LangSmith · Rate Limits

Langsmith Rate Limits

LangSmith does not publish per-endpoint request-rate limits in its public docs; the primary throttling surface is monthly base-trace and Fleet-run quotas defined on each plan. Enterprise contracts negotiate custom limits.

Langsmith Rate Limits is the machine-readable rate-limit profile for LangSmith on the APIs.io network, conforming to the API Commons Rate Limits specification.

It captures 5 rate-limit definitions, measuring trace, run, and varies.

The profile also includes 2 backoff/retry policies defined and response codes documented for throttled.

Tagged areas include AI, LLM, Observability, Evaluations, and LangChain.

5 Limits Throttle: 429
AILLMObservabilityEvaluationsLangChainRate LimitingQuotasThrottling

Limits

Developer Monthly Base Traces account
trace · monthly
5000
Hard cap on free tier base traces; overage requires upgrading to a paid plan.
Plus Monthly Base Traces (Included) account
trace · monthly
10000
Included allowance; additional traces billed at $2.50 per 1,000.
Developer Fleet Runs account
run · monthly
50
Maximum monthly Fleet agent runs on the Developer plan.
Plus Fleet Runs (Included) account
run · monthly
500
Included Fleet agent run allowance on the Plus plan.
Enterprise Custom Limits account
varies
contract
Enterprise customers negotiate custom trace, run, and rate-limit ceilings.

Policies

Backoff Strategy
Clients should implement exponential backoff with jitter and honor any Retry-After header.
Trace Batching
SDKs batch trace events client-side before flushing to the ingest endpoint to minimize per-request overhead.

Sources