Live  /  Baseten  /  Incident

Baseten: Elevated errors for multiple models on Model APIs

Baseten · baseten.coMinor incidentResolved2026-11-14 06:58 UTC
Public — what happened

Summary

Baseten said it saw a higher-than-normal rate of errors on two models in its Model APIs, GLM 5.3 and DeepSeek V4.1 Flash, starting at 06:22 UTC on 2026-11-14. By 06:35 UTC the company said DeepSeek V4.1 Flash had fully recovered and it expected GLM 5.3 to follow within about 10 minutes. At 06:45 UTC Baseten reported GLM 5.3 had recovered and it was continuing to monitor, and the incident was marked resolved at 06:58. The company did not state a cause in the text provided.

Affected

Model APIs

As listed on Baseten’s status page.

Timeline

Source of record: provider status page. Summary written by SquidGrid from the provider’s published updates; times in UTC.

Independent path health

The status page is the symptom. SquidGrid measures the paths that reach Baseten against their own baselines — whether the routes carrying your traffic degraded, at which handoff, and who owns that stretch.

🔒 Sign in to see
Customers get the live Provider Assessment Report for Baseten: its full incident track record, what tends to break, and recent public reports of problems.

Included with any paid plan.

Open the Baseten report →

More from Baseten

Covered in The Squid’s Ink, Week 47, 2026, our weekly internet health report.

The full archive is on the Baseten status & history page.

Related: Baseten status & history. SquidGrid is not affiliated with Baseten.