">
sevanalysis

Baseten

AI. Source: Baseten status page.

Incidents, last 90 days
29
Median duration
37m
p95 duration
1h 22m
Naming an upstream provider
3%
With a postmortem on the status page
0%

What failed, last 90 days

The text does not say enough to tell17
A zone, region or data center became unavailable5
A provider or third-party service this vendor depends on failed4
Data delayed, stale, lost or corrupted, or needing replay after recovery2
Exhausted memory, disk, CPU, queues, connection pools or quotas1

Tagged by claude-haiku-5-5 from each incident's updates. See the methodology.

Incidents per month

Hatched months are before the recorded history starts.

All recorded incidents

Elevated errors on DeepSeek V4 Flash on Model APIs minor 2026-10-21 01:48 UTC 40m

Affected: Model APIs

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

    We are currently investigating this issue.

  2. resolved

    This incident has been resolved.

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

Elevated errors for image requests on multiple Model APIs minor 2026-10-21 01:05 UTC 21m

Affected: Model APIs

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

    There are elevated errors for image requests on Deepseek V4 Flash and GLM 5.3 Flash

  2. investigating

    GLM 5.3 Flash has recovered, we continue to see degraded performance on Deepseek V4 Flash

  3. resolved

    This incident has been resolved.

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

DeepSeek V4.1 Flash Fast Outage on Model APIs major 2026-10-20 19:04 UTC 6m

Affected: Model APIs

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

    We are currently investigating this issue.

  2. resolved

    This incident has been resolved.

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

Elevated errors on Model APIs minor 2026-10-20 01:35 UTC 8m

Affected: Model APIs

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

    Elevated errors across Model APIs due to provider outage

  2. monitoring

    A fix has been implemented and we are seeing recovery on all models

  3. resolved

    This incident has been resolved.

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

Elevated errors on new model builds. Existing models are not affected minor 2026-10-09 21:29 UTC 37m

Affected: Model Management API

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

    We are currently investigating this issue.

  2. monitoring

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

  3. resolved

    This incident has been resolved.

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

DeepSeek v4.1 outage on Model APIs. Dedicated Inference is not affected major 2026-10-06 04:35 UTC 13m

Affected: Model APIs

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

    We are currently investigating this issue.

  2. resolved

    This incident has been resolved.

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

Elevated 500s in Single us-central Region major 2026-09-29 08:12 UTC 11h 45m

Affected: Dedicated Inference

Failure mode: A zone, region or data center became unavailable. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with medium confidence (taxonomy v0.2).

  1. identified

    The issue has been identified and we're looking into a fix.

  2. monitoring

    A fix has been implemented and we're monitoring the results.

  3. resolved

    This incident has been resolved.

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

Metrics degradation in UI and API. **Inference not affected** minor 2026-09-29 01:07 UTC 21m

Affected: Model Management API, Web Application

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

    We are currently investigating this issue.

  2. investigating

    We are continuing to investigate this issue.

  3. resolved

    This incident has been resolved.

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

Intermittent 5xx for a subset of models in 1 US Central cluster minor 2026-09-24 18:35 UTC 1h 22m

Affected: Dedicated Inference

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

    We are currently investigating this issue.

  2. investigating

    0.15% of requests on this cluster resulted in a 5xx error, confined to two 2-3 min spikes. The team is continuing to investigate.

  3. resolved

    This incident has been resolved.

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

Elevated inference 500s for a subset of models deployed in 1 US-East cluster major 2026-09-24 07:23 UTC 42m

Affected: Dedicated Inference

Failure mode: A zone, region or data center became unavailable. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with medium confidence (taxonomy v0.2).

  1. identified

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

  2. monitoring

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

  3. monitoring

    We are continuing to monitor for any further issues.

  4. resolved

    This incident has been resolved.

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

Elevated inference 500s for a subset of models deployed in GCP central1 major 2026-09-21 18:34 UTC 7m

Affected: Dedicated Inference

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).

Names an upstream provider: Google Cloud.

  1. identified

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

  2. monitoring

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

  3. resolved

    This incident has been resolved.

