Unverified50% confidenceFactExact time
Cached input tokens enjoy significant discounts because they do not require recalculation of embeddings and attention weights.
1
Sources
50%
Confidence
Long-term
Relevance
9/7/2026
First Seen
Sources
Related Entities
Related Claims
Partially VerifiedDeepSeek GUI's caching mechanism can reduce token consumption by 60%–90%.71% similarVerifiedIn DeepSeek's caching mechanism (Context Caching), cache-hit tokens are typically billed at one-tenth of the original price or even lower.67% similarUnverifiedThe Prompt Caching mechanism can typically save 50%–90% of input costs.67% similarUnverifiedCaching mechanisms can reduce API costs by 70–90% for use cases that frequently reference large codebases.65% 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.64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/870391API
curl https://kongchang.com/api/v1/knowledge/claims/870391MCP
get_claim(id=870391)