langfuse.generation.latency

LLM generation request latency

Dimensions:None

Available on:

Latency of LLM generation requests

Dimensions:None

Sources

Technical Annotations (4)

Error Signatures (3)

API failureserror code

content policy violationserror code

parsing errorserror code

Technical References (1)

blue-green deploymentconcept

High latency detected in LLM execution traceswarning

▸

Automated rollback prevents prompt deployment failures from impacting productioncritical

▸

Response latency degradation indicates prompt performance issueswarning

▸

High error rates or latency spikes indicate system degradationwarning

▸