Is LangSmith down right now?
No, it is up
Operational · All systems operational
Components
All 44 components operational.
Show all 44 components
- LangSmith APIOperational
- LangSmith ApplicationOperational
- LangSmith BillingOperational
- LangSmith Bulk ExportsOperational
- LangSmith Deployments Control PlaneOperational
- LangSmith Deployments Data PlaneOperational
- LangSmith FleetOperational
- LangSmith LLM GatewayOperational
- LangSmith PromptHubOperational
- LangSmith Run IngestionOperational
- LangSmith SandboxesOperational
- LangSmith APIOperational
- LangSmith ApplicationOperational
- LangSmith BillingOperational
- LangSmith Bulk ExportsOperational
- LangSmith Deployments Control PlaneOperational
- LangSmith Deployments Data PlaneOperational
- LangSmith FleetOperational
- LangSmith LLM GatewayOperational
- LangSmith PromptHubOperational
- LangSmith Run IngestionOperational
- LangSmith SandboxesOperational
- LangSmith APIOperational
- LangSmith ApplicationOperational
- LangSmith BillingOperational
- LangSmith Bulk ExportsOperational
- LangSmith Deployments Control PlaneOperational
- LangSmith Deployments Data PlaneOperational
- LangSmith FleetOperational
- LangSmith LLM GatewayOperational
- LangSmith PromptHubOperational
- LangSmith Run IngestionOperational
- LangSmith SandboxesOperational
- LangSmith APIOperational
- LangSmith ApplicationOperational
- LangSmith BillingOperational
- LangSmith Bulk ExportsOperational
- LangSmith Deployments Control PlaneOperational
- LangSmith Deployments Data PlaneOperational
- LangSmith FleetOperational
- LangSmith LLM GatewayOperational
- LangSmith PromptHubOperational
- LangSmith Run IngestionOperational
- LangSmith SandboxesOperational
User reports
Having trouble with LangSmith? Reports are anonymous and only counted, no cookies.
LangSmith uptime, last 90 days
Each bar is one UTC day, coloured by the worst state we saw on the official status page.
Recent LangSmith incidents
Increased latency and 500 rate · 30 Oct 2026, 22:29 UTC · major
resolved · 29 Oct 2026, 19:56 UTC
A migration caused an unexpected spike in our Postgres memory usage. This resulted in latency increases, and eventually pod restarts which caused some existing connections to 500 for about two minutes. The issue was mitigated by 12:58pm PT.
Sandbox Performance Degraded · 14 Oct 2026, 19:47 UTC · 9 days · minor
resolved · 23 Oct 2026, 11:18 UTC
The bad host has been removed from the fleet and we aren’t seeing any issues.
monitoring · 14 Oct 2026, 20:08 UTC
We've identified the issue as a bad host and resolved. Monitoring for any abnormalities.
investigating · 14 Oct 2026, 19:47 UTC
Following a caching change sandbox performance is experiencing some degradation. We are investigating.
APAC Region Querying is down · 12 Oct 2026, 06:46 UTC · major
resolved · 12 Oct 2026, 06:24 UTC
An image pull failure temporarily took down our querying services. We swapped to a pullable image resolving the issue.
investigating · 12 Oct 2026, 06:08 UTC
We are seeing errors fetching runs in APAC.
Seeing some issues logging into the application · 12 Oct 2026, 05:42 UTC · 2 days · major
resolved · 14 Oct 2026, 16:02 UTC
Underlying captcha issue has been resolved.
monitoring · 12 Oct 2026, 06:10 UTC
We were having an issue with our captcha provider. For now we have disabled captcha which has resolved the issue
investigating · 12 Oct 2026, 05:42 UTC
Some users can't log in to or sign up for LangSmith right now. Login attempts may time out or fail. Users who are already logged in should not be affected. We are actively investigating and will post another update as we learn more.
LLM Gateway service interruption · 8 Oct 2026, 10:05 UTC · critical
resolved · 8 Oct 2026, 07:43 UTC
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.
investigating · 8 Oct 2026, 07:08 UTC
The LLM Gateway ([gateway.smith.langchain.com](http://gateway.smith.langchain.com)) is returning an elevated rate of 502 errors. We are investigating.
Increased latency in Run Query V1 APIs · 8 Oct 2026, 00:48 UTC · 1 h 42 min · minor
resolved · 8 Oct 2026, 02:30 UTC
Capacity remained stable in the last hour. Incident resolved.
monitoring · 8 Oct 2026, 01:39 UTC
Query API performance is back to normal after capacity adjustment. We are currently monitoring for further problems.
investigating · 8 Oct 2026, 00:48 UTC
We are investigating a latency increase in our V1 Run Query APIs. V2 Run Query APIs backed by SmithDB are unaffected.
