Measurements

Why this site exists makes a claim about cost. This page is the evidence, measured on live pages of both sites so anyone can repeat it and disagree with the result.

What one page costs an agent

A token is how a language model measures text — roughly three or four characters — and it is what the model pays for, in money and in the limited space it has to think in. A model with a 200,000-token working memory can hold two of our documentation pages as the live site serves them, or about seventy of the same pages as this site serves them.

Content kept is the guard against the obvious objection — that a page could be made cheap simply by deleting things. Every page here carries more than the original, so the savings come from dropping markup, not substance.

What each site offers an agent

Every row below was probed against both live sites.

Gaps on the current documentation

1. No Markdown representation. llms.txt points an agent at pages it can only then read as full HTML. Discovery without cheap retrieval.
2. No llms-full.txt. Bulk ingestion means crawling every page at full HTML cost.
3. /robots.txt returns 404. Crawlers get no directives at all, so there is no way to steer them away from superseded pages.
4. No way to mark a page superseded. Legacy integration paths read to an agent exactly like current ones, so a coding assistant can confidently recommend an approach we no longer support.
5. Hydration overhead. Up to half of each page is a duplicate copy of its own content in JSON.

Gaps on this site

Stated with the same directness, because a measurements page that only flatters its author is worthless.

Two remain, and both live in the web server rather than in this repository — the deploy is an rsync of static files, so nothing here can set a header.

1. Markdown is served as application/octet-stream. It should be text/markdown; charset=utf-8. Browsers download the file instead of showing it, and content-type-sensitive agents may skip it. The fix is one line in the nginx config on the host:

   types { text/markdown md; }
   location ~ \.md$ { add_header Vary "Accept"; charset utf-8; }

   Copy

2. Accept: text/markdown is not honoured. The canonical URL returns HTML on both sites. The .md paths work; header negotiation does not, and it also needs host access. A sketch is in Reading these docs as an agent.

3. Rendered HTML is still HTML. Serving this site's own page costs 54,076 tokens against 3,917 for its Markdown. Markdown is not an optimisation of HTML; it is a different representation, and agents should be sent to it. Every page now advertises its Markdown twin in the head, which is the part we can do without the server:

   <link rel="alternate" type="text/markdown" href="ekyc.md" title="This page as Markdown">

   Copy

Fixed since the first version of this page: the broken canonical on document-verification.md, and the absence of <link rel="canonical"> in the head — every page now points search engines at its docs.seon.io original, so this parallel site cannot compete with the real documentation in search.

Reproducing this

# What the canonical URL actually returns
curl -sSL https://docs.seon.io/api-reference/workflow-api | wc -c
curl -sSL https://hackathon.seondf.net/api-reference/workflow-api.md | wc -c

# What each site offers an agent
curl -sSI https://docs.seon.io/llms.txt      | head -1
curl -sSI https://docs.seon.io/llms-full.txt | head -1
curl -sSI https://hackathon.seondf.net/llms-full.txt | head -1

Token counts used cl100k_base via tiktoken. Figures were taken on 2 September 2026; the live site changes, so re-run rather than trusting them.