Baseten Outage History

Baseten is up right now

Baseten had 43 outages in the last 2 years totaling 24h 0m of downtime, averaging 1.8 incidents per month.

There were 43 Baseten outages since June 15, 2026 totaling 24h 0m of downtime. Each is summarised below. Incident details, duration, and resolution information.

Source: status.baseten.co

Minor October 21, 2026

Elevated errors for image requests on multiple Model APIs

Detected by Pingoru
Oct 21, 2026, 01:05 AM UTC
Resolved
Oct 21, 2026, 01:26 AM UTC
Duration
20m
Affected: Model APIs
Timeline · 3 updates
  1. investigating Oct 21, 2026, 01:05 AM UTC

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

  2. investigating Oct 21, 2026, 01:24 AM UTC

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

  3. resolved Oct 21, 2026, 01:26 AM UTC

    This incident has been resolved.

Read the full incident report →

Major October 20, 2026

DeepSeek V4.1 Flash Fast Outage on Model APIs

Detected by Pingoru
Oct 20, 2026, 07:04 PM UTC
Resolved
Oct 20, 2026, 07:10 PM UTC
Duration
5m
Affected: Model APIs
Timeline · 2 updates
  1. investigating Oct 20, 2026, 07:04 PM UTC

    We are currently investigating this issue.

  2. resolved Oct 20, 2026, 07:10 PM UTC

    This incident has been resolved.

Read the full incident report →

Minor October 20, 2026

Elevated errors on Model APIs

Detected by Pingoru
Oct 20, 2026, 01:35 AM UTC
Resolved
Oct 20, 2026, 01:43 AM UTC
Duration
8m
Affected: Model APIs
Timeline · 3 updates
  1. investigating Oct 20, 2026, 01:35 AM UTC

    Elevated errors across Model APIs due to provider outage

  2. monitoring Oct 20, 2026, 01:40 AM UTC

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

  3. resolved Oct 20, 2026, 01:43 AM UTC

    This incident has been resolved.

Read the full incident report →

Minor October 9, 2026

Elevated errors on new model builds. Existing models are not affected

Detected by Pingoru
Oct 09, 2026, 09:29 PM UTC
Resolved
Oct 09, 2026, 10:06 PM UTC
Duration
37m
Affected: Model Management API
Timeline · 3 updates
  1. investigating Oct 09, 2026, 09:29 PM UTC

    We are currently investigating this issue.

  2. monitoring Oct 09, 2026, 09:57 PM UTC

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

  3. resolved Oct 09, 2026, 10:06 PM UTC

    This incident has been resolved.

Read the full incident report →

Major September 29, 2026

Elevated 500s in Single us-central Region

Detected by Pingoru
Sep 29, 2026, 08:12 AM UTC
Resolved
Sep 29, 2026, 07:57 PM UTC
Duration
11h 45m
Affected: Dedicated Inference
Timeline · 3 updates
  1. identified Sep 29, 2026, 08:12 AM UTC

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

  2. monitoring Sep 29, 2026, 08:14 AM UTC

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

  3. resolved Sep 29, 2026, 08:15 AM UTC

    This incident has been resolved.

Read the full incident report →

Minor September 29, 2026

Metrics degradation in UI and API. **Inference not affected**

Detected by Pingoru
Sep 29, 2026, 01:07 AM UTC
Resolved
Sep 29, 2026, 01:28 AM UTC
Duration
21m
Affected: Model Management APIWeb Application
Timeline · 3 updates
  1. investigating Sep 29, 2026, 01:07 AM UTC

    We are currently investigating this issue.

  2. investigating Sep 29, 2026, 01:09 AM UTC

    We are continuing to investigate this issue.

  3. resolved Sep 29, 2026, 01:28 AM UTC

    This incident has been resolved.

Read the full incident report →

Minor September 24, 2026

Intermittent 5xx for a subset of models in 1 US Central cluster

Detected by Pingoru
Sep 24, 2026, 06:35 PM UTC
Resolved
Sep 24, 2026, 07:57 PM UTC
Duration
1h 22m
Affected: Dedicated Inference
Timeline · 3 updates
  1. investigating Sep 24, 2026, 07:09 PM UTC

    We are currently investigating this issue.

