2026-10-13T03:37:55Z https://www.scidb.cn/oai

10.57760/sciencedb.013yr 2026-09-29T15:42:58Z

2026-09-29 Prompt Component Cost Dataset for LLM Deployment doi:10.57760/sciencedb.013yr en This dataset investigates the impact of prompt components on LLM inference cost in terms of token consumption, latency, and output length. It contains a main full-factorial experiment with 256 configurations (215,040 inferences) and four engineering validation experiments: a code-level simulation (Plan C), a physics simulation (EmbodiedJev), cross-domain validation on the public ALFRED benchmark, and a real FastAPI service deployment. Each inference records input/output/total tokens, latency, output length metrics, and success rates where applicable. The dataset includes raw per-inference records, data dictionaries, a quality report, and experiment code for reproducibility. All dependent variables are token, latency, and output length; quality scoring is not involved. Prompt engineering; LLM inference cost; Token consumption; Latency; Full-factorial design; Component additivity; Large language models 周科宇 PUBLIC https://creativecommons.org/licenses/by/4.0/ dataset Science Data Bank