LangSmith outage history

Biggest LangSmith outages

Ranked by the official impact level, then by how long they lasted. Each has its own page with the cause, the fix time and every official update.

1. Oct 12, 2026: Seeing some issues logging into the application 2 days 10 hours · rated "Major"
2. Aug 6, 2026: Partial ingestion failures for traces with large payloads 16 hours 37 min · rated "Major"
3. Oct 3, 2026: LangSmith Deployment Database Provisioning Error 5 hours 3 min · rated "Major"
4. Sep 2, 2026: Agent-scoped sandbox fails to initialize on new agents 3 hours 43 min · rated "Major"

Every smaller LangSmith incident

Minor and short incidents from the LangSmith Global status page, newest first, each with a line from the official updates. Times are UTC.

October 2026

• Oct 14, 2026, 19:47 UTC · Sandbox Performance Degraded

  ongoing, 7 days 17 hours so far · rated "Minor" · still open at our last refresh

  "Following a caching change sandbox performance is experiencing some degradation. We are investigating."

• Oct 12, 2026, 06:46 UTC · APAC Region Querying is down

  duration not stated · rated "Major"

  "An image pull failure temporarily took down our querying services. We swapped to a pullable image resolving the issue."

• Oct 8, 2026, 10:05 UTC · LLM Gateway service interruption

  duration not stated · rated "Critical"

  "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."

• Oct 8, 2026, 00:48 UTC · Increased latency in Run Query V1 APIs

  1 hour 42 min · rated "Minor"

  "Capacity remained stable in the last hour. Incident resolved."

September 2026

• Sep 4, 2026, 17:19 UTC · Thread-scoped sandbox initialization timeouts on new agents

  2 hours 18 min · rated "Minor"

  "All systems are operational"

• Sep 1, 2026, 19:43 UTC · Elevated error rate for bulk exports

  34 minutes · rated "Major"

  "We are investigating an elevated error rate for bulk exports executions. Bulk exports are currently delayed. New bulk exports can still be created."

August 2026

• Aug 26, 2026, 16:16 UTC · Fetching traces timing out

  37 minutes · rated "Major"

  "A pathological query was impacting other query services. We've added protections against the pathological case and scaled up our query services. All services are now functioning as normal"

• Aug 20, 2026, 15:54 UTC · [GCP US only] LangSmith Deployments Builds Outage

  2 hours 37 min · rated "Major"

  "New revisions are deploying correctly."

• Aug 5, 2026, 15:27 UTC · Agent tool calls failing on Anthropic Claude models

  6 hours 25 min · rated "Minor"

  "Resolved. Fix is now deployed that skips an unsupported tool schema and logs a warning instead of failing the request."

• Aug 3, 2026, 18:15 UTC · High latencies and increased rate of 500s for analytical queries (stats and dashboards)

  2 hours 58 min · rated "Minor"

  "The issue has been resolved, and service has returned to normal. We identified the root cause, implemented a mitigation, and have observed stable system performance following the change."

July 2026

• Jul 15, 2026, 18:23 UTC · Internal errors and elevated latency on US LangSmith instance

  duration not stated · rated "Major"

  "We are actively investigating an issue impacting run ingestion, frontend and API access in the LangSmith US instance."

• Jul 15, 2026, 18:23 UTC · Increased trace latency with LangSmith

  duration not stated · rated "Minor"

  "All LangSmith services are operational after the us-central1 region service impact was addressed by Google Cloud Platform."

• Jul 15, 2026, 18:23 UTC · Run ingest delays and slow queries

  duration not stated · rated "Major"

  "Performance has returned to historic norms."

• Jul 15, 2026, 18:23 UTC · New Revisions failing for LangGraph Platform Deployments

  duration not stated · rated "Major"

  "New revisions are failing for LangGraph Platform deployments. Engineers have identified the issue and pushed out a fix."

• Jul 15, 2026, 18:23 UTC · Increased latency on Run Ingest

  duration not stated · marked as no impact

  "Between 1652 and 1711 UTC, an issue with a production deployment caused a backlog in our run ingest queues, delaying the display of traces in the LangSmith UI. No runs were blocked from ingest during this time."

• Jul 15, 2026, 18:23 UTC · Sandbox create failing

  duration not stated · rated "Major"

  "Fix is rolling out"

• Jul 15, 2026, 18:23 UTC · Elevated run ingest latency in US instance of LangSmith

  duration not stated · rated "Minor"

  "We have identified a performance regression in our production database and are working with our vendor to resolve. Run ingest may experiment intermittent periods of increased latency of up to 60s while we work to mitigate the issue."

• Jul 15, 2026, 18:23 UTC · Elevated 5xx rate on run ingest and some API endpoints

  duration not stated · rated "Major"

  "All error rates have been at baseline level for almost 24 hours."

• Jul 15, 2026, 18:23 UTC · Increased Read latency in LangSmith EU Instance

  duration not stated · rated "Minor"

  "We are investigating increased read latency in the LangSmith EU instance. Run ingest is not affected at this time."

• Jul 15, 2026, 18:23 UTC · Login and Run Ingestion impacted for LangSmith SaaS

  duration not stated · rated "Critical"

  "One of our underlying cloud services was impacted triggering the outage. Further details will be shared offline. Appreciate all the patience"

• Jul 15, 2026, 18:23 UTC · Billing usage ingestion delays

  duration not stated · rated "Minor"

  "The backlog has completed processing. This incident is resolved."