INTer token latency
Also known as INTer token latency, AI INTer token latency
Definition
INTer token latency is the serving concept concerned with inter token latency during AI inference.
What inter token latency means
INTer token latency is the serving concept concerned with inter token latency during AI inference. In a serving system, define the measurement boundary before collecting data. State whether the worker is warm, which model and precision are active, how batching is configured, and whether the request is streamed. These details determine whether two similar measurements describe the same operating condition.
How it appears in a workload
An engineer can isolate this behavior in a warm serving test before comparing complete user tasks. Record relevant timestamps and runtime signals with the request rather than relying on one dashboard aggregate. A useful comparison includes request mix, arrival pattern, concurrency, and output limits. For routed traffic, retain the selected route so a change can be investigated rather than attributed to inter token latency without evidence.
Limitations and tradeoffs
A benchmark that omits cold starts, cache state, retries, or queueing may not represent production traffic. Use it with p50 and tail latency, useful token throughput, errors, memory pressure, and cost. The best configuration is the one that meets the application's reliability and responsiveness requirements under representative traffic.
How this relates to Weave
Weave Router comparisons can record inter token latency beside model, provider, workload, and request outcome. That context helps explain whether a routing change altered inter token latency, but Weave does not make an inference runtime faster by itself. Keep serving conditions visible when using these observations to compare complete AI tasks.
Explore Router