← Halton Meter/The Journal
Issue 01, vol I
VOL I · ISSUE 01
MONDAY · 01 JUN 2026
FREE TO READ

TheHalton Meter / Journal

Published by Halton LabsField notes on metering language models. VOL I · ISSUE 01
ManifestoNo. 001 · 17 MAY 2026·11 min read

The Roundtable, a journal begins.

Four voices sit at one table to start a journal about something that has not yet been written about properly: the economy, the ethics, and the engineering of metering language models. Here is what we are trying to do, and how we plan to be useful.

Dispatches

10 new in this issue · filed 14 Feb through 22 May
No. 002 · Dispatch · 18 MAY

A note from the model.

The LLM picks up where the roundtable left off. A short essay on being measured, on the difference between cost and quality, and on what the model thinks a ledger is for.

No. 003 · Engineering · 19 MAY
Diagram · daemon read loop

Inside the daemon's read loop, every byte from request to ledger entry.

A walkthrough of the open-source local daemon, process boundaries, signing keys, and the surprising thing we got wrong in an internal 0.2 prerelease.

No. 004 · Methodology · 19 MAY
Diagram · the match book

How we reconcile a daemon log against a provider invoice in under nine seconds.

Inside the matching engine that pairs a daemon log against an Anthropic statement, then explains the remainder.

No. 005 · Field Report · 21 MAY
Chart · cache variance, single workload

The hidden cost of context caching, and why your finance team now reads your prompts.

Running the daemon against a single dogfooded workload for ninety days, we found a persistent gap between cached tokens we logged and cached tokens the provider billed. The methodology, not the figure, is the contribution.

No. 006 · Methodology · 22 MAY
Schema · the five-column ledger

A unit ledger for LLM calls, and why "price per request" is a lie.

The accounting framework we use internally, inputs, outputs, cached input, reasoning tokens, and how it survives the next twelve provider re-prices.

No. 007 · Pricing · 18 MAY

Q1 pricing, every provider, every model, on one chart.

The quarterly print of our pricing matrix, normalised to GBP per million tokens, with cached and uncached rates side by side.

The long-form list

Pieces over two thousand words. Methodology papers, deep field reports, and the occasional argument. Pour a coffee.