generated/token_usage.pb library

Classes

TokenUsage
One token-accounting shape embedded by every result and metrics message, replacing the input/output/total/throughput quadruple that was copied inline across LLM, VLM, and RAG results. Names follow the OpenAI Responses API; the timing fields follow llama.cpp's timings object, which names the phase it measures.

Extensions

GeneratedMessageGenericExtensions on T
Extensions on GeneratedMessages.