@article{cacheawarepromptcompressionatwotiercostm,
  title = {Cache-Aware Prompt Compression:A Two-Tier Cost Model for LLM API Caching},
  author = {Yan Song},
  year = {2026},
  eprint = {2607.15516},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2607.15516},
}