Unverified50% confidenceFactExact time
Running '/effort high' does not break the prompt cache, and the next question still reads about 19,000 tokens from the cache; however, this setting is saved as the default for all future sessions.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
11/8/2026
First Seen
Valid until: 2/6/2027
Sources
Measured: Claude Code Built Games Nine Times — Which Token Tips Actually Save Money
youtubeProof Run11/7/2026
Related Entities
Related Claims
UnverifiedEach retry resends the complete prompt input tokens and is billed in full; a request with 4,000 input tokens retried 3 times will consume 16,000 tokens.69% similarUnverifiedThe token counting endpoint is free but rate-limited: the Start tier allows 5,000 requests per minute, which do not count against the message creation quota.68% similarUnverifiedA calculation example: asking 20 questions about a 50,000-token document requires about 1 million input tokens without prompt caching, and about 157,000 with caching, reducing input cost by about 84%, with faster time to first token as well.67% similarUnverifiedFor one-off inference where inputs never repeat or for batches of unique documents, because of the cache-write premium, enabling caching costs more with zero benefit, so it should simply be skipped.66% similarUnverifiedPrompt Caching is triggered when the prompt prefix is completely identical and exceeds a threshold of approximately 1,024 tokens, and cached tokens are typically billed at 25% or even less of the original price.66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1147929API
curl https://kongchang.com/api/v1/knowledge/claims/1147929MCP
get_claim(id=1147929)