Expired60% confidenceFactExact time
GPT-5.6 supports explicit cache breakpoints, with cache reads enjoying a 90% discount.
2
Sources
60%
Confidence
Medium-term (~90 days)
Relevance
7/8/2026
First Seen
Valid until: 10/6/2026(expired)
Sources
GPT-5.6编程基准91.9%：三档模型选择与Ultra模式避坑指南
bilibili费曼学AI6/28/2026
Related Claims
UnverifiedGPT-5.6 supports explicit cache breakpoints, with cache hits billed at a 10% rate.85% 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.75% similarUnverifiedFrom GPT-3.5 to GPT-4o mini, the token cost for handling the same tasks has dropped by more than 90%.72% 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.72% similarUnverifiedGPT-5.6 更新的核心是性价比，在保持或提升性能的同时压低推理成本与响应时间72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/230623API
curl https://kongchang.com/api/v1/knowledge/claims/230623MCP
get_claim(id=230623)