Unverified50% confidenceFactExact time
Official data shows that the 1017 version reduces costs by 76% to 91%.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
10/22/2026
First Seen
Valid until: 11/5/2026
Sources
Related Entities
Related Claims
UnverifiedAccording to a cross-vendor empirical comparison, reusing a 100,000-token prefix can reduce costs by 71% to 93%.77% similarUnverifiedAnthropic officially states that about 90% of Haiku 4.5 requests are below 100,000 tokens, and that average operating cost is about 75% lower.63% similarUnverifiedIn 2024, the price per million input tokens for large model APIs fell approximately 90% compared to 2023, dropping from approximately $30 to $2–3.62% similarUnverifiedThe official cost comparison chart shows that the new model's highest point costs a bit over 2 yuan (at the 77% position), while OPUS-5 is close to 100 yuan (around 70%).62% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1086989API
curl https://kongchang.com/api/v1/knowledge/claims/1086989MCP
get_claim(id=1086989)