Unverified60% confidenceFactExact time
OpenAI launched the Prompt Caching feature in 2024; when the prompt prefix is completely identical and exceeds the 1,024-token threshold, the KV Cache is reused, and the cached portion is typically billed at 25% of the original price or even lower.
2
Sources
60%
Confidence
Long-term
Relevance
7/18/2026
First Seen
Sources
Related Claims
UnverifiedPrompt 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79% similarUnverifiedOpenAI provides a Prompt Caching mechanism for models such as Codex, which allows reuse of previously computed KV cache when the prefix token sequence of a request is identical to a prior one, reducing the billing price for that portion (typically 50% or even lower than the normal price).78% similarVerifiedCached input tokens are a discount mechanism offered by providers such as OpenAI for large repeated prefixes (such as system prompts, long documents, and few-shot examples); input tokens that hit the cache are billed at a lower rate, usually only about one-tenth of the standard input price.75% similarUnverifiedOpenAI reports cached input tokens in usage.prompt_tokens_details.cached_tokens, and the billing rate is lower; ignoring this causes costs to be overestimated.72% similarUnverifiedPrompt caching allows vendors to cache the same repeated prefix in an Agent loop, with subsequent calls billed at the cache read price, in this example $0.20 versus $4 for input, 20 times cheaper.72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/552250API
curl https://kongchang.com/api/v1/knowledge/claims/552250MCP
get_claim(id=552250)