The page grew, the agent token count did not
2026-07-04
A July measurement compared the token counts of the homepage's HTML and Markdown representations. The result describes that page and measurement date.
In late June this site published a post on what an agent pays to read a page, and the measurement in it said the homepage as markdown cost roughly a third of the HTML form. The most recent scan, as of 4 July 2026, reports the same homepage at 10,320 tokens as HTML and 1,723 as markdown. That is a sixth of the cost, an 83% saving, and nothing in the meantime was done to improve the number. The post tracks what each form costs to read in tokens, not what any agent's operator actually paid.
Where the weight came from
Since that post went out the site has gained six blog posts before this one, two tool pages, a feed, a share image for every page and related links at the end of every post. None of that was content negotiation work. It was ordinary growth, and it landed where growth always lands, on the human-facing page. Between the 1 July and 4 July scans alone the HTML form of the homepage went from 9,560 tokens to 10,320, about 8% heavier in three days. The markdown form went from 1,750 to 1,723. It got slightly smaller.
Two surfaces, two growth rates
The HTML form of a page carries everything a site accumulates: navigation, styling, social metadata, structured data and links to whatever shipped last week. Each of those earns its place for a human reader or a search engine. The markdown form carries the words and the links and nothing else, so it grows only when the actual content grows. Serve one surface to everyone and every agent pays for the whole accumulation on every visit. Serve both forms from the same URL and the costs come apart on their own, the human page free to get richer while the agent page stays at the price of the text.
Read the number yourself
The token split is measured, not typed in by hand. It comes from scanning both forms of the page, and this site logs the pair after every deploy. The June post carried the measurement of its day and this one carries the measurement of 4 July. If the pattern holds, a later post will quote a wider gap still, because the human surface keeps accumulating and the text does not.
For an audit that measures what agents pay to read your site, contact info@turva.dev.
Corrected 2026-09-28. The heading called the token count an agent bill. The post measures what each form costs to read in tokens, not a paid invoice, and the body now says so.
Corrected 2026-09-28. The heading, and the same words used elsewhere on the site for this post's title, still called the token count an agent bill after the body already said it was not. They now use the same words as the body, agent token count. A sentence also said the token split is not self-reported: it now says it is measured, not typed in by hand.
Corrected 2026-09-29. The opening still explained the word bill in the title after the title had dropped it. That explanation is gone, and the sentence says what the post measures.
Corrected 2026-10-02. One sentence said the site had gained seven blog posts since the earlier post. The blog index lists six, so it now says: "Since that post went out the site has gained six blog posts before this one."