Unverified60% confidenceFactExact time
The per-token call cost among mainstream large model vendors shows a continued downward trend.
2
Sources
60%
Confidence
Medium-term (~90 days)
Relevance
9/5/2026
First Seen
Valid until: 12/4/2026
Sources
Related Entities
Related Claims
UnverifiedThe compute cost per unit of inference is declining at a rate of 40% to 60% per year.71% similarUnverifiedThe tiered model routing strategy of 'cheap first, expensive later' cascading typically reduces average cost by an order of magnitude while maintaining output quality.69% similarUnverifiedInference costs have dropped sharply, with the token cost of some models falling by more than 90%.69% similarUnverifiedThe cost of flagship models has decreased by approximately 10x over the past year and a half.69% similarUnverifiedCompared with the baseline, HybridAgent reduces token consumption by 35.5% to 54.7%, improves inference speed by 1.8x to 2.6x, and lowers cost by 2.7x to 3.7x.68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/860838API
curl https://kongchang.com/api/v1/knowledge/claims/860838MCP
get_claim(id=860838)