Tools Howto
A 429 is free. The ninth retry is not.
A 429 bills you nothing - the request never reaches the model. The cost arrives when your backoff outlives the cache TTL and the cold retry burns 101x the limit.
Journal Independent editorial
The journal.
20 posts across analysis, opinion, how-to, research, and roundups.
20
2
16min avg
About
Independent analysis, opinion, and how-to coverage of LLM tooling -- written for engineers who pay the bill. No vendor talking points, no benchmarks lifted from press kits. Every model price comes from the vendor's own page, verified the week of publication; every cost calculation shows its math. The blog sits next to the price desk and the comparisons -- prose covers the questions a table cannot answer (when does a 90% cache discount stop mattering? which workload class breaks GPT vs Claude pricing parity?). Cornerstone analysis ships first; opinion, tools how-to, research summaries, and roundups will join as the catalogue grows. Read for the math, stay for the disagreements.
§ Filter by category
Category
Editor's pick
1 of 20 Showing 11 of 20 posts — page 1 of 2
Tools Howto 02
input_tokens means three different things. Your cost function knows one of them.
Anthropic's input_tokens excludes cached tokens, OpenAI's includes them. Port a cost function between the two and a $0.082 request bills $0.378. Fields, traps, code.
Analysis 03
The list price is not the price your agent pays
The model 5.7% cheaper on the price tag billed an agent session 4.4x higher. The cached-read rate decides an agent bill, and it runs from 2% to 25% of input.
Analysis 04
Running many agents at once: the tax is linear, the rebate is quadratic
Every extra agent pays for its own cold prefix. But re-reading history grows with the square of turns, so splitting one job across three agents ran 17% cheaper.
Tools Howto 05
The 20x in Claude Code caching is real — it's a penalty, not a discount
A cache miss costs exactly 20x the warm read of the same history. What that does to your plan limits, which settings change it, and the number nobody can compute.
Tools Howto 06
The Batch API discount isn't 50% -- and it isn't always a discount
Batch halves token rates at OpenAI, Anthropic and Google -- but takes 20% at SpaceXAI and nothing on its flagship. When batch beats a warm cache, and when it costs more.
Tools Howto 07
How to actually get prompt cache hits (and why yours are missing)
Prompt caching fails silently -- no error, no warning, just a full-price bill. The floors, the breakpoint rules, and everything that quietly invalidates a cache.
Analysis 08
Routing by task complexity: what the 2026 evidence actually shows
Ten routers launched on HN in five weeks. The peer-reviewed 2026 benchmarks say they barely beat a baseline. The arithmetic that decides it, on verified rates.
Tools Howto 09
The context engineering playbook: which lever, in what order, and what each is worth
Five levers, one deployment order: which context feature to reach for by symptom, what each does to your cache and your bill, and one config that runs them all.
Analysis 10
Token savings are not dollar savings: the conversion math
Cutting 63% of an agent's tokens moved its bill 9%. Cutting 1.2% moved it 15%. The arithmetic that converts token reductions into dollars, on verified 2026 rates.
Tools Howto 11
The MCP context tax: how to stop paying for tools your agent never calls
Five MCP servers burn ~55k tokens before you ask anything. Tool search and programmatic tool calling (both now GA) cut that 85%+ — with one caveat that bites.
Tools Howto 12
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.