LangSmith Deployment Database Provisioning Error · 3 Oct 2026, 05:10 UTC · 5 h 3 min · major
resolved · 3 Oct 2026, 10:13 UTC
This is now resolved.
identified · 3 Oct 2026, 06:46 UTC
Issue has been identified, attempted mitigation is being deployed.
investigating · 3 Oct 2026, 05:55 UTC
Creating new deployments and new revisions for dedicated instances is failing for LangSmith Deployment in all GCP regions due to an issue with an upstream cloud provider. Existing deployments continue to run and serve traffic.
investigating · 3 Oct 2026, 05:10 UTC
Creation of new LangSmith deployment dedicated instances are failing during database provisioning because of an issue with an upstream cloud provider. Only GCP regions are affected.
Thread-scoped sandbox initialization timeouts on new agents · 4 Sept 2026, 17:19 UTC · 2 h 18 min · minor
resolved · 4 Sept 2026, 19:38 UTC
All systems are operational
monitoring · 4 Sept 2026, 19:31 UTC
The fix has been deployed. All systems are operational
identified · 4 Sept 2026, 18:12 UTC
We have identified the cause and are working on resolving the issue.
investigating · 4 Sept 2026, 17:19 UTC
This is impacting the creation of new agents with a computer per thread configuration
Agent-scoped sandbox fails to initialize on new agents · 2 Sept 2026, 17:04 UTC · 3 h 43 min · major
resolved · 2 Sept 2026, 20:47 UTC
All systems are operational
monitoring · 2 Sept 2026, 20:32 UTC
The fix has been deployed. All systems are operational
identified · 2 Sept 2026, 17:59 UTC
We have identified the root cause of this incident and are actively working on a fix. The issue originates from a recent change to how sandbox slugs are generated in our backend systems, which now derive slugs directly rather than referencing sandbox IDs. This has introduced a mismatch between the values returned by the backend and those the frontend expects. We will share a further update as remediation progresses.
investigating · 2 Sept 2026, 17:04 UTC
This affects only newly created agents with a shared computer.
Elevated error rate for bulk exports · 1 Sept 2026, 19:43 UTC · 34 min · major
resolved · 1 Sept 2026, 20:17 UTC
This incident has been resolved.
monitoring · 1 Sept 2026, 19:53 UTC
We have mitigated the issue and have seen recovery. We're continuing to monitor.
investigating · 1 Sept 2026, 19:43 UTC
We are investigating an elevated error rate for bulk exports executions. Bulk exports are currently delayed. New bulk exports can still be created.
Fetching traces timing out · 26 Aug 2026, 16:16 UTC · 37 min · major
resolved · 26 Aug 2026, 16:53 UTC
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
monitoring · 26 Aug 2026, 16:42 UTC
We've identified the query causing problems to our systems and have pushed a mitigation. All systems look recovered but we are monitoring for any other problems.
investigating · 26 Aug 2026, 16:27 UTC
This is primarily affecting run querying
investigating · 26 Aug 2026, 16:26 UTC
Currently dealing with some heavy queries causing issues fetching traces. We are scaling out our system which should remediate.
investigating · 26 Aug 2026, 16:16 UTC
We are currently investigating an issue where some trace loads are timing out
[GCP US only] LangSmith Deployments Builds Outage · 20 Aug 2026, 15:54 UTC · 2 h 37 min · major
resolved · 20 Aug 2026, 18:32 UTC
New revisions are deploying correctly.
monitoring · 20 Aug 2026, 17:54 UTC
New revisions are being processed normally. Validating recovery.
identified · 20 Aug 2026, 17:05 UTC
GCP is having an incident in us-west-1. Deployments may experience issues deploying new revisions.
monitoring · 20 Aug 2026, 16:30 UTC
Builds are being processed. Validating recovery.
investigating · 20 Aug 2026, 15:54 UTC
Builds for new revisions of LangSmith Deployments are not being processed.
Partial ingestion failures for traces with large payloads · 6 Aug 2026, 15:03 UTC · 16 h 37 min · major
resolved · 7 Aug 2026, 07:40 UTC
The full fix took an extraordinarily long time to release due to an outage at our CI provider. In the meantime, the mitigation we had deployed mitigated the problem.
monitoring · 6 Aug 2026, 16:43 UTC
The service is temporarily patched. Large payloads are now ingested normally.
identified · 6 Aug 2026, 15:33 UTC
Updated affected regions
identified · 6 Aug 2026, 15:03 UTC
Traces including large payloads might currently fail to be ingested or can be delayed. We are working on a fix.
LangSmith is listed under Dev tools. Status data comes from the official status page and is checked every 5 minutes.All AI service statuses