Companies / ai

Baseten

baseten.coStatus page: status.baseten.coNow: operational since 2026-10-17
148incidents since 2022-03-04
31major or critical
27in the last 90 days
0silently edited or deleted

Recent notable changes

When (UTC)ChangeKind
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

Full Baseten change timeline, with diffs →

Status incident history

Baseten status incidents per year
0204060↑ incidents20222023202420252026210244171
Grey: all non-maintenance incidents. Orange: major or critical. Years before Oct 2026 come from the vendor’s own status history.
Data table
YearIncidentsMajor/critical
202220
2023102
2024242
20254111
20267116
Incidents per month, last 36 months
By impact as reported by the vendor. Maintenance excluded.
Data table
MonthImpactIncidents
2023-12minor2
2024-01minor3
2024-01none1
2024-02minor1
2024-04minor2
2024-05minor2
2024-05none1
2024-06minor2
2024-06none1
2024-07major1
2024-07minor3
2024-08major1
2024-08minor4
2024-10minor1
2024-11minor1
2025-01minor1
2025-02critical1
2025-02minor4
2025-03minor2
2025-04minor1
2025-04none1
2025-05minor1
2025-06major1
2025-06minor3
2025-06none2
2025-07major5
2025-07minor2
2025-07none1
2025-08minor1
2025-09major1
2025-09minor1
2025-10major1
2025-10minor6
2025-11major1
2025-11minor1
2025-11none1
2025-12major1
2025-12minor2
2026-01major1
2026-01minor1
2026-02major1
2026-02minor3
2026-03minor1
2026-04major1
2026-04minor3
2026-05major1
2026-05minor5
2026-05none4
2026-06major2
2026-06minor10
2026-07major4
2026-07minor11
2026-08major1
2026-08minor10
2026-09major4
2026-09minor6
2026-10major1
2026-10minor1

Silent edits

No silent edits or deletions detected for Baseten yet. We compare every 10-minute snapshot of each incident.

The Weekly Rewind: one short weekly email on what changed at Baseten and the other vendors we track, including silent edits. Subscribe →

Pricing, trust and legal pages

Page snapshot history
PricingTrust / security26Jul2Aug91623306Sep1320274Oct11182026-10-17 Trust / security: baseline2026-10-17 Trust / security: baseline2026-10-17 Pricing: baseline
One dot per archived version. Grey = first archived (baseline), orange = text changed.
Data table
DatePageChange
2026-10-17Trust / securitybaseline
2026-10-17Trust / securitybaseline
2026-10-17Pricingbaseline
PageURLVersionsLast changedLast fetched OKHistory
Pricingbaseten.co/pricing12026-10-172026-10-17none yet
Trust / securitypartialtrust.baseten.co22026-10-172026-10-17none yet

No changes since the first snapshot. Each change links to its diff: the changed passages with a few words of context, never a full copy of the page.

