Baseten status history
71 incidents over the last year, newest first; 99.99% uptime (90 days), 99.99% uptime (12 months). History from before down.guide started reading the page is imported from Baseten's own archive.
Month
2026-11
1 incident
Month
2026-10
7 incidents
- BasetenDegradedElevated errors for US-only GLM 5.3 Flash on Model APIs
- BasetenDegradedElevated errors on DeepSeek V4 Flash on Model APIs
- BasetenDegradedElevated errors for image requests on multiple Model APIs
- BasetenPartial outageDeepSeek V4.1 Flash Fast Outage on Model APIs
- BasetenDegradedElevated errors on Model APIs
- BasetenDegradedElevated errors on new model builds. Existing models are not affected
- BasetenPartial outageDeepSeek v4.1 outage on Model APIs. Dedicated Inference is not affected
Month
2026-09
10 incidents
- BasetenPartial outageElevated 500s in Single us-central Region
- BasetenDegradedMetrics degradation in UI and API. **Inference not affected**
- BasetenDegradedIntermittent 5xx for a subset of models in 1 US Central cluster
- BasetenPartial outageElevated inference 500s for a subset of models deployed in 1 US-East cluster
- BasetenPartial outageElevated inference 500s for a subset of models deployed in GCP central1
- BasetenDegradedMetrics degradation in UI and API. **Inference not affected**
- BasetenPartial outageKimi K3 Model API outage
- BasetenDegradedElevated errors for models in a single India-based cluster
- BasetenDegradedPartial outage on Kimi K3 model API inference (non-US only)
- BasetenDegradedPartial outage on Nemotron Ultra Model API. **Dedicated Inference is not affected**
Month
2026-08
11 incidents
- BasetenPartial outageElevated inference 500s for models in a single US-based cluster
- BasetenDegradedElevated errors for models in a single US cluster due to provider outage
- BasetenDegradedElevated errors for deepseek-ai/DeepSeek-V4-Flash-0731 on Model APIs. **Dedicated Inference is not affected**
- BasetenDegradedElevated inference 500s for models in an EU cluster due to provider outage
- BasetenDegradedElevated errors for moonshotai/Kimi-K3 for US-pinned traffic on Model APIs. **Dedicated Inference is not affected**
- BasetenDegradedElevated errors for moonshotai/Kimi-K3 for US-pinned traffic on Model APIs. **Dedicated Inference is not affected**
- BasetenDegradedElevated errors for moonshotai/Kimi-K3 for US-pinned traffic on Model APIs. **Dedicated Inference is not affected**
- BasetenDegradedElevated errors for moonshotai/Kimi-K3 for US-pinned traffic on Model APIs. **Dedicated Inference is not affected**
- BasetenDegradedElevated errors for moonshotai/Kimi-K3 for US-pinned traffic
- BasetenDegradedMetrics degradation in UI and API. **Inference not affected**
- BasetenDegradedElevated inference 502s for a subset of models in a single US cluster
Month
2026-07
15 incidents
- BasetenDegradedElevated inference 502s for a subset of models in a single US cluster
- BasetenDegradedSlower than usual scale-ups for B200s
- BasetenDegradedElevated inference failures for models in an EU cluster
- BasetenDegradedSlower than usual scale-ups in 1 us-central cluster
- BasetenPartial outageGLM 5.2 Model API partial outage due to provider network failure
- BasetenDegradedElevated inference errors in 1 Canada cluster due to provider network outage
- BasetenDegradedElevated errors in accessing the Baseten UI. **Inference is not affected**
- BasetenPartial outagePartial Outage on Model APIs
- BasetenDegradedElevated inference 500s for models deployed in 1 US-east cluster
- BasetenDegradedMetrics degradation in UI and API. **Inference not affected**
- BasetenDegradedElevated inference 500s — network outage in our cloud provider in Delaware
- BasetenPartial outageElevated errors for GLM 5.2 on Model APIs. **Dedicated Inference is not affected**
- BasetenDegradedElevated inference 500s for a subset of models deployed in 1 cluster
- BasetenDegradedDegraded metrics performance in dashboard and API. **Inference is not affected**
- BasetenPartial outageElevated errors in a single EU cluster
Month
2026-06
12 incidents
- BasetenDegradedElevated error rates on GLM 5.2 Model APIs. **Dedicated Inference is not affected**
- BasetenDegradedElevated inference 500s for models in 1 cluster due to cloud provider outage
- BasetenDegradedElevated model deployment failures. **Inference is not affected**
- BasetenPartial outageElevated errors for dedicated inference in a subset of clusters
- BasetenDegradedSlower than usual scale-ups. High failure rate for new model deploys. Existing replicas aren't impacted.
- BasetenDegradedElevated errors for models in 1 Austin-based cluster affecting some models on B200s
- BasetenDegradedElevated errors for models in 1 Sweden-based cluster
- BasetenDegradedElevated errors for models in a single EU cloud provider
- BasetenDegradedElevated errors for models in a single cloud provider
- BasetenPartial outageElevated errors in a single US-East cluster
- BasetenDegradedElevated latencies for a subset of models in a US-East cluster
- BasetenDegradedSlower than usual scale-ups for some models using H100s
Month
2026-05
10 incidents
- BasetenDegradedElevated async inference errors in a single cluster
- BasetenDegradedSlower than usual scale-ups in 1 India cluster
- BasetenDegradedElevated errors for models in single region
- BasetenDegradedSlower than usual scale-ups for L4s in US-East
- BasetenDegradedSlower than usual scale-ups in EU due to a provider failure
- BasetenDegradedHigher latencies for a subset of models in one cluster. Root caused and a fix is in progress
- BasetenDegradedElevated errors in a single cluster
- BasetenPartial outageTraining cluster is down due to a provider failure
- BasetenDegradedIntermittent failure in loading the webapp — inference is *not* affected
- BasetenDegradedElevated errors for models in single region
Month
2026-04
4 incidents
- BasetenDegradedSlower than usual scale-ups for a small subset of models
- BasetenDegradedSlower than usual scale-ups for a small subset of models
- BasetenPartial outageBuilds of new models are currently failing. **Inference is not affected**
- BasetenDegradedElevated deploy failures. Inference is **not** affected.
Month
2026-03
1 incident