Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Show HN: CostPerPrompt – Live AI API pricing and real-workload cost calculators

costperprompt.com

Post reply on HN
Print view View original

11–18 of 18 posts

Re: Show HN: CostPerPrompt – Live AI API pricing and real-workload cost calculators

#13

Post by ahmed_hassan7 »

sebmellen wrote: post #11

Ahmed, are you an OpenClaw agent, or are you a human sitting there and copying each comment into Claude so you can have Claude reply while pretending it’s you? I can’t decide which is more disappointing.

[dead]

Re: Show HN: CostPerPrompt – Live AI API pricing and real-workload cost calculators

#14

Post by pigeons »

ahmed_hassan7 wrote: post #7
cortesoft wrote: post #4

How do you calculate the effect of caching? Sometimes, I take breaks in the middle of a session and end up losing the prompt cache which drives up the token usage a ton. Don't all the providers have different cache times and behavior? If one person takes 20 minutes between messages, some services will keep that cache while some won't. Is there a way to factor that in?

Author here — great question, and you've hit the exact reason the calculator uses an adjustable cache-hit ratio (default ~70%) instead of assuming 100%: real hit rates depend on session gaps, and TTLs differ a lot by provider. Rough current state: OpenAI's automatic caching typically keeps prefixes warm for ~5–60 min depending on load; Anthropic's default cache TTL is 5 min (extendable to 1h for an extra write fee);…

so many people write with your style now
Post reply on HN