Unverified50% confidenceFactExact time
Anthropic explicitly states that the batch discount and the prompt caching discount can be stacked, but the cache hit rate within batch jobs cannot be guaranteed, because the batch scheduler may spread requests across different time windows and machines.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/18/2026
First Seen
Valid until: 1/16/2027
Sources
Related Entities
Related Claims
UnverifiedGateway discounts and vendor batch discounts are different levers: gateway discounts apply to synchronous interactive traffic; the 50% batch discount applies only to asynchronous tasks that can wait, and currently can only be obtained directly from the vendor.76% similarUnverifiedDuring peak load periods, some platforms impose inference step limits on non-paying users or downgrade them to models with fewer parameters.74% similarUnverified寄生式应用模式不承载自身计算成本而复用宿主平台算力配额，避免了用量焦虑，但性能天花板受限于宿主订阅的速率限制和配额上限73% similarVerifiedSome service providers have introduced cache-hit pricing, charging at a lower discounted rate when repeated long system prompts hit the cache.71% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1060521API
curl https://kongchang.com/api/v1/knowledge/claims/1060521MCP
get_claim(id=1060521)