Unverified50% confidenceFactExact time
Implicit caching is enabled by default for prompts above 4,096 tokens, with a 95% discount on cached input.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/14/2026
First Seen
Valid until: 1/12/2027
Sources
Related Entities
Related Claims
UnverifiedTokenRouter does not store prompt and response bodies by default, and request logs record only token counts, cost, and latency; captured bodies are compressed and encrypted before leaving the API process, and capture never fails, slows down, or changes a request.68% similarUnverifiedOmega's Usage records three categories—input tokens, output tokens, and cache read tokens—rather than a vague total token count.66% similarUnverifiedReasoning tokens are billed as output tokens but are generally invisible to users or only partially visible.64% similarUnverifiedToken leaks often come with no obvious indication, making them difficult for users to detect; it is recommended to immediately log out of all device sessions after completing operations to invalidate old tokens.62% similarUnverifiedImmutable storage or cryptographic signatures should be applied to critical operation logs to ensure they cannot be silently modified after the fact.62% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1023075API
curl https://kongchang.com/api/v1/knowledge/claims/1023075MCP
get_claim(id=1023075)