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.
| Page | Today, on docs.seon.io | On the new docs, as Markdown | Cheaper by |
|---|---|---|---|
| Workflow API | 96,495 | 3,917 | 25× |
| Orchestration integration | 60,281 | 4,551 | 13× |
| eKYC | 118,868 | 1,820 | 65× |
| Proof of Address | 116,261 | 1,211 | 96× |
Is it the same content?
The obvious objection is that any page can be made cheap by deleting things, so here is the honest answer, counting prose words with markup stripped from both sides:
| Page | Words in the live article | Words here | |
|---|---|---|---|
| eKYC | 1,098 | 1,144 | 104% |
| Proof of Address | 923 | 932 | 101% |
| Workflow API | 2,384 | 1,658 | 70% |
| Orchestration integration | 1,919 | 1,405 | 73% |
The two prose pages are at parity, so their 65× and 96× are clean: the saving is markup, not substance.
The two API pages are not, and the reason is a real gap rather than lost prose. Their Markdown contains {% attributes %} and {% endpoint %} tags, which expand into full reference tables when the page renders. An agent fetching the Markdown gets the tags; a person reading the page gets the tables. So 25× and 13× flatter us — those two rows compare a full page against a thinner one. Expanding the tags when the Markdown is written, rather than only when the HTML is, is the fix.
What each site offers an agent
Every row below was probed against both live sites.
| Capability | docs.seon.io | This site | What it means for an agent |
|---|---|---|---|
/llms.txt index | ✓ Yes — real, text/plain | ✓ Yes | How it discovers what exists at all. Without one, it crawls or guesses URLs. |
Per-section llms.txt | ✗ No | ✓ Yes | Lets it pull just the Fraud API without ingesting the entire corpus first. |
/llms-full.txt for bulk ingestion | ✗ No — 404 | ✓ Yes — 219 KB | One request instead of hundreds when vectorising or working offline. |
Page as raw Markdown, <path>.md | ✗ No — 404 | ✓ Yes | The whole ballgame: 3,917 tokens instead of 96,495 for the same page. |
Page as raw Markdown, <path>/index.md | ✗ No — 404 | ✓ Yes | Agents guess differently. Serving both means neither has to know our conventions. |
Content negotiation on Accept: text/markdown | ✗ No — returns HTML | ✗ No — returns HTML | Would let an agent holding only the canonical link get Markdown with no path convention at all. |
/robots.txt | ✗ No — 404 | ✓ Yes | The one standard channel for telling a crawler what not to ingest. |
| Deprecated pages kept out of agent indexes | ✗ No | ✓ Yes | Stops a coding assistant confidently recommending an integration path we no longer support. |
| Copy-as-Markdown control in the page | ✗ No | ✓ Yes | Lets a person hand the page to their own agent in one click, correctly. |
<link rel="alternate" type="text/markdown"> in the head | ✗ No | ✓ Yes | An agent that landed on the HTML learns a cheaper representation exists, without guessing a path. |
Markdown served as text/markdown | ✗ No | ✗ No — octet-stream | Content-type-sensitive agents may skip a file they cannot identify. Ours needs a host-side fix. |
Gaps on the current documentation
- No Markdown representation.
llms.txtpoints an agent at