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

Metrics degradation in UI and API. **Inference not affected** minor 2026-09-21 13:31 UTC 11m

Affected: Model Management API

Failure mode: Data delayed, stale, lost or corrupted, or needing replay after recovery. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with low confidence (taxonomy v0.2).

  1. investigating

    We are currently investigating this issue.

  2. resolved

    This incident has been resolved.

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

Kimi K3 Model API outage major 2026-09-20 07:19 UTC 55m

Affected: Model APIs

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

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

  2. identified

    ~20% of calls are resulting in errors. A fix is in progress.

  3. identified

    Calls to the US-hosted endpoint are resulting in errors. A fix is in progress.

  4. monitoring

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

  5. resolved

    This incident has been resolved.

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

Elevated errors for models in a single India-based cluster minor 2026-09-15 01:22 UTC 45m

Affected: Dedicated Inference

Failure mode: A zone, region or data center became unavailable. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with medium confidence (taxonomy v0.2).

  1. investigating

    We are currently investigating this issue.

  2. monitoring

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

  3. resolved

    This incident has been resolved.

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

Partial outage on Kimi K3 model API inference (non-US only) minor 2026-09-14 16:21 UTC 42m

Affected: Model APIs

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

    We are currently investigating this issue.

  2. resolved

    This incident has been resolved.

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

Partial outage on Nemotron Ultra Model API. **Dedicated Inference is not affected** minor 2026-09-09 17:42 UTC 6m

Affected: Model APIs

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

    We are currently investigating this issue.

  2. monitoring

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

  3. resolved

    This incident has been resolved.

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

Elevated inference 500s for models in a single US-based cluster major 2026-08-31 06:38 UTC 24m

Affected: Dedicated Inference

Failure mode: A zone, region or data center became unavailable. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with low confidence (taxonomy v0.2).

  1. investigating

    We are currently investigating this issue.

  2. monitoring

    Fix is in place and traffic is back.

  3. resolved

    This incident has been resolved.

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

Elevated errors for models in a single US cluster due to provider outage minor 2026-08-27 21:17 UTC 14m

Affected: Dedicated Inference

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

    We are currently investigating this issue.

  2. monitoring

    Auto-recovery is in progress.

  3. resolved

    This incident has been resolved.

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

Elevated errors for deepseek-ai/DeepSeek-V4-Flash-0731 on Model APIs. **Dedicated Inference is not affected** minor 2026-08-25 16:17 UTC 41m

Affected: Model APIs

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

    We are currently investigating this issue.

  2. monitoring

    A fix is in place and we are monitoring

  3. resolved

    This incident has been resolved.

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

Elevated inference 500s for models in an EU cluster due to provider outage minor 2026-08-25 12:34 UTC 41m

Affected: Dedicated Inference

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. identified

    Failover in progress.

  2. monitoring

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

  3. resolved

    This incident has been resolved.

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

Elevated errors for moonshotai/Kimi-K3 for US-pinned traffic on Model APIs. **Dedicated Inference is not affected** minor 2026-08-19 01:23 UTC 37m

Affected: Model APIs

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

    We are currently investigating this issue.

  2. monitoring

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

  3. resolved

    This incident has been resolved.

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

Elevated errors for moonshotai/Kimi-K3 for US-pinned traffic on Model APIs. **Dedicated Inference is not affected** minor 2026-08-18 19:04 UTC 1h 17m

Affected: Model APIs

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

    We are currently investigating this issue.

  2. monitoring

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

  3. resolved

    This incident has been resolved.

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

Elevated errors for moonshotai/Kimi-K3 for US-pinned traffic on Model APIs. **Dedicated Inference is not affected** minor 2026-08-18 17:24 UTC 12m

Affected: Model APIs

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

    We are currently investigating this issue.

  2. resolved

    This incident has been resolved.

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

Elevated errors for moonshotai/Kimi-K3 for US-pinned traffic on Model APIs. **Dedicated Inference is not affected** minor 2026-08-18 16:27 UTC 48m

Affected: Model APIs

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

    We are currently investigating this issue.

  2. resolved

    This incident has been resolved.

