** for llama-3.1-8b-instant service and performance is improving. We’re now **monitoring** the model to ensure stability. If all remains normal, we will resolve the incident in the next update.
  3. 02:47 UTC · resolved
    The issues affecting llama-3.1-8b-instant have been **resolved**. The model is operating normally. Root cause: Two recent changes to the inference-engine-instances repository that were contributing to the elevated Orion LoRA latencies were reverted . We apologize for the disruption and thank you for your patience.
Source
Oct 22, 20252h 08mSEV 2
openai/gpt-oss-120b Degraded PerformanceSev 2 from the incident title (no components listed)
5 updates
  1. 15:51 UTC · investigating
    We are currently investigating reports of an issue with ouropenai/gpt-oss-120b. Users may be experiencing elevated error rates and or slow responses. Other models remain operational. Our team is analyzing traces, logs and infrastructure to identify the cause.
  2. 16:22 UTC · investigating
    We are continuing to investigate issues with our openai/gpt-oss-120b model. Users may be experiencing elevated error rates and or slow responses. Other models remain operational. Our team is analyzing traces, logs and infrastructure to identify the cause.
  3. 17:17 UTC · investigating
    We are continuing to investigate issues with our openai/gpt-oss-120b model. Users may be experiencing elevated error rates and or slow responses. Other models remain operational. Our team is analyzing traces, logs and infrastructure to identify the cause.
  4. 17:46 UTC · investigating
    We are continuing to investigate issues with our openai/gpt-oss-120b model. Users may be experiencing or slow responses. Other models remain operational. Our team is analyzing traces, logs and infrastructure to identify the cause.
  5. 17:59 UTC · resolved
    The latency issues affecting openai/gpt-oss-120b have been resolved. The model is now operating normally and latency has returned to expected ranges. We apologize for the disruption and thank you for your patience.
Source
Oct 21, 20251h 53mSEV 2
openai/gpt-oss-120b Degraded PerformanceSev 2 from the incident title (no components listed)
4 updates
  1. 15:19 UTC · investigating
    We are currently investigating reports of an issue with our openai/gpt-oss-120b model. Users may be experiencing **elevated error rates and or slow responses**. Other models remain operational. Our team is analyzing logs and infrastructure to identify the cause.
  2. 15:45 UTC · identified
    We have **identified a problem** affecting the openai/gpt-oss-120b service. The issue was traced to . A fix is in progress, which may take some time to implement. Users may still see elevated error rates or delayed responses until the fix is in place.
  3. 16:47 UTC · monitoring
    We are actively implementing a fix for openai/gpt-oss-120b and we expect performance to begin improving shortly. We’ll be monitoring the model to ensure stability as this fix rolls out. If all remains normal, we will resolve the incident in the next update.
  4. 17:12 UTC · resolved
    The issues affecting openai/gpt-oss-120b have been **resolved**. The model is operating normally. We apologize for the disruption and thank you for your patience.
Source
Oct 14, 20252h 02mSEV 2
meta-llama/llama-4-scout-17b-16e-instruct & groq/compound Degraded PerformanceSev 2 from the incident title (no components listed)
5 updates
  1. 21:16 UTC · investigating
    We are currently investigating reports of an issue with our meta-llama/llama-4-scout-17b-16e-instruct model. Users may be experiencing **elevated error rates and or slow responses**. Other models remain operational. Our team is analyzing metrics and logs to identify the cause.
  2. 21:48 UTC · investigating
    We are continuing to investigate an issue with our meta-llama/llama-4-scout-17b-16e-instruct model. Users may be experiencing **elevated error rates and or slow responses**. Other models remain operational.
  3. 22:30 UTC · investigating
    We are still working to identify the root cause of the issue with our meta-llama/llama-4-scout-17b-16e-instruct model. As part of the investigation our team has implemented additional logging to pinpoint the issue. Users may still be experiencing elevated error rates and or slow responses. Other models remain operational.
  4. 22:50 UTC · monitoring
    We have implemented a fix for the issue impacting our meta-llama/llama-4-scout-17b-16e-instruct model and performance has improved. We’re now **monitoring** the model to ensure stability. If all remains normal, we will resolve the incident in the next update.
  5. 23:18 UTC · resolved
    The issues affecting meta-llama/llama-4-scout-17b-16e-instruct have been **resolved**. The model is operating normally. We apologize for the disruption and thank you for your patience.
Source

Peers, 90 days

Compare
GroqGrade B100.00% up3 incidentsMTTR 23mCohereGrade C100.00% up2 incidentsMTTR 4h 22mOpenAI APIGrade C100.00% up27 incidentsMTTR 1h 38mAnthropic APIGrade D99.97% up50 incidentsMTTR 1h 13m

README badge

Groq's live grade, for your README.

Groq grade badge
[![groq on downagain.dev](https://downagain.dev/badge/groq.svg)](https://downagain.dev/p/groq)