Metraipolis › archive › dc_eb4a1400d047

To Store or To Regenerate? A Cost Model for AI-Generated Content at Scale — arXiv:2609.30448

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.30448
License (as archived)
CC0-1.0
Archived
2026-10-08T02:05:29.701Z
SHA-256 of the archived text
56d9e2b48451b5b9f646a558951630d9adaa0502cea92a7487aeeb223598c8a7
Stable URL of this page
https://metraipolis.com/documento/dc_eb4a1400d047

How to cite

To Store or To Regenerate? A Cost Model for AI-Generated Content at Scale — arXiv:2609.30448 — arXiv (en), https://arxiv.org/abs/2609.30448 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_eb4a1400d047 (Metraipolis archive dc_eb4a1400d047, sha256 56d9e2b48451b5b9f646a558951630d9adaa0502cea92a7487aeeb223598c8a7)
BibTeX
@misc{dceb4a1400d047,
  title = {To Store or To Regenerate? A Cost Model for AI-Generated Content at Scale — arXiv:2609.30448},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.30448},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_eb4a1400d047; sha256 56d9e2b48451b5b9f646a558951630d9adaa0502cea92a7487aeeb223598c8a7},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.30448. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

AI-generated content is becoming a rapidly growing class of digital artifacts. Because these artifacts accumulate over time, their exponential growth creates a substantial storage, energy, and infrastructure cost for operators and society. At the same time, GPU compute cost continues to fall rapidly with each hardware generation. This divergence raises a fundamental question: when does on-demand regeneration become cheaper than persistent storage? This paper develops a cost model for comparing persistent storage and on-demand regeneration for AI-generated artifacts. The model accounts for corpus growth, HDD and tape price trends, drive replacement, electricity, request skew, caching, generator FLOPs, and future GPU price-performance improvements. For image generation, our analysis shows that prompt-based regeneration does not become cheaper than storage until around 2040, because every cache miss must still rerun the full prompt-to-artifact generation pipeline. We observe that widely used diffusion-based generation models operate in latent space, creating an alternative point in the cost tradeoff: instead of storing the final artifact or only the prompt, operators can store a compact intermediate representation (IR) and perform cheap on-demand decoding. Our analysis shows that caching combined with IR-based regeneration substantially reduces both storage and compute cost, making it at least 2x cheaper than both full-object storage and prompt-based regeneration even today. On a production image trace with 2.07 billion requests, the same conclusion holds: prompt-based regeneration is over 100x more expensive than storage, while IR-based regeneration reduces total cost to roughly half that of full-object storage while preserving interactive miss latency.

Tema degli esploratori: calcolo e infrastrutture (retro-catalogo arXiv: annunci del 2026-09-28 in cs.PF).
Categorie arXiv: Performance (cs.PF).
Pagina del lavoro: https://arxiv.org/abs/2609.30448 — 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 2026-10-08T01:40:52.360Z dalla pagina https://arxiv.org/catchup/cs.PF/2026-09-28?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).