Incident timeline

Latest 100 of 148 incidents. Full list: last 90 days · JSON · Markdown

Started (UTC)IncidentImpactDuration
Elevated errors on new model builds. Existing models are not affectedminor37 min
DeepSeek v4.1 outage on Model APIs. Dedicated Inference is not affectedmajor13 min
Elevated 500s in Single us-central Regionmajor13 min
Metrics degradation in UI and API. **Inference not affected**minor21 min
Intermittent 5xx for a subset of models in 1 US Central clusterminor1.4 h
Elevated inference 500s for a subset of models deployed in 1 US-East clustermajor42 min
Elevated inference 500s for a subset of models deployed in GCP central1major7 min
Metrics degradation in UI and API. **Inference not affected**minor11 min
Kimi K3 Model API outagemajor55 min
Elevated errors for models in a single India-based clusterminor45 min
Partial outage on Kimi K3 model API inference (non-US only)minor42 min
Partial outage on Nemotron Ultra Model API. **Dedicated Inference is not affected**minor6 min
Elevated inference 500s for models in a single US-based clustermajor24 min
Elevated errors for models in a single US cluster due to provider outageminor14 min
Elevated errors for deepseek-ai/DeepSeek-V4-Flash-0731 on Model APIs. **Dedicated Inference is not affected**minor41 min
Elevated inference 500s for models in an EU cluster due to provider outageminor41 min
Elevated errors for moonshotai/Kimi-K3 for US-pinned traffic on Model APIs. **Dedicated Inference is not affected**minor37 min
Elevated errors for moonshotai/Kimi-K3 for US-pinned traffic on Model APIs. **Dedicated Inference is not affected**minor1.3 h
Elevated errors for moonshotai/Kimi-K3 for US-pinned traffic on Model APIs. **Dedicated Inference is not affected**minor12 min
Elevated errors for moonshotai/Kimi-K3 for US-pinned traffic on Model APIs. **Dedicated Inference is not affected**minor48 min
Elevated errors for moonshotai/Kimi-K3 for US-pinned trafficminor46 min
Metrics degradation in UI and API. **Inference not affected**minor24 min
Elevated inference 502s for a subset of models in a single US clusterminor43 min
Elevated inference 502s for a subset of models in a single US clusterminor29 min
Slower than usual scale-ups for B200sminor12 min
Elevated inference failures for models in an EU clusterminor33 min
Slower than usual scale-ups in 1 us-central clusterminor19 min
GLM 5.2 Model API partial outage due to provider network failuremajor32 min
Elevated inference errors in 1 Canada cluster due to provider network outageminor6 min
Elevated errors in accessing the Baseten UI. **Inference is not affected**minor1.3 h
Partial Outage on Model APIsmajor2.1 h
Elevated inference 500s for models deployed in 1 US-east clusterminor14 min
Metrics degradation in UI and API. **Inference not affected**minor1.9 h
Elevated inference 500s — network outage in our cloud provider in Delawareminor14 min
Elevated errors for GLM 5.2 on Model APIs. **Dedicated Inference is not affected**major1.4 h
Elevated inference 500s for a subset of models deployed in 1 clusterminor16 min
Degraded metrics performance in dashboard and API. **Inference is not affected**minor1.2 h
Elevated errors in a single EU clustermajor59 min
Elevated error rates on GLM 5.2 Model APIs. **Dedicated Inference is not affected**minor35 min
Elevated inference 500s for models in 1 cluster due to cloud provider outageminor15 min
Elevated model deployment failures. **Inference is not affected**minor1.2 h
Elevated errors for dedicated inference in a subset of clustersmajor14 min
Slower than usual scale-ups. High failure rate for new model deploys. Existing replicas aren't impacted.minor44 min
Elevated errors for models in 1 Austin-based cluster affecting some models on B200sminor1.7 h
Elevated errors for models in 1 Sweden-based clusterminor1.4 h
Elevated errors for models in a single EU cloud providerminor44 min
Elevated errors for models in a single cloud providerminor44 min
Elevated errors in a single US-East clustermajor19 min
Elevated latencies for a subset of models in a US-East clusterminor1.1 h
Slower than usual scale-ups for some models using H100sminor2.3 h
Elevated async inference errors in a single clusterminor33 min
Slower than usual scale-ups in 1 India clusterminor14 min
Elevated errors for models in single regionminor14 min
Slower than usual scale-ups for L4s in US-Eastnone39 min
Slower than usual scale-ups in EU due to a provider failurenone1.6 h
Higher latencies for a subset of models in one cluster. Root caused and a fix is in progressnone37 min
Elevated errors in a single clusterminor2.0 h
Training cluster is down due to a provider failuremajor2.9 h
Intermittent failure in loading the webapp — inference is *not* affectednone42 min
Elevated errors for models in single regionminor47 min
Slower than usual scale-ups for a small subset of modelsminor49 min
Slower than usual scale-ups for a small subset of modelsminor4.8 h
Builds of new models are currently failing. **Inference is not affected**major55 min
Elevated deploy failures. Inference is **not** affected.minor2.0 h
gpt-oss model API service degradationminor17 min
Elevated 500s on Model APIs. **Dedicated Inference is not affected**major43 min
Partial inference outage in AWS us-east-1minor3.0 h
Network Errors in single EU Clusterminor3.4 h
Elevated inference latencies in AWS us-west-2minor2.2 h
Baseten web app is down. **Inference is unaffected**major24 min
Elevated latency for inference requests in single region in Baseten Cloud Westminor1.1 h
GPT-OSS on Model APIs is degraded. **Dedicated inference is not affected**.minor22 min
Slower than usual scale-ups and new deploys for all models in GCPminor55 min
Deepseek V3-0324 on Model APIs is down. **Dedicated inference is not affected**.major20 min
Elevated error rates for inference requests for a subset of models in GCP us-central1major19 min
New builds are failing to push. Inference is *not* affectedminor16 min
Elevated errors and delays in new model deploys in 1 cluster. Inference is *not* affected.none39 min
Elevated errors in model deploys and promotions in 2 clusters. Inference is *not* affected.major1.3 h
Slower than usual scale-ups in 1 regionminor3.7 h
Slower than usual scale-ups in 2 regionsminor4.2 h
Model logs are slow to load in a single cluster. Inference is not affected.minor15 min
Login timing out on webappminor6.6 h
Baseten Web Application is down due to AWS outage. Inference is unaffected.minor2.3 h
High latency on Baseten Web Application and Model Management APIs. Inference is unaffected.minor14 min
Build Infrastructure degraded due to Dockerhub outagemajor58 min
L4 capacity in single us-east region having issuesminor28 min
GCP is reporting elevated packet loss in us-central1minor16 min
Elevated inference 500s for a subset of models deployed in GCP central1major37 min
Elevated inference 500s for a subset of models deployed in GCP central1major59 min
Elevated inference 500s for a subset of models deployed in GCP central1major11 min
Elevated inference 500s for a subset of models deployed in GCP central1major15 min
Elevated errors in model APIs. Dedicated inference is *not* affected.major7 min
DeepSeek and Llama model APIs are down. Dedicated inference is *not* affected.none1.4 h
Elevated inference latencies in 3 clustersminor2.3 h
Issue with image builds for new modelsminor11 min
Elevated inference 500s for a subset of models deployed in GCP central1major6 min
Major outage in GCP with partial impact on several customersnone16 min
Deepseek V3 API Operationalnone0 min
Degraded performance only on Deepseek V3 0324minor0 min
The web application and the model management API are having intermittent failures. Inference is *not* affected.minor6 min