Unverified50% confidenceTradeoffExact time
In agentic scenarios where system prompts run to thousands of tokens, if more than 90% of requests hit the cache, the effective input cost per request may be only 5%–10% of the listed price.
1
Sources
50%
Confidence
Long-term
Relevance
9/26/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedIn long-running agentic conversation scenarios, more than 90% of input tokens are billed at the cache price.77% similarUnverifiedUnder the cache-hit billing mechanism, the portion that hits the cache is billed at a lower price; in Agent scenarios the cache hit rate is often as high as 90% or above, and the cache price has a far greater impact on the actual costs of heavy Agent users than the nominal input unit price.74% similarUnverifiedThe API cache hit mechanism allows input tokens that have already been sent to enjoy discounted pricing on repeated calls, typically at 10%–50% of the original price.71% similarUnverifiedInput tokens now account for more than 90% of total non-cached tokens, and the cost share of input context has risen from 47.5% to nearly 70%.70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/951860API
curl https://kongchang.com/api/v1/knowledge/claims/951860MCP
get_claim(id=951860)