Baseten change history
| When (UTC) | Change | Kind |
|---|---|---|
| Major incident: DeepSeek v4.1 outage on Model APIs. Dedicated Inference is not affected Baseten reported a major DeepSeek v4.1 outage on Model APIs from 2026-10-06 04:35 UTC to 2026-10-06 04:48 UTC, lasting 13 min. Dedicated Inference was not affected; the incident was resolved, with no cause or fix specified. | Major incident | |
| Major incident: Elevated 500s in Single us-central Region Baseten reported a major incident affecting Dedicated Inference, with elevated 500s in a single us-central region starting 2026-09-29 19:44 UTC. A fix was implemented at 2026-09-29 19:52 UTC, and the incident was resolved at 2026-09-29 19:57 UTC after 13 min. | Major incident | |
| Major incident: Elevated inference 500s for a subset of models deployed in 1 US-East cluster Baseten reported a major Dedicated Inference outage with elevated inference 500s affecting a subset of models in 1 US-East cluster. It started at 2026-09-24 07:23 UTC and was resolved at 2026-09-24 08:06 UTC, lasting 42 min; a fix was implemented at 07:48 UTC. | Major incident | |
| Major incident: Elevated inference 500s for a subset of models deployed in GCP central1 Baseten reported a major Dedicated Inference incident causing elevated inference 500s for a subset of models deployed in GCP central1. It started at 2026-09-21 18:34 UTC and was resolved at 2026-09-21 18:41 UTC, with a computed duration of 6 min; a fix was implemented by 18:38 UTC. | Major incident | |
| Major incident: Kimi K3 Model API outage Baseten reported a major Kimi K3 Model API outage starting 2026-09-20 07:19 UTC, lasting 54 min and resolving at 2026-09-20 08:13 UTC. About 20% of calls returned errors, with calls to the US-hosted endpoint specifically affected; a fix was implemented at 08:04 UTC. | Major incident | |
| Major incident: Elevated inference 500s for models in a single US-based cluster Baseten reported a major Dedicated Inference incident with elevated inference 500s for models in a single US-based cluster. It ran from 2026-08-31 06:38 UTC to 2026-08-31 07:02 UTC (24 min); a fix was in place and traffic was back at 06:57 UTC. | Major incident | |
| Major incident: GLM 5.2 Model API partial outage due to provider network failure Baseten’s GLM 5.2 Model API experienced a major partial outage due to provider network failure, starting 2026-07-18 22:40 UTC and lasting 32 min until resolution at 2026-07-18 23:12 UTC. Dedicated inference was not affected; Baseten reported implementing a fix at 07-18 23:05 UTC. | Major incident | |
| Major incident: Partial Outage on Model APIs Baseten reported a major partial outage of Model APIs affecting Kimi-K2.6 and GLM-5.2, starting 2026-07-13 00:04 UTC and lasting 2 h 6 min until resolution at 2026-07-13 02:10 UTC. Baseten identified an infiniband outage at one provider; GLM-5.2 recovered first, followed by Kimi-K2.6. | Major incident | |
| Major incident: Elevated errors for GLM 5.2 on Model APIs. **Dedicated Inference is not affected** Baseten reported a major incident with elevated errors for GLM 5.2 on Model APIs; Dedicated Inference was not affected. It started at 2026-07-03 02:59 UTC and resolved at 2026-07-03 04:25 UTC, lasting 1 h 25 min. A fix was implemented and monitored before resolution. | Major incident | |
| Major incident: Elevated errors in a single EU cluster Baseten reported a major incident affecting Dedicated Inference, with elevated errors due to degradation in a single EU cluster. It started at 2026-07-01 10:30 UTC and was resolved at 2026-07-01 11:30 UTC; the computed duration was 59 min. No specific fix was stated. | Major incident | |
| Major incident: Elevated errors for dedicated inference in a subset of clusters Baseten reported a major incident causing elevated errors for Dedicated Inference in a subset of clusters, starting at 2026-06-26 22:00 UTC and resolved at 2026-06-26 22:15 UTC (computed duration: 14 min). A fix was being implemented, and nearly all clusters had recovered by 22:03 UTC; no cause was stated. | Major incident | |
| Major incident: Elevated errors in a single US-East cluster Baseten reported a major incident affecting Dedicated Inference, with elevated errors in a single US-East cluster. It started at 2026-06-05 02:10 UTC and was resolved at 2026-06-05 02:29 UTC, lasting 19 min; no cause or fix was stated. | Major incident |