Unverified70% confidenceFactExact time
Almost all LLM APIs typically charge only 10% of the full price for cache-hit tokens on the second and subsequent times identical content is seen.
2
Sources
70%
Confidence
Medium-term (~90 days)
Relevance
8/12/2026
First Seen
Valid until: 11/10/2026
Sources
Related Claims
UnverifiedPrompt caching charges only one-tenth the price for input tokens that have already been processed, making it one of the highest-leverage cost optimizations on modern LLM APIs.71% similarUnverifiedThe current pricing systems of mainstream LLM APIs are usually composed of several dimensions: per-token billing (distinguishing input/output), per-call billing, tiered pricing, and cache-hit discounts.69% similarUnverifiedMany API service providers offer substantial discounts for cache-hit tokens, typically 1/4 to 1/10 of the regular price.67% similarUnverifiedMainstream LLM APIs are typically billed based on actually generated output tokens, not based on tokens successfully received by the client.64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/736877API
curl https://kongchang.com/api/v1/knowledge/claims/736877MCP
get_claim(id=736877)