---
title: "Token reduction: glossary: Agent Ready HTML"
description: "Token reduction defined: How many fewer model tokens a page costs as markdown than as HTML. A dated, sourced example follows."
canonical: https://agentreadyhtml.com/glossary/token-reduction/
site: "Agent Ready HTML"
last_updated: 2026-11-04
section: "Glossary"
---

# Token reduction: glossary: Agent Ready HTML

> Token reduction defined: How many fewer model tokens a page costs as markdown than as HTML. A dated, sourced example follows.

Source: https://agentreadyhtml.com/glossary/token-reduction/
Site: Agent Ready HTML
Last reviewed: 2026-11-04

# Token reduction

In short

How many fewer model tokens a page costs as markdown than as HTML. Example: Cloudflare measured 16,180 tokens in HTML against 3,150 in markdown for one post. Related terms: Universal rendering, Subpath llms.txt. Universal rendering: Nuxt term for rendering on the server first and hydrating in the browser.

## Source of the example

The example in the summary above is from [blog.cloudflare.com](https://blog.cloudflare.com/markdown-for-agents/), read 4 November 2026.

## Where it shows up on this site

-   [Method](https://agentreadyhtml.com/method/)

## Neighbouring terms

-   [Universal rendering](https://agentreadyhtml.com/glossary/universal-rendering/): Nuxt term for rendering on the server first and hydrating in the browser.
-   [Subpath llms.txt](https://agentreadyhtml.com/glossary/subpath-llms-txt/): An llms.txt below the root that covers the pages under its path; v2 says the most specific file applies.

## Sources

1.  [blog.cloudflare.com](https://blog.cloudflare.com/markdown-for-agents/) https://blog.cloudflare.com/markdown-for-agents/, read 4 November 2026

Last reviewed 4 November 2026

Edition

Crawl

2026-11-04

Page updated

2026-11-04

Method

How the viewer reads a page, how a file is graded and how a platform is scored: [the method page](https://agentreadyhtml.com/method/).