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

Elevated errors for moonshotai/Kimi-K3 for US-pinned traffic minor 2026-08-17 16:56 UTC 46m

Affected: Model APIs

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

    We are currently investigating this issue.

  2. resolved

    This incident has been resolved.

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

Metrics degradation in UI and API. **Inference not affected** minor 2026-08-17 13:11 UTC 24m

Affected: Model Management API, Web Application

Failure mode: Data delayed, stale, lost or corrupted, or needing replay after recovery. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with medium confidence (taxonomy v0.2).

  1. investigating

    We are currently investigating this issue.

  2. monitoring

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

  3. resolved

    This incident has been resolved.

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

Elevated inference 502s for a subset of models in a single US cluster minor 2026-08-01 23:57 UTC 43m

Affected: Dedicated Inference

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

    This is due to a networking failure in a cloud provider.

  2. identified

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

  3. resolved

    This incident has been resolved.

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

Elevated inference 502s for a subset of models in a single US cluster minor 2026-07-31 23:52 UTC 29m

Affected: Dedicated Inference

Failure mode: A zone, region or data center became unavailable. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with medium confidence (taxonomy v0.2).

  1. investigating

    We are currently investigating this issue.

  2. monitoring

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

  3. resolved

    This incident has been resolved.

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

Slower than usual scale-ups for B200s minor 2026-07-31 16:46 UTC 12m

Affected: Dedicated Inference

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. investigating

    We are currently investigating this issue.

  2. resolved

    This incident has been resolved.

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

Elevated inference failures for models in an EU cluster minor 2026-07-22 17:49 UTC 33m

Affected: Dedicated Inference

Failure mode: Hardware, power, cooling or another physical failure. 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. identified

    Failure in GPU provider's cooling system. Models are automatically migrating over to other EU clusters.

  2. identified

    We are continuing to work on a fix for this issue.

  3. resolved

    This incident has been resolved.

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

Slower than usual scale-ups in 1 us-central cluster minor 2026-07-22 17:45 UTC 19m

Affected: Dedicated Inference

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. identified

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

  2. resolved

    This incident has been resolved.

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

GLM 5.2 Model API partial outage due to provider network failure major 2026-07-18 22:40 UTC 32m

Affected: Model APIs

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. identified

    Escalated Dedicated inference is *not* affected.

  2. monitoring

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

  3. monitoring

    We are continuing to monitor for any further issues.

  4. resolved

    This incident has been resolved.

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

Elevated inference errors in 1 Canada cluster due to provider network outage minor 2026-07-18 00:22 UTC 6m

Affected: Dedicated Inference

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. identified

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

  2. resolved

    This incident has been resolved.

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

Elevated errors in accessing the Baseten UI. **Inference is not affected** minor 2026-07-16 09:06 UTC 1h 19m

Affected: Model Management API, Web Application

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

    We are currently investigating this issue.

  2. investigating

    We are continuing to investigate this issue.

  3. monitoring

    We are starting to see recovery and are continuing to monitor.

  4. resolved

    This incident has been resolved.

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

Partial Outage on Model APIs major 2026-07-13 00:04 UTC 2h 7m

Affected: Model APIs

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. identified

    Affecting Kimi-K2.6 and GLM-5.2.

  2. monitoring

    Identified an infiniband outage in one of our providers. GLM-5.2 Recovered. Kimi-K2.6 recovering.

  3. resolved

    Kimi-K2.6 recovered.

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

Elevated inference 500s for models deployed in 1 US-east cluster minor 2026-07-09 14:07 UTC 20m

Affected: Dedicated Inference

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. identified

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

  2. monitoring

    The provider had a network outage. Affected models are automatically moving to other clusters.

  3. resolved

    This incident has been resolved.

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

Metrics degradation in UI and API. **Inference not affected** minor 2026-07-08 16:50 UTC 1h 55m

Affected: Model Management API

Failure mode: Data delayed, stale, lost or corrupted, or needing replay after recovery. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with medium confidence (taxonomy v0.2).

  1. investigating

    Incorrect values recorded for some metrics

  2. resolved

    This incident has been resolved.

