Where does this status come from?

From Baseten's own status page API at https://status.baseten.co. UpButler reads it once for everyone (not once per visitor) every 120 seconds with conditional requests, and shows it unchanged: incident titles and component names are Baseten's words.

How can my agent or app check Baseten status?

Fetch https://upbutler.com/status/baseten/status.agent.json: a small JSON document with a verdict (proceed, retry, fallback or pause) and retryAfterSec. No key is needed. The same answer is an MCP tool, upstream_status {"service":"baseten"}, on https://upbutler.com/mcp/public.

How do I know whether an outage is mine or Baseten's?

Add "baseten" to the dependencies of your UpButler workspace. When one of your monitors fails while Baseten has an incident that began around the same time, your incident is tagged "likely upstream" with their incident linked, and your on-call agent is told not to change code.

Is Baseten down?

Right now

No. Baseten is operational.

No incidents reported.

Read from status.baseten.co 2 min ago · every 120s

For agents

proceed

Proceed.

GET upbutler.com/status/baseten/status.agent.json

MCP: upstream_status {"service":"baseten"}

Dedicated model deployments and model APIs.

What Baseten reports

Operational

Taken as is from Baseten's own status page API. Incident titles and component names below are theirs.

Open status.baseten.co

UpButler's independent probe

There is no keyless endpoint of Baseten that says anything useful, so UpButler does not probe it. To check your own Baseten account, add a monitor with your key: it is yours alone and catches what a shared probe cannot.

Baseten components

6 operational

Dedicated InferenceOperational
Model APIsOperational
TrainingOperational
Model Management APIOperational
Web ApplicationOperational
Homepage and DocsOperational

Baseten incidents, last 90 days

4 finished incidents seen since UpButler started tracking on 2026-10-10, 2 of them rated major or critical by Baseten. A typical one lasted 21 min; the longest 37 min.

Started (UTC)	Incident	Impact	Lasted
2026-10-09 21:29	Elevated errors on new model builds. Existing models are not affected	minor	37 min
2026-10-06 04:35	DeepSeek v4.1 outage on Model APIs. Dedicated Inference is not affected	major	13 min
2026-09-29 19:44	Elevated 500s in Single us-central Region	major	13 min
2026-09-29 01:07	Metrics degradation in UI and API. Inference not affected	minor	21 min

Tell your outage from Baseten's

Declare that your project depends on Baseten. When one of your monitors fails while Baseten has an incident that began around the same time, UpButler tags your incident "likely upstream" with their incident linked, says so in the alert and the AI report, and tells your on-call agent not to change code.

npx upbutler init finds the dependency from your env var names and packages. The catalog, dependencies and upstream-aware incidents are on every plan, including Free.

Start free How it works

upbutler.yaml

# upbutler.yaml
dependencies:
  - baseten

Ask before you retry

curl -s https://upbutler.com/status/baseten/status.agent.json

status.agent.json (live)

{
  "schema": "upbutler.upstream-status/v1",
  "service": "baseten",
  "verdict": "proceed",
  "status": "operational",
  "reason": "No incidents reported",
  "retryAfterSec": null,
  "incident": null,
  "probe": null
}

Questions

Is Baseten down right now?: No. As of 2026-10-10 05:10 UTC, Baseten is operational. This page reads the status again every 2 minutes.
Where does this status come from?: From Baseten's own status page API at https://status.baseten.co. UpButler reads it once for everyone (not once per visitor) every 120 seconds with conditional requests, and shows it unchanged: incident titles and component names are Baseten's words.
How can my agent or app check Baseten status?: Fetch https://upbutler.com/status/baseten/status.agent.json: a small JSON document with a verdict (proceed, retry, fallback or pause) and retryAfterSec. No key is needed. The same answer is an MCP tool, upstream_status {"service":"baseten"}, on https://upbutler.com/mcp/public.
How do I know whether an outage is mine or Baseten's?: Add "baseten" to the dependencies of your UpButler workspace. When one of your monitors fails while Baseten has an incident that began around the same time, your incident is tagged "likely upstream" with their incident linked, and your on-call agent is told not to change code.

More in hosting and compute

UpButler is not affiliated with Baseten. Status and incident text belong to Baseten and are read from their public status source; the probe result is UpButler's own measurement.