Unverified50% confidenceFactExact time
In GPT-5.6 and later, OpenAI charges 1.25× for cache writes and 0.1× the uncached input rate for cache reads, with a minimum cacheable prefix of 1,024 tokens.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/12/2026
First Seen
Valid until: 1/10/2027
Sources
Related Entities
Related Claims
UnverifiedOpenAI's cache hit tokens are typically billed at a 50% discount.74% similarUnverifiedOpenAI's official example shows that one write plus nine full reads totals 2.15× the prefix input price, compared to 10× without caching.72% similarVerifiedThe cache read mechanism retains the KV cache for recurring long prompt prefixes, charging at an extremely low rate upon a cache hit; the leaked cache read price for Opus 5.5 is approximately 1/20 of the input price.72% similarUnverifiedA Prompt Caching cache hit read costs only 0.1 times the base input price, while the initial write cost is 2 times the regular input price.69% similarUnverifiedIn agentic coding work, the proportion of cache reads in total cost is under 5% in Fable, close to 20% in Opus, and potentially over 50% in Sonnet 5.5.69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1002838API
curl https://kongchang.com/api/v1/knowledge/claims/1002838MCP
get_claim(id=1002838)