Cached Input
A mechanism in which model providers cache the intermediate state of long text that appears repeatedly, so that subsequent calls are billed only at the cache-hit price, typically at a substantial discount. This is significant for multi-agent and RAG scenarios.
Timeline (last 90 days)
For agent or chat products that resend long system prompts and history on every turn, cache prices may have a greater impact on the bill than input prices.
In Agent workflows, the proportion of repeated context in total input is extremely high, so the decline in caching costs is far more significant for Agent developers than for ordinary users.
Cached input refers to pre-storing the same context on the server side so that subsequent requests can reuse the cache without repeated computation, and is billed at a lower price.
All Facts (3)
For agent or chat products that resend long system prompts and history on every turn, cache prices may have a greater impact on the bill than input prices.
50%UnverifiedIn Agent workflows, the proportion of repeated context in total input is extremely high, so the decline in caching costs is far more significant for Agent developers than for ordinary users.
50%UnverifiedCached input refers to pre-storing the same context on the server side so that subsequent requests can reuse the cache without repeated computation, and is billed at a lower price.
50%