cost analysis

5 articles

AI
Prompt Caching, End to End · Part 4

Prompt Caching (Part 4): AWS Documents 4,096 — I Measured 1,024

AWS gives Claude Sonnet 4.5 a 4,096-token minimum cacheable prefix. Bisecting on Bedrock put the real threshold at 1,024. Three control models matched their docs; only this row was off.

AI
Prompt Caching, End to End · Part 1

Prompt Caching (Part 1): What Is Actually Cached

Prompt caching saves the server's prefill compute, not the cost of re-sending tokens. Where the KV cache comes from, why a prefix must match token for token, and why caching can cost more.

AI
Prompt Caching, End to End · Part 2

Prompt Caching (Part 2): Five Vendors, Three Clouds, One Bill

AWS documents a 4,096-token minimum for Sonnet 4.5 on Bedrock; I measured 1,024. Multipliers, TTL tiers and cross-region behaviour for five vendors — measured kept apart from documented.

AI
Prompt Caching, End to End · Part 3

Prompt Caching (Part 3): It Is On and Not Hitting — Now What

Cache invalidation almost never errors: inference succeeds, the logs are clean, only the bill grows. Four culprits by frequency, plus a cross-vendor hit-rate self-check you can run today.

AI

Seedance 2.5 Hands-On: 725 Credits Buy 27 Seconds, and the CLI Costs Extra

A ¥69/month membership buys 725 credits — enough for 27 seconds of finished video, about ¥2.5 per second. The Dreamina CLI needs the ¥998/month premium tier, which is where my agent-driven pipeline stopped. Three blockers, one cost calculation done on what I actually paid, and four things wrong with the subtitles.