Unverified50% confidenceFactExact time
全栈优化的叠加效应使得过去18个月内每token的推理成本下降了约10倍
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
8/25/2026
First Seen
Valid until: 11/23/2026
Sources
Related Claims
UnverifiedAI inference prices, measured per unit of compute, have dropped approximately 10-fold over the past two years, a phenomenon the industry calls the AI inference price spiral.75% similarUnverifiedA new MIT paper shows that pruning techniques can shrink a neural network by 90%, directly reducing inference costs by 10x73% similarUnverifiedThe compute cost per unit of inference is declining at a rate of 40% to 60% per year.71% similarUnverifiedInference costs have dropped sharply, with the token cost of some models falling by more than 90%.70% similarUnverifiedModel distillation technology can reduce inference costs by 5–10 times.70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/799593API
curl https://kongchang.com/api/v1/knowledge/claims/799593MCP
get_claim(id=799593)