Unverified50% confidenceFactExact time
The prompt caching of many providers (such as Anthropic, OpenAI, and Google) uses token sequences as the unit of matching rather than strings, so subtle differences in spaces, line breaks, or encoding can cause cache misses.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/15/2026
First Seen
Valid until: 1/13/2027
Sources
Related Entities
Related Claims
UnverifiedIn Anthropic's API billing system, prompt caching allows a stable prefix to be marked as cached content, and subsequent identical prefixes directly reuse the KV without recomputing attention, with these tokens recorded as "cache reads".74% similarUnverifiedThe prompt caching mechanism of language models caches previously sent messages, eliminating the need to repeatedly reprocess the same content.71% similarUnverifiedPrompt Caching requires the prompt to meet a minimum cacheable length (typically 1024 tokens for Anthropic), and the prefix must be byte-for-byte identical for the cache to hit.71% similarUnverifiedPrompt caching can avoid repeated charges for identical prefixes, because system prompts and retrieved document fragments tend to be highly repetitive across multiple conversation turns.71% similarUnverifiedThe same passage of text may be split into different numbers of tokens under different tokenizers, while API billing and context window limits are both measured in token counts.69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1036604API
curl https://kongchang.com/api/v1/knowledge/claims/1036604MCP
get_claim(id=1036604)