Unverified50% confidenceFactExact time
Different AI providers differ in cache granularity, hit conditions and billing methods; for example, some price cache-write tokens and cache-read tokens separately, and some set a minimum cacheable token length.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/20/2026
First Seen
Valid until: 1/18/2027
Sources
Related Entities
Related Claims
UnverifiedThe cache pricing strategies of mainstream AI providers (such as OpenAI and Anthropic) usually charge some storage fee for long caches but greatly reduce the input cost of repeated requests.73% similarUnverifiedThe aforementioned cache duration applies to using Claude Code under a subscription plan; behavior may differ in scenarios such as API, prepaid credits, and cloud providers.72% similarUnverifiedAnthropic explicitly states that the batch discount and the prompt caching discount can be stacked, but the cache hit rate within batch jobs cannot be guaranteed, because the batch scheduler may spread requests across different time windows and machines.70% similarUnverifiedDifferent models price input and output tokens differently, and some providers have differentiated pricing for scenarios such as cache hits and batch requests.70% similarUnverifiedCache hit rate refers to the proportion, in continuous conversations or repeated requests, in which the model provider caches and reuses context with the same prefix and bills it at a discounted price; in programming agent workflows, the higher the cache hit rate, the less actual token billing and the faster the response.69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1078502API
curl https://kongchang.com/api/v1/knowledge/claims/1078502MCP
get_claim(id=1078502)