Baseten Outage History

Baseten is up right now

Pingoru has recorded 51 incidents for Baseten: 51 in the last 12 months and 30 in the last 90 days.

Source: status.baseten.co

51incidents recorded
51last 12 months
30last 90 days
54 minutestypical duration

Incidents, newest first

Minor July 22, 2026 Slower than usual scale-ups in 1 us-central cluster 19m Dedicated Inference

Started Jul 22, 2026, 05:45 PM UTC· resolved Jul 22, 2026, 06:04 PM UTC

  1. identified Jul 22, 2026, 05:45 PM UTC

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

  2. resolved Jul 22, 2026, 06:04 PM UTC

    This incident has been resolved.

Read the full incident report →

Major July 18, 2026 GLM 5.2 Model API partial outage due to provider network failure 32m Model APIs

Started Jul 18, 2026, 10:40 PM UTC· resolved Jul 18, 2026, 11:12 PM UTC

  1. identified Jul 18, 2026, 10:40 PM UTC

    Escalated Dedicated inference is *not* affected.

  2. monitoring Jul 18, 2026, 11:05 PM UTC

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

  3. monitoring Jul 18, 2026, 11:05 PM UTC

    We are continuing to monitor for any further issues.

  4. resolved Jul 18, 2026, 11:12 PM UTC

    This incident has been resolved.

Read the full incident report →

Minor July 18, 2026 Elevated inference errors in 1 Canada cluster due to provider network outage 5m Dedicated Inference

Started Jul 18, 2026, 12:22 AM UTC· resolved Jul 18, 2026, 12:28 AM UTC

  1. identified Jul 18, 2026, 12:22 AM UTC

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

  2. resolved Jul 18, 2026, 12:28 AM UTC

    This incident has been resolved.

Read the full incident report →

Minor July 16, 2026 Elevated errors in accessing the Baseten UI. **Inference is not affected** 1h 18m Model Management API, Web Application

Started Jul 16, 2026, 09:06 AM UTC· resolved Jul 16, 2026, 10:25 AM UTC

  1. investigating Jul 16, 2026, 09:06 AM UTC

    We are currently investigating this issue.

  2. investigating Jul 16, 2026, 10:07 AM UTC

    We are continuing to investigate this issue.

  3. monitoring Jul 16, 2026, 10:14 AM UTC

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

  4. resolved Jul 16, 2026, 10:25 AM UTC

    This incident has been resolved.

Read the full incident report →

Major July 13, 2026 Partial Outage on Model APIs 2h 6m Model APIs

Started Jul 13, 2026, 12:04 AM UTC· resolved Jul 13, 2026, 02:10 AM UTC

  1. identified Jul 13, 2026, 12:04 AM UTC

    Affecting Kimi-K2.6 and GLM-5.2.

  2. monitoring Jul 13, 2026, 01:46 AM UTC

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

  3. resolved Jul 13, 2026, 02:10 AM UTC

    Kimi-K2.6 recovered.

Read the full incident report →

Minor July 9, 2026 Elevated inference 500s for models deployed in 1 US-east cluster 20m Dedicated Inference

Started Jul 09, 2026, 02:07 PM UTC· resolved Jul 09, 2026, 02:28 PM UTC

  1. identified Jul 09, 2026, 02:07 PM UTC

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

  2. monitoring Jul 09, 2026, 02:24 PM UTC

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

  3. resolved Jul 09, 2026, 02:38 PM UTC

    This incident has been resolved.

Read the full incident report →

Minor July 6, 2026 Elevated inference 500s — network outage in our cloud provider in Delaware 13m Dedicated Inference

Started Jul 06, 2026, 09:08 PM UTC· resolved Jul 06, 2026, 09:22 PM UTC

  1. identified Jul 06, 2026, 09:08 PM UTC

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

  2. resolved Jul 06, 2026, 09:22 PM UTC

    This incident has been resolved.

Read the full incident report →

Major July 3, 2026 Elevated errors for GLM 5.2 on Model APIs. **Dedicated Inference is not affected** 1h 25m Model APIs

Started Jul 03, 2026, 02:59 AM UTC· resolved Jul 03, 2026, 04:25 AM UTC

  1. investigating Jul 03, 2026, 02:59 AM UTC

    We are currently investigating this issue.

  2. investigating Jul 03, 2026, 03:06 AM UTC

    We are continuing to investigate this issue.

  3. monitoring Jul 03, 2026, 03:56 AM UTC

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

  4. resolved Jul 03, 2026, 04:25 AM UTC

    This incident has been resolved.

Read the full incident report →

Minor July 3, 2026 Elevated inference 500s for a subset of models deployed in 1 cluster 15m Dedicated Inference

Started Jul 03, 2026, 12:21 AM UTC· resolved Jul 03, 2026, 12:36 AM UTC

  1. identified Jul 03, 2026, 12:21 AM UTC

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

  2. identified Jul 03, 2026, 12:36 AM UTC

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

  3. resolved Jul 03, 2026, 12:36 AM UTC

    This incident has been resolved.

