Expired50% confidenceFactExact time
GPT-5.6 supports explicit cache breakpoints, with cache hits billed at a 10% rate.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/8/2026
First Seen
This claim has expired. It is kept for the record and no longer describes the current state.
Valid until: 10/6/2026(expired)
Sources
GPT-5.6三版本解析：OpenAI首次让政府审核AI模型
bilibili五里墩茶社6/28/2026
Related Claims
UnverifiedGPT-5.6 supports explicit cache breakpoints, with cache reads enjoying a 90% discount.85% similarUnverifiedIn the official documentation for GPT-5.6, 272k is marked as the 'doubled context' threshold: beyond this threshold, the input portion is billed at 2x, the output portion at 1.5x, and cache read costs increase proportionally.80% 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.79% similarUnverifiedIt is recommended to keep the GPT-5.6 context window within 272k as much as possible in order to balance cost and quality.78% 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.76% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/236063API
curl https://kongchang.com/api/v1/knowledge/claims/236063MCP
get_claim(id=236063)