Analysis
How prompt caching actually changes the LLM cost math
Anthropic charges 10% of input for cache reads, with a 1.25x write fee. OpenAI auto-caches above 1024 tokens. The math changes which LLM is cheapest -- here is when.
Tag Independent editorial
Tag / prompt caching
4 posts tagged "prompt-caching".
4
2
13min avg
About
Every post tagged "prompt caching" in the journal. Tag archives are auto-generated from post frontmatter -- one entry per unique tag across non-draft posts. Currently 4 posts share this tag. Use the category filter above to scope by editorial type.
§ Filter by category
Category
Editor's pick
1 of 4 Showing 3 of 4 posts — page 1 of 1
Tools Howto 02
Compaction: when to summarize an agent's history — and when it backfires
Anthropic's compaction API summarizes an agent's history when it hits a token threshold. How it works, the billing pass you don't see, and when it backfires.
Tools Howto 03
Context editing: cut agent token bills ~84% by clearing stale tool results
Anthropic's context editing clears stale tool results from an agent's window, cutting token use up to 84%. How it works, the config, and the prompt-cache catch.
Analysis 04
Hidden LLM API costs nobody quotes (2026)
The $/M input/output sticker hides cache-write premiums, a tokenizer tax, context surcharges, invisible reasoning tokens, and more. Ten verified costs, with proofs.