- Level
- confirmed
- Worst impact
- Major outage
- LangSmith says
- 2026-10-08 07:08 to 07:43 UTC (35m)
- Down Index
- 54of 100
What to do
Check whether your product depends on LangSmith. Check your stack
Drop a package.json, lockfile, Terraform or a list of domains at down.guide to see every provider you depend on.Confirm your retries, queues and scheduled jobs caught up after the 0m it lasted.
Anything that failed between 2026-10-08 10:05 UTC and 2026-10-08 07:43 UTC may need a replay.Subscribe to LangSmith's feed to hear about the next one first. RSS feed
https://down.guide/feed?provider=langsmith works in Slack (/feed subscribe), Discord feed bots and any RSS reader.
Root cause
It was due to an incorrect infrastructure configuration change that stopped traffic from reaching the gateway.
Category: Deploy or config change
Read the postmortemUpdates from LangSmith 2
- investigating
The LLM Gateway (gateway.smith.langchain.com (http://gateway.smith.langchain.com)) is returning an elevated rate of 502 errors. We are investigating.
provider
- resolved
From 07:08 to 07:43 UTC on October 8, 2026, the LLM Gateway (gateway.smith.langchain.com (http://gateway.smith.langchain.com)) returned high 502 error rates. It was due to an incorrect infrastructure configuration change that stopped traffic from reaching the gateway. We fully restored the service at 07:43 UTC, and no other LangSmith services were affected. We're sorry for the disruption.
provider
Reports count in aggregate; nothing about you is shown.
Corrections
None so far.
Something wrong on this page? Report an error or send us a note. Every fix is listed here.
Questions about DWN-fcd9fdea78
Is LangSmith still down?
No, this incident was resolved 2026-10-08 07:43 UTC. For LangSmith's live state, see https://down.guide/providers/langsmith.
How long did it last?
0m, from 2026-10-08 10:05 UTC to 2026-10-08 07:43 UTC, by the times LangSmith posted.
What caused it?
Deploy or config change. LangSmith wrote: "It was due to an incorrect infrastructure configuration change that stopped traffic from reaching the gateway." The postmortem: https://global.status.smith.langchain.com/incidents/01M4DFKCK22TD3N84814NSJJ9W
Where does this come from?
LangSmith's official status page, https://global.status.smith.langchain.com/gcp-us, quoted verbatim. down.guide's own probes, reports and social counts are labeled as ours.