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

Elevated inference 500s — network outage in our cloud provider in Delaware minor 2026-07-06 21:08 UTC 14m

Affected: Dedicated Inference

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. identified

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

  2. resolved

    This incident has been resolved.

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

Elevated errors for GLM 5.2 on Model APIs. **Dedicated Inference is not affected** major 2026-07-03 02:59 UTC 1h 26m

Affected: Model APIs

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

    We are currently investigating this issue.

  2. investigating

    We are continuing to investigate this issue.

  3. monitoring

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

  4. resolved

    This incident has been resolved.

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

Elevated inference 500s for a subset of models deployed in 1 cluster minor 2026-07-03 00:21 UTC 16m

Affected: Dedicated Inference

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. identified

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

  2. identified

    We are continuing to work on a fix for this issue.

  3. resolved

    This incident has been resolved.

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

Degraded metrics performance in dashboard and API. **Inference is not affected** minor 2026-07-02 22:00 UTC 1h 14m

Affected: Model Management API

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

    We are currently investigating this issue.

  2. monitoring

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

  3. resolved

    This incident has been resolved.

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

Elevated errors in a single EU cluster major 2026-07-01 10:30 UTC 59m

Affected: Dedicated Inference

Failure mode: A zone, region or data center became unavailable. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with medium confidence (taxonomy v0.2).

  1. investigating

    Elevated errors due to degradation in a single EU cluster

  2. investigating

    We are continuing to investigate this issue.

  3. resolved

    This incident has been resolved.

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

Elevated error rates on GLM 5.2 Model APIs. **Dedicated Inference is not affected** minor 2026-06-29 18:26 UTC 35m

Affected: Model APIs

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

    Elevated error rates on GLM 5.2 Model APIs. **Dedicated Inference is not affected**

  2. resolved

    This incident has been resolved.

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

Elevated inference 500s for models in 1 cluster due to cloud provider outage minor 2026-06-27 06:35 UTC 15m

Affected: Dedicated Inference

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. identified

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

  2. monitoring

    Models are auto-moving to other clusters

  3. resolved

    This incident has been resolved.

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

Elevated model deployment failures. **Inference is not affected** minor 2026-06-26 23:41 UTC 1h 14m

Affected: Model Management API

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

    New model deployments failing to become ready

  2. resolved

    The incident has resolved. New model deployments are successfully coming up.

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

Elevated errors for dedicated inference in a subset of clusters major 2026-06-26 22:00 UTC 14m

Affected: Dedicated Inference

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

    We are currently investigating this issue.

  2. identified

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

  3. identified

    Nearly all clusters have recovered.

  4. identified

    We are continuing to work on a fix for this issue.

  5. resolved

    This incident has been resolved.

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

Slower than usual scale-ups. High failure rate for new model deploys. Existing replicas aren't impacted. minor 2026-06-23 00:10 UTC 44m

Affected: Dedicated Inference, Model Management API

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. identified

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

  2. identified

    We are continuing to work on a fix for this issue.

  3. resolved

    This incident has been resolved.

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

Elevated errors for models in 1 Austin-based cluster affecting some models on B200s minor 2026-06-18 12:46 UTC 1h 44m

Affected: Dedicated Inference, Model APIs

Failure mode: A zone, region or data center became unavailable. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with medium confidence (taxonomy v0.2).

  1. identified

    GLM 5.1 and Kimi k2.6 Model APIs are also affected.

  2. monitoring

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

  3. resolved

    This incident has been resolved.

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

Elevated errors for models in 1 Sweden-based cluster minor 2026-06-17 04:40 UTC 1h 23m

Affected: Dedicated Inference

Failure mode: A zone, region or data center became unavailable. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with low confidence (taxonomy v0.2).

  1. investigating

    We are currently investigating this issue.

  2. identified

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

  3. resolved

    This incident has been resolved.

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

Elevated errors for models in a single EU cloud provider minor 2026-06-15 16:14 UTC 44m

Affected: Dedicated Inference

Failure mode: A zone, region or data center became unavailable. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with medium confidence (taxonomy v0.2).

  1. investigating

    We are currently investigating this issue.

  2. monitoring

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

  3. resolved

    This incident has been resolved.

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