# Latency / Throughput/Batching

> "latency" (performance-core layer) is traded against "Throughput/Batching" (performance-core layer) — a principle cannot be scope-separated from a quality, metric, or cost it competes with; resolve by measuring "Throughput/Batching" and choosing an explicit operating point.

Record: `tension:latency-throughput-batching`
Kind: tension
Canonical: https://banes-lab.com/ontology/schema#tension-latency-throughput-batching

## tensions-with

- [Latency](https://banes-lab.com/records/arch/latency.md)
- [Throughput/Batching](https://banes-lab.com/records/lex/throughput-batching.md)