Unverified50% confidenceFactExact time
Prompt Cache refers to a provider caching already-processed identical prefix tokens, where the price of cache-hit tokens is typically only 10%–50% of the normal price.
1
Sources
50%
Confidence
Long-term
Relevance
9/18/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedPrompt Caching在提示词前缀完全相同且超过约1024 token阈值时命中，缓存token通常按原价的25%甚至更低计费80% similarVerifiedThe Prompt Caching mechanism can reuse the KV Cache of identical prefix contexts, typically reducing input token costs by 50%–90%.77% similarUnverifiedIn cache hit scenarios, hit tokens are typically charged at 1/10 of the original price or even lower76% similarVerifiedIn DeepSeek's caching mechanism (Context Caching), cache-hit tokens are typically billed at one-tenth of the original price or even lower.76% similarUnverifiedCached input tokens typically enjoy a discount of 25%–50% off the original price, as there is no need to recompute embeddings and attention weights—only the precomputed KV vectors need to be loaded from cache.74% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/931959API
curl https://kongchang.com/api/v1/knowledge/claims/931959MCP
get_claim(id=931959)