Metraipolis › archive › dc_6dce6d1e35fc

Pricing Time, Not Just Tokens: Latency-Aware Mechanism Design for LLM Inference — arXiv:2609.40098

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.40098
License (as archived)
CC0-1.0
Archived
2026-10-07T13:16:33.872Z
SHA-256 of the archived text
c1085abca5a97f9f6f81c99d0c6fcc966f84a519cecc6c36f9a5f8fe107b9779
Stable URL of this page
https://metraipolis.com/documento/dc_6dce6d1e35fc

How to cite

Pricing Time, Not Just Tokens: Latency-Aware Mechanism Design for LLM Inference — arXiv:2609.40098 — arXiv (en), https://arxiv.org/abs/2609.40098 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_6dce6d1e35fc (Metraipolis archive dc_6dce6d1e35fc, sha256 c1085abca5a97f9f6f81c99d0c6fcc966f84a519cecc6c36f9a5f8fe107b9779)
BibTeX
@misc{dc6dce6d1e35fc,
  title = {Pricing Time, Not Just Tokens: Latency-Aware Mechanism Design for LLM Inference — arXiv:2609.40098},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.40098},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_6dce6d1e35fc; sha256 c1085abca5a97f9f6f81c99d0c6fcc966f84a519cecc6c36f9a5f8fe107b9779},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.40098. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

The economic theory of LLM pricing treats tokens as a homogeneous commodity considering aggregate token count as the main features buyers and sellers consider. We model inference as a service market where buyers have three-dimensional private information - willingness-to-pay, task volume, and time preference - and utility depends on latency slack alongside token quantities. Our main result is a separation theorem: discrete hardware tiers induce endogenous self-selection on time preferences, reducing three-dimensional screening to standard one-dimensional screening within each tier. We derive the cost structure from GPU inference physics - compute-bound prefill and bandwidth-bound decode - and characterize optimal tiered mechanisms via virtual-value techniques. Optimal per-task prices are volume-independent, providing theoretical grounding for flat per-token API pricing. We verify the mechanism empirically by calibrating to 8-GPU clusters of H100 and B200 hardware. The separation theorem holds in 83% of 105 tested configurations overall, rising to 96% at economically relevant WTP scales. A seller adopting two-tier pricing under the optimal mechanism captures 26-66% higher profit than the best single-tier alternative, with gains driven by efficient cross-tier allocation in regimes where hardware costs are a significant fraction of per-request value.

Tema degli esploratori: economia dei servizi IA (retro-catalogo arXiv: annunci del 2026-10-01 in cs.GT).
Categorie arXiv: Computer Science and Game Theory (cs.GT).
Pagina del lavoro: https://arxiv.org/abs/2609.40098 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-07T12:48:01.883Z dalla pagina https://arxiv.org/catchup/cs.GT/2026-10-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).