  2. investigating Sep 24, 2026, 07:50 PM UTC

    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 Sep 24, 2026, 07:57 PM UTC

    This incident has been resolved.

Read the full incident report →

Major September 24, 2026

Elevated inference 500s for a subset of models deployed in 1 US-East cluster

Detected by Pingoru
Sep 24, 2026, 07:23 AM UTC
Resolved
Sep 24, 2026, 08:06 AM UTC
Duration
42m
Affected: Dedicated Inference
Timeline · 4 updates
  1. identified Sep 24, 2026, 07:43 AM UTC

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

  2. monitoring Sep 24, 2026, 07:48 AM UTC

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

  3. monitoring Sep 24, 2026, 08:05 AM UTC

    We are continuing to monitor for any further issues.

  4. resolved Sep 24, 2026, 08:30 AM UTC

    This incident has been resolved.

Read the full incident report →

Major September 21, 2026

Elevated inference 500s for a subset of models deployed in GCP central1

Detected by Pingoru
Sep 21, 2026, 06:34 PM UTC
Resolved
Sep 21, 2026, 06:41 PM UTC
Duration
6m
Affected: Dedicated Inference
Timeline · 3 updates
  1. identified Sep 21, 2026, 06:34 PM UTC

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

  2. monitoring Sep 21, 2026, 06:38 PM UTC

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

  3. resolved Sep 21, 2026, 06:41 PM UTC

    This incident has been resolved.

Read the full incident report →

Major September 20, 2026

Kimi K3 Model API outage

Detected by Pingoru
Sep 20, 2026, 07:19 AM UTC
Resolved
Sep 20, 2026, 08:13 AM UTC
Duration
54m
Affected: Model APIs
Timeline · 5 updates
  1. identified Sep 20, 2026, 07:19 AM UTC

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

  2. identified Sep 20, 2026, 07:30 AM UTC

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

  3. identified Sep 20, 2026, 07:59 AM UTC

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

  4. monitoring Sep 20, 2026, 08:04 AM UTC

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

  5. resolved Sep 20, 2026, 08:13 AM UTC

    This incident has been resolved.

Read the full incident report →

Minor September 15, 2026

Elevated errors for models in a single India-based cluster

Detected by Pingoru
Sep 15, 2026, 01:22 AM UTC
Resolved
Sep 15, 2026, 02:07 AM UTC
Duration
44m
Affected: Dedicated Inference
Timeline · 3 updates
  1. investigating Sep 15, 2026, 01:22 AM UTC

    We are currently investigating this issue.

  2. monitoring Sep 15, 2026, 01:39 AM UTC

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

  3. resolved Sep 15, 2026, 02:07 AM UTC

    This incident has been resolved.

Read the full incident report →

Minor September 9, 2026

Partial outage on Nemotron Ultra Model API. **Dedicated Inference is not affected**

Detected by Pingoru
Sep 09, 2026, 05:42 PM UTC
Resolved
Sep 09, 2026, 05:49 PM UTC
Duration
6m
Affected: Model APIs
Timeline · 3 updates
  1. investigating Sep 09, 2026, 05:42 PM UTC

    We are currently investigating this issue.

  2. monitoring Sep 09, 2026, 05:45 PM UTC

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

  3. resolved Sep 09, 2026, 05:52 PM UTC

    This incident has been resolved.

Read the full incident report →

Major August 31, 2026

Elevated inference 500s for models in a single US-based cluster

Detected by Pingoru
Aug 31, 2026, 06:38 AM UTC
Resolved
Aug 31, 2026, 07:02 AM UTC
Duration
24m
Affected: Dedicated Inference
Timeline · 3 updates
  1. investigating Aug 31, 2026, 06:38 AM UTC

    We are currently investigating this issue.

  2. monitoring Aug 31, 2026, 06:57 AM UTC

    Fix is in place and traffic is back.

