How this calculator works
Enter embedding latency (ms), vector retrieval (ms), reranking latency (ms), first-token latency (ms). Select Calculate to apply the displayed formula and review the labeled results.
Formula / method
Total latency = embedding + retrieval + reranking + generation first-token
Worked example
Use the documented default inputs to model rag retrieval latency.
Assumptions and limitations
Inputs represent stable average operating conditions and the displayed equation applies.
This is a planning model; real systems and measurements can require domain-specific corrections.