Unverified50% confidenceFactExact time
Prompt caching usually has an expiration period, requires rewriting after content changes, and the cache discount applies only to the input side, while output tokens are still billed at the standard rate.
1
Sources
50%
Confidence
Long-term
Relevance
10/14/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedCached 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.77% similarUnverifiedWhen a streaming response is interrupted midway, the portion of output tokens already generated is still billed, even though the client may not have received the complete result.77% similarUnverifiedCache hit discounts target repeated system prompts or context prefixes: if this content has already been cached, the provider does not need to recompute it and can heavily discount the cost of the hit portion, commonly to 10% to 25% of the original price.76% 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76% similarUnverifiedReasoning content is often billed the same as regular text in terms of token counting, so retaining reasoning increases the number of tokens carried in requests and affects call costs.75% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1031485API
curl https://kongchang.com/api/v1/knowledge/claims/1031485MCP
get_claim(id=1031485)