Unverified50% confidenceFactExact time
Mainstream hosted LLM providers bill cached prompt prefixes at a discounted rate, provided that the fixed part is placed first and kept byte-identical.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/12/2026
First Seen
Valid until: 1/10/2027
Sources
Related Entities
Related Claims
UnverifiedMainstream model providers (including Anthropic, DeepSeek, and others) offer a prompt caching mechanism for repeated prompt prefixes, charging a lower token price for cache hits (typically 10%–50% of the original price)72% similarUnverifiedCache hit discounts target repeated system prompts or context prefixes: if this content has already been cached, the provider does not need to recompute it and can heavily discount the cost of the hit portion, commonly to 10% to 25% of the original price.71% similarUnverifiedVendors commonly adopt a tiered subscription plus usage quota model to control inference costs.68% similarUnverifiedThe fixed subscription plus quota cap pricing model is logically similar to cloud computing's Reserved Instances: users commit to consumption in advance in exchange for a lower unit price.67% similarUnverifiedVendors commonly adopt a tiered subscription plus usage quota model to control costs, including free tiers, paid subscription tiers, and pay-as-you-go API billing.66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1006120API
curl https://kongchang.com/api/v1/knowledge/claims/1006120MCP
get_claim(id=1006120)