Analysis 01
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.
Tag Independent editorial
Tag / anthropic
16 posts tagged "anthropic".
16
2
16min avg
About
Every post tagged "anthropic" in the journal -- page 2 of 2.
§ Filter by category
Category
Showing 4 of 16 posts — page 2 of 2
Analysis 02
The reasoning dial nobody touches: why your thinking-model bill is so high
In 2026 the biggest lever on your LLM bill isn't which model. It's how hard the model thinks: reasoning tokens bill as output, and most models think by default.
Tools Howto 03
Caveman mode for Claude Code: the math behind the 65% headline
Caveman mode strips filler from Claude's output. The 65% headline is real for output tokens. Here's what it actually saves on your monthly bill.
Analysis 04
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.