  3. resolved Aug 31, 2026, 07:02 AM UTC

    This incident has been resolved.

Read the full incident report →

Minor August 25, 2026

Elevated errors for deepseek-ai/DeepSeek-V4-Flash-0731 on Model APIs. **Dedicated Inference is not affected**

Detected by Pingoru
Aug 25, 2026, 04:17 PM UTC
Resolved
Aug 25, 2026, 04:59 PM UTC
Duration
41m
Affected: Model APIs
Timeline · 3 updates
  1. investigating Aug 25, 2026, 04:17 PM UTC

    We are currently investigating this issue.

  2. monitoring Aug 25, 2026, 04:43 PM UTC

    A fix is in place and we are monitoring

  3. resolved Aug 25, 2026, 04:59 PM UTC

    This incident has been resolved.

Read the full incident report →

Minor August 25, 2026

Elevated inference 500s for models in an EU cluster due to provider outage

Detected by Pingoru
Aug 25, 2026, 12:34 PM UTC
Resolved
Aug 25, 2026, 01:15 PM UTC
Duration
40m
Affected: Dedicated Inference
Timeline · 3 updates
  1. identified Aug 25, 2026, 12:34 PM UTC

    Failover in progress.

  2. monitoring Aug 25, 2026, 12:53 PM UTC

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

  3. resolved Aug 25, 2026, 01:15 PM UTC

    This incident has been resolved.

Read the full incident report →

Minor August 19, 2026

Elevated errors for moonshotai/Kimi-K3 for US-pinned traffic on Model APIs. **Dedicated Inference is not affected**

Detected by Pingoru
Aug 19, 2026, 01:23 AM UTC
Resolved
Aug 19, 2026, 02:00 AM UTC
Duration
36m
Affected: Model APIs
Timeline · 3 updates
  1. investigating Aug 19, 2026, 01:23 AM UTC

    We are currently investigating this issue.

  2. monitoring Aug 19, 2026, 01:45 AM UTC

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

  3. resolved Aug 19, 2026, 02:00 AM UTC

    This incident has been resolved.

Read the full incident report →

Minor August 1, 2026

Elevated inference 502s for a subset of models in a single US cluster

Detected by Pingoru
Aug 01, 2026, 11:57 PM UTC
Resolved
Aug 02, 2026, 12:41 AM UTC
Duration
43m
Affected: Dedicated Inference
Timeline · 3 updates
  1. investigating Aug 01, 2026, 11:57 PM UTC

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

  2. identified Aug 02, 2026, 12:06 AM UTC

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

  3. resolved Aug 02, 2026, 12:56 AM UTC

    This incident has been resolved.

Read the full incident report →

Minor July 31, 2026

Slower than usual scale-ups for B200s

Detected by Pingoru
Jul 31, 2026, 04:46 PM UTC
Resolved
Jul 31, 2026, 04:58 PM UTC
Duration
11m
Affected: Dedicated Inference
Timeline · 2 updates
  1. investigating Jul 31, 2026, 04:46 PM UTC

    We are currently investigating this issue.

  2. resolved Jul 31, 2026, 04:58 PM UTC

    This incident has been resolved.

Read the full incident report →

Minor July 22, 2026

Elevated inference failures for models in an EU cluster

Detected by Pingoru
Jul 22, 2026, 05:49 PM UTC
Resolved
Jul 22, 2026, 06:22 PM UTC
Duration
32m
Affected: Dedicated Inference
Timeline · 3 updates
  1. identified Jul 22, 2026, 05:49 PM UTC

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

  2. identified Jul 22, 2026, 06:05 PM UTC

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

  3. resolved Jul 22, 2026, 06:22 PM UTC

    This incident has been resolved.

Read the full incident report →

Minor July 22, 2026

Slower than usual scale-ups in 1 us-central cluster

Detected by Pingoru
Jul 22, 2026, 05:45 PM UTC
Resolved
Jul 22, 2026, 06:04 PM UTC
Duration
19m
Affected: Dedicated Inference
Timeline · 2 updates
  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 →