B
Outage recap · Baseten

Baseten outage — July 2, 2026

On July 2, 2026, Baseten had 3 reported incidents on Baseten's official status page. Below is what was reported — impact, timing, and the AI services the same upstream outage could affect.

Degraded metrics performance in dashboard and API. **Inference is not affected**

minor
Started
Jul 2, 6:35 PM EDT
Resolved
Jul 2, 7:13 PM EDT
Duration
39 min

Baseten's updates (3)

  1. investigating · Jul 2, 6:00 PM EDT

    We are currently investigating this issue.

  2. monitoring · Jul 2, 6:53 PM EDT

    A fix has been implemented and we are monitoring the results.

  3. resolved · Jul 2, 7:13 PM EDT

    This incident has been resolved.

What our checks recorded

We checked Baseten 8 times from Baseten's start time to its resolution, once every five minutes. Every one of them reached Baseten's site, so this incident did not show up as a failed page load. Our check loads the public site; it cannot see an API error or a broken feature. Median response time was 95 ms, against 86 ms over the 24 hours before. Baseten posted the incident at Jul 2, 6:00 PM EDT.

Updates are Baseten's own words from its status page (status: resolved); we never add an inferred cause. The vendor's incident page ↗

Elevated inference 500s for a subset of models deployed in 1 cluster

minor
Started
Jul 2, 8:21 PM EDT
Resolved
Jul 2, 8:36 PM EDT
Duration
16 min

Baseten's updates (3)

  1. identified · Jul 2, 8:21 PM EDT

    The issue has been identified and a fix is being implemented.

  2. identified · Jul 2, 8:36 PM EDT

    We are continuing to work on a fix for this issue.

  3. resolved · Jul 2, 8:36 PM EDT

    This incident has been resolved.

What our checks recorded

We checked Baseten 3 times from Baseten's start time to its resolution, once every five minutes. Every one of them reached Baseten's site, so this incident did not show up as a failed page load. Our check loads the public site; it cannot see an API error or a broken feature. Median response time was 80 ms, against 86 ms over the 24 hours before. Baseten posted the incident at Jul 2, 8:21 PM EDT.

Updates are Baseten's own words from its status page (status: resolved); we never add an inferred cause. The vendor's incident page ↗

Elevated errors for GLM 5.2 on Model APIs. **Dedicated Inference is not affected**

major
Started
Jul 2, 10:59 PM EDT
Resolved
Jul 3, 12:25 AM EDT
Duration
1h 26m

Baseten's updates (4)

  1. investigating · Jul 2, 10:59 PM EDT

    We are currently investigating this issue.

  2. investigating · Jul 2, 11:06 PM EDT

    We are continuing to investigate this issue.

  3. monitoring · Jul 2, 11:56 PM EDT

    A fix has been implemented and we are monitoring the results.

  4. resolved · Jul 3, 12:25 AM EDT

    This incident has been resolved.

What our checks recorded

We checked Baseten 17 times from Baseten's start time to its resolution, once every five minutes. Every one of them reached Baseten's site, so this incident did not show up as a failed page load. Our check loads the public site; it cannot see an API error or a broken feature. Median response time was 105 ms, against 84 ms over the 24 hours before. Baseten posted the incident at Jul 2, 10:59 PM EDT.

Updates are Baseten's own words from its status page (status: resolved); we never add an inferred cause. The vendor's incident page ↗

AIDownCheck is not affiliated with Baseten. This recap summarizes incidents published on Baseten's official status page.