Is Baseten down right now?
No, it is up
Operational · All Systems Operational
Components
- Dedicated InferenceOperational
- Sandboxes · Oregon (us-pdx-1)Operational
- Model APIsOperational
- Sandboxes · Virginia (us-was-1)Operational
- TrainingOperational
- Sandboxes · Frankfurt (eu-fra-1)Operational
- Model Management APIOperational
- Web ApplicationOperational
- Homepage and DocsOperational
User reports
Having trouble with Baseten? Reports are anonymous and only counted, no cookies.
Baseten uptime, last 90 days
Each bar is one UTC day, coloured by the worst state we saw on the official status page.
Recent Baseten incidents
Elevated errors for US-only GLM 5.3 Flash on Model APIs · 23 Oct 2026, 01:51 UTC · 56 min · minor
resolved · 23 Oct 2026, 02:48 UTC
This incident has been resolved.
investigating · 23 Oct 2026, 01:51 UTC
We are currently investigating this issue.
Elevated errors on DeepSeek V4 Flash on Model APIs · 21 Oct 2026, 01:48 UTC · 40 min · minor
resolved · 21 Oct 2026, 02:28 UTC
This incident has been resolved.
investigating · 21 Oct 2026, 01:48 UTC
We are currently investigating this issue.
Elevated errors for image requests on multiple Model APIs · 21 Oct 2026, 01:05 UTC · 21 min · minor
resolved · 21 Oct 2026, 01:26 UTC
This incident has been resolved.
investigating · 21 Oct 2026, 01:24 UTC
GLM 5.3 Flash has recovered, we continue to see degraded performance on Deepseek V4 Flash
investigating · 21 Oct 2026, 01:05 UTC
There are elevated errors for image requests on Deepseek V4 Flash and GLM 5.3 Flash
DeepSeek V4.1 Flash Fast Outage on Model APIs · 20 Oct 2026, 19:04 UTC · 6 min · major
resolved · 20 Oct 2026, 19:10 UTC
This incident has been resolved.
investigating · 20 Oct 2026, 19:04 UTC
We are currently investigating this issue.
Elevated errors on Model APIs · 20 Oct 2026, 01:35 UTC · 8 min · minor
resolved · 20 Oct 2026, 01:43 UTC
This incident has been resolved.
monitoring · 20 Oct 2026, 01:40 UTC
A fix has been implemented and we are seeing recovery on all models
investigating · 20 Oct 2026, 01:35 UTC
Elevated errors across Model APIs due to provider outage
Elevated errors on new model builds. Existing models are not affected · 9 Oct 2026, 21:29 UTC · 37 min · minor
resolved · 9 Oct 2026, 22:06 UTC
This incident has been resolved.
monitoring · 9 Oct 2026, 21:57 UTC
A fix has been implemented and we are monitoring the results.
investigating · 9 Oct 2026, 21:29 UTC
We are currently investigating this issue.
DeepSeek v4.1 outage on Model APIs. Dedicated Inference is not affected · 6 Oct 2026, 04:35 UTC · 13 min · major
resolved · 6 Oct 2026, 04:48 UTC
This incident has been resolved.
investigating · 6 Oct 2026, 04:35 UTC
We are currently investigating this issue.
Elevated 500s in Single us-central Region · 29 Sept 2026, 19:44 UTC · 13 min · major
resolved · 29 Sept 2026, 19:57 UTC
This incident has been resolved.
monitoring · 29 Sept 2026, 19:52 UTC
A fix has been implemented and we're monitoring the results.
identified · 29 Sept 2026, 19:44 UTC
The issue has been identified and we're looking into a fix.
Metrics degradation in UI and API. **Inference not affected** · 29 Sept 2026, 01:07 UTC · 21 min · minor
resolved · 29 Sept 2026, 01:28 UTC
This incident has been resolved.
investigating · 29 Sept 2026, 01:09 UTC
We are continuing to investigate this issue.
investigating · 29 Sept 2026, 01:07 UTC
We are currently investigating this issue.
Intermittent 5xx for a subset of models in 1 US Central cluster · 24 Sept 2026, 18:35 UTC · 1 h 22 min · minor
resolved · 24 Sept 2026, 19:57 UTC
This incident has been resolved.
investigating · 24 Sept 2026, 19:50 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.
investigating · 24 Sept 2026, 18:35 UTC
We are currently investigating this issue.
Elevated inference 500s for a subset of models deployed in 1 US-East cluster · 24 Sept 2026, 07:23 UTC · 42 min · major
resolved · 24 Sept 2026, 08:06 UTC
This incident has been resolved.
monitoring · 24 Sept 2026, 08:05 UTC
We are continuing to monitor for any further issues.
monitoring · 24 Sept 2026, 07:48 UTC
A fix has been implemented and we are monitoring the results.
identified · 24 Sept 2026, 07:23 UTC
The issue has been identified and a fix is being implemented.
Elevated inference 500s for a subset of models deployed in GCP central1 · 21 Sept 2026, 18:34 UTC · 7 min · major
resolved · 21 Sept 2026, 18:41 UTC
This incident has been resolved.
monitoring · 21 Sept 2026, 18:38 UTC
A fix has been implemented and we are monitoring the results.
identified · 21 Sept 2026, 18:34 UTC
The issue has been identified and a fix is being implemented.
Metrics degradation in UI and API. **Inference not affected** · 21 Sept 2026, 13:31 UTC · 11 min · minor
resolved · 21 Sept 2026, 13:42 UTC
This incident has been resolved.
investigating · 21 Sept 2026, 13:31 UTC
We are currently investigating this issue.
Kimi K3 Model API outage · 20 Sept 2026, 07:19 UTC · 55 min · major
resolved · 20 Sept 2026, 08:13 UTC
This incident has been resolved.
monitoring · 20 Sept 2026, 08:04 UTC
A fix has been implemented and we are monitoring the results.
identified · 20 Sept 2026, 07:59 UTC
Calls to the US-hosted endpoint are resulting in errors. A fix is in progress.
identified · 20 Sept 2026, 07:30 UTC
~20% of calls are resulting in errors. A fix is in progress.
identified · 20 Sept 2026, 07:19 UTC
The issue has been identified and a fix is being implemented.
Elevated errors for models in a single India-based cluster · 15 Sept 2026, 01:22 UTC · 45 min · minor
resolved · 15 Sept 2026, 02:07 UTC
This incident has been resolved.
monitoring · 15 Sept 2026, 01:39 UTC
A fix has been implemented and we are monitoring the results.
investigating · 15 Sept 2026, 01:22 UTC
We are currently investigating this issue.
Baseten is listed under Infrastructure. Status data comes from the official status page and is checked every 5 minutes.All AI service statuses