Unverified50% confidenceFactExact time
GPT-5.6 中官方文档标注 272k 为'翻倍上下文'分界线，超过该阈值后输入部分按2倍计费，输出部分按1.5倍计费，缓存读取成本同步上涨
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/19/2026
First Seen
Valid until: 10/17/2026
Sources
Related Claims
UnverifiedGPT-5.6 supports explicit cache breakpoints, with cache hits billed at a 10% rate.80% similarUnverifiedGPT-5.6的缓存机制成本略有上升76% similarPartially VerifiedGPT-5.6 has improved the prompt caching mechanism by adding explicit cache breakpoints, with a minimum cache retention of 30 minutes and output speeds of up to hundreds of tokens per second.74% similarUnverifiedCompared to GPT-5.5, GPT-5.6 consumes approximately one-third of the Tokens per PR, and the median completion time is nearly halved.74% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/558699API
curl https://kongchang.com/api/v1/knowledge/claims/558699MCP
get_claim(id=558699)