Read the full incident report →

Minor July 2, 2026 Degraded metrics performance in dashboard and API. **Inference is not affected** 1h 13m Model Management API

Started Jul 02, 2026, 10:00 PM UTC· resolved Jul 02, 2026, 11:13 PM UTC

  1. investigating Jul 02, 2026, 10:35 PM UTC

    We are currently investigating this issue.

  2. monitoring Jul 02, 2026, 10:53 PM UTC

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

  3. resolved Jul 02, 2026, 11:13 PM UTC

    This incident has been resolved.

Read the full incident report →

Major July 1, 2026 Elevated errors in a single EU cluster 59m Dedicated Inference

Started Jul 01, 2026, 10:30 AM UTC· resolved Jul 01, 2026, 11:30 AM UTC

  1. investigating Jul 01, 2026, 08:51 PM UTC

    Elevated errors due to degradation in a single EU cluster

  2. investigating Jul 01, 2026, 08:51 PM UTC

    We are continuing to investigate this issue.

  3. resolved Jul 01, 2026, 08:52 PM UTC

    This incident has been resolved.

Read the full incident report →

Minor June 29, 2026 Elevated error rates on GLM 5.2 Model APIs. **Dedicated Inference is not affected** 35m Model APIs

Started Jun 29, 2026, 06:26 PM UTC· resolved Jun 29, 2026, 07:01 PM UTC

  1. investigating Jun 29, 2026, 08:08 PM UTC

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

  2. resolved Jun 29, 2026, 08:08 PM UTC

    This incident has been resolved.

Read the full incident report →

Minor June 27, 2026 Elevated inference 500s for models in 1 cluster due to cloud provider outage 15m Dedicated Inference

Started Jun 27, 2026, 06:35 AM UTC· resolved Jun 27, 2026, 06:50 AM UTC

  1. identified Jun 27, 2026, 06:35 AM UTC

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

  2. monitoring Jun 27, 2026, 06:38 AM UTC

    Models are auto-moving to other clusters

  3. resolved Jun 27, 2026, 06:50 AM UTC

    This incident has been resolved.

Read the full incident report →

Minor June 26, 2026 Elevated model deployment failures. **Inference is not affected** 1h 14m Model Management API

Started Jun 26, 2026, 11:41 PM UTC· resolved Jun 27, 2026, 12:55 AM UTC

  1. investigating Jun 26, 2026, 11:41 PM UTC

    New model deployments failing to become ready

  2. resolved Jun 27, 2026, 12:55 AM UTC

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

Read the full incident report →

Major June 26, 2026 Elevated errors for dedicated inference in a subset of clusters 14m Dedicated Inference

Started Jun 26, 2026, 10:00 PM UTC· resolved Jun 26, 2026, 10:15 PM UTC

  1. investigating Jun 26, 2026, 10:03 PM UTC

    We are currently investigating this issue.

  2. identified Jun 26, 2026, 10:05 PM UTC

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

  3. identified Jun 26, 2026, 10:09 PM UTC

    Nearly all clusters have recovered.

  4. identified Jun 26, 2026, 10:11 PM UTC

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

  5. resolved Jun 26, 2026, 10:15 PM UTC

    This incident has been resolved.

Read the full incident report →

Minor June 23, 2026 Slower than usual scale-ups. High failure rate for new model deploys. Existing replicas aren't impacted. 44m Dedicated Inference, Model Management API

Started Jun 23, 2026, 12:10 AM UTC· resolved Jun 23, 2026, 12:54 AM UTC

  1. identified Jun 23, 2026, 12:10 AM UTC

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

  2. identified Jun 23, 2026, 12:16 AM UTC

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

  3. resolved Jun 23, 2026, 12:54 AM UTC

    This incident has been resolved.

Read the full incident report →

Minor June 18, 2026 Elevated errors for models in 1 Austin-based cluster affecting some models on B200s 1h 43m Dedicated Inference, Model APIs

Started Jun 18, 2026, 12:46 PM UTC· resolved Jun 18, 2026, 02:30 PM UTC

  1. identified Jun 18, 2026, 12:46 PM UTC

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

  2. monitoring Jun 18, 2026, 01:40 PM UTC

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

  3. resolved Jun 18, 2026, 02:30 PM UTC

    This incident has been resolved.

Read the full incident report →

Minor June 17, 2026 Elevated errors for models in 1 Sweden-based cluster 1h 23m Dedicated Inference

Started Jun 17, 2026, 04:40 AM UTC· resolved Jun 17, 2026, 06:03 AM UTC

  1. investigating Jun 17, 2026, 04:40 AM UTC

    We are currently investigating this issue.

  2. identified Jun 17, 2026, 04:44 AM UTC

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

  3. resolved Jun 17, 2026, 06:03 AM UTC

    This incident has been resolved.

Read the full incident report →

Minor June 15, 2026 Elevated errors for models in a single EU cloud provider 44m Dedicated Inference

Started Jun 15, 2026, 04:14 PM UTC· resolved Jun 15, 2026, 04:58 PM UTC

  1. investigating Jun 15, 2026, 04:14 PM UTC

    We are currently investigating this issue.

  2. monitoring Jun 15, 2026, 04:54 PM UTC

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

  3. resolved Jun 15, 2026, 04:58 PM UTC

    This incident has been resolved.

Read the full incident report →