Implicit Caching
A cost optimization mechanism of the Gemini API that automatically identifies and reuses the KV cache of repeated input prefixes in consecutive requests, without explicitly creating a cache object, and is transparent to developers.
Timeline (last 90 days)
The TTL of implicit caching (automatic hits) tends to be shorter, and no exact value is publicly committed to.
Implicit caching is a cost optimization mechanism of the Gemini API: when the input prefixes of consecutive requests are highly repetitive, the system automatically identifies and reuses the already-computed KV cache, billing only the new portion at the standard rate and settling the reused portion at a discounted price.
All Facts (2)
The TTL of implicit caching (automatic hits) tends to be shorter, and no exact value is publicly committed to.
50%UnverifiedImplicit caching is a cost optimization mechanism of the Gemini API: when the input prefixes of consecutive requests are highly repetitive, the system automatically identifies and reuses the already-computed KV cache, billing only the new portion at the standard rate and settling the reused portion at a discounted price.
50%