Vendor record
LangSmith
Checked
Front door check counts and LangSmith’s own incident posts. Use them to investigate a dependency; neither confirms what happened in your app.
Front door checks
We send a request to a documented LangSmith endpoint and count the checks that got the answer it is documented to give.
No clear answer in 24 hours. These counts are from before this check went quiet.
Front door reachable in 1,441 of 1,441 checks with a clear answer, last 30 days, checked every 15 minutes from a single CheckUpstream location.
1,438 more checks gave no clear answer and are not counted.
- Endpoint checked
- api.smith.langchain.com
- Scope
- apiNo vendor region
- First check in this window
- Latest clear answer
Checks 15 minutes apart cannot see disruptions shorter than that. A check that reached the front door does not show that every LangSmith product, region or your app worked.
How we count front door checksLangSmith says
Incident posts from LangSmith’s status page, with its titles, impact levels and times. They say what LangSmith chose to post, not what reached your app.
A closed record shows when our record closed. Some older records closed when a post left the status page, without a resolution post from the vendor.
18
incidents LangSmith posted, last 180 days
Median recorded duration: 1h 4m. From 18 incidents with vendor-supplied starts and recorded closure times.
Most recent records · all dates
Thread-scoped sandbox initialization timeouts on new agents
MinorLangSmith’s postStarted, per LangSmith
Closed in our record(2h 18m)
Agent-scoped sandbox fails to initialize on new agents
MajorLangSmith’s postStarted, per LangSmith
Closed in our record(3h 42m)
Elevated error rate for bulk exports
MajorLangSmith’s postStarted, per LangSmith
Closed in our record(34m)
Fetching traces timing out
MajorLangSmith’s postStarted, per LangSmith
Closed in our record(36m)
[GCP US only] LangSmith Deployments Builds Outage
MajorLangSmith’s postStarted, per LangSmith
Closed in our record(2h 37m)
13 older records
Partial ingestion failures for traces with large payloads
MajorLangSmith’s postStarted, per LangSmith
Closed in our record(16h 37m)
Agent tool calls failing on Anthropic Claude models
MinorLangSmith’s postStarted, per LangSmith
Closed in our record(6h 25m)
High latencies and increased rate of 500s for analytical queries (stats and dashboards)
MinorLangSmith’s postStarted, per LangSmith
Closed in our record(2h 57m)
Build failure on new revisions
Not specifiedStarted, per LangSmith
Closed in our record(43m)
Ingestion is delayed
Not specifiedStarted, per LangSmith
Closed in our record(30m)
Elevated Errors in Fleet
Not specifiedStarted, per LangSmith
Closed in our record(10m)
Performance degradation of legacy storage cluster
Not specifiedStarted, per LangSmith
Closed in our record(1h 4m)
Elevated LangSmith API error rate
Not specifiedStarted, per LangSmith
Closed in our record(9m)
Billing usage ingestion delays
Not specifiedStarted, per LangSmith
Closed in our record(7h 35m)
Bulk exports not being processed
Not specifiedStarted, per LangSmith
Closed in our record(3h 30m)
Sandbox create failing
Not specifiedStarted, per LangSmith
Closed in our record(10m)
Bulk export failures
Not specifiedStarted, per LangSmith
Closed in our record(1d 7h)
Increased latency in LangSmith API backend
Not specifiedStarted, per LangSmith
Closed in our record(59m)
Your code, your dependencies
See which of your code paths call LangSmith
Connect GitHub or GitLab to find where your public or private repository uses LangSmith. Review each match and your alert settings.
Free to start. No credit card.
Use this record on your site
Add LangSmith status to your page.
Choose the format your page supports, then copy the code. Badges show the recorded vendor status; they do not establish impact on your app.
Frequently Asked Questions
Is LangSmith currently down?
LangSmith's latest recorded status is Degraded. Check the timestamp and linked source at the top of this page. A vendor status report does not establish whether your application was affected.
When did LangSmith last have an outage?
The most recent closed incident record began 42 days ago and spans 2h 18m. The vendor reported degraded performance. Closure may reflect a disappeared post or an expired tracking period; it does not confirm vendor or application recovery. Check the dated history and source links.
Does CheckUpstream publish an uptime percentage for LangSmith?
No. CheckUpstream checks LangSmith’s front door every 15 minutes and publishes how many checks reached it over the last 30 days, with the endpoint checked. Checks 15 minutes apart cannot see disruptions shorter than that. A percentage would claim more than the checks can show.
How do I monitor LangSmith in production?
Create your account, connect GitHub or GitLab and choose a public or private repository. Review the vendor matches and your alert settings. Available notification channels and history depend on your plan.
How does CheckUpstream track LangSmith?
This record separates vendor-reported incidents from independent checks. Sources and coverage vary by vendor: review the linked source, check time and measurement scope. Neither kind of evidence establishes SLA credit eligibility.