Unverified50% confidenceFactExact time
From GPT-3.5 to GPT-4o mini, the token cost for handling the same tasks has dropped by more than 90%.
1
Sources
50%
Confidence
Long-term
Relevance
7/22/2026
First Seen
Sources
Related Claims
UnverifiedThe cost of calling GPT-4 Turbo decreased by approximately 80% compared to the original GPT-4.84% similarUnverifiedThe release of GPT-3.5-turbo in March 2023 reduced API call costs by approximately 90%.83% similarVerifiedThe cost of calling GPT-4o is approximately 15–20 times that of GPT-4o-mini.82% similarUnverified斯坦福大学开源的RouteLLM系统实测显示，在保持GPT-4级别输出质量的前提下可将成本降低40%-70%81% similarUnverifiedSome wrapper services use lower-spec models to reduce costs, such as passing off GPT-3.5 as GPT-4.80% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/590265API
curl https://kongchang.com/api/v1/knowledge/claims/590265MCP
get_claim(id=590265)