Unverified50% confidenceFactExact time
In mainstream API pricing structures such as Anthropic's, the unit price of cache-read tokens is only 1/10 to 1/30 of standard input tokens.
1
Sources
50%
Confidence
Long-term
Relevance
9/29/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedPrompt Cache refers to a provider caching already-processed identical prefix tokens, where the price of cache-hit tokens is typically only 10%–50% of the normal price.75% similarUnverifiedBoth Anthropic's Claude API and OpenAI's API natively support prompt caching, with input token prices on cache hits typically only 10%–25% of the normal price.74% similarUnverifiedPrompt Caching在提示词前缀完全相同且超过约1024 token阈值时命中，缓存token通常按原价的25%甚至更低计费74% similarVerifiedOpenAI's API billing distinguishes between input tokens and output tokens, with output tokens typically priced higher.74% similarUnverifiedThe 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% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/957969API
curl https://kongchang.com/api/v1/knowledge/claims/957969MCP
get_claim(id=957969)