Langtrace Rate Limits
Langtrace does not publish explicit per-endpoint request rate limits for its REST API. The practical ceiling on Langtrace Cloud is the span allowance of the active plan (monthly/annual span quotas), rather than RPM/TPM throttles. The trace retrieval endpoint caps pageSize at 100 traces per request, which bounds read pagination. Self-hosted deployments are limited only by the capacity of the operator's own infrastructure. Specific throttle values are not reconciled in this artifact.
Langtrace Rate Limits is the machine-readable rate-limit profile for Langtrace AI on the APIs.io network, conforming to the API Commons Rate Limits specification.
It captures 4 rate-limit definitions, measuring traces, spans, and requests.
The profile also includes 2 backoff/retry policies defined and response codes documented for throttled.
Tagged areas include AI, LLM, Observability, OpenTelemetry, and Tracing.