Unverified50% confidenceFactExact time
Context caching is a feature provided by some model vendors (such as Anthropic's Claude and Google's Gemini) that allows frequently occurring long text prefixes to be cached on the server side to reduce the cost of subsequent calls.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/8/2026
First Seen
Valid until: 1/6/2027
Sources
Related Entities
Related Claims
UnverifiedGoogle的Gemini提供显式的缓存内容API，开发者可主动指定缓存内容，并按存储时间计费73% similarUnverifiedMainstream products such as Google Gemini and Claude also have similar cross-session context retention mechanisms.71% similarUnverified在Google Gemini API的响应结构中，finishReason字段用于指示模型为何停止生成内容69% similarUnverifiedThe application uses the Gemini API (powered by the Gemini Flash model) as the backend, evaluating dates, merchants, and amounts through a server-side classification interface and mapping them to a standard chart of accounts, with support for syncing to QuickBooks.66% similarUnverifiedGemini 免费层的数据可能被 Google 用于模型改进，涉及商业机密的代码建议使用付费层或本地模型65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/990013API
curl https://kongchang.com/api/v1/knowledge/claims/990013MCP
get_claim(id=990013)