Expired70% confidenceFactTime unknown
In API providers' cache hit mechanisms, the cost of cached tokens is typically only 1/10 of the initial computation cost.
1
Sources
70%
Confidence
Medium-term (~90 days)
Relevance
6/2/2026
First Seen
Valid until: 8/31/2026(expired)
Sources
Related Entities
Related Claims
UnverifiedThe 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.75% similarUnverifiedThird-party API relay platforms (such as Kongcai) use a multiplier billing mechanism, where a 0.1x multiplier means the call cost is approximately one-tenth of the official pricing71% similarUnverifiedBoth Anthropic's Claude API and OpenAI's API natively support prompt caching, with input token prices on cache hits typically only 10%–25% of the normal price.71% similarVerifiedIn API billing, the unit price of output tokens is generally higher than that of input tokens, because the generation process requires autoregressive inference token by token70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/37468API
curl https://kongchang.com/api/v1/knowledge/claims/37468MCP
get_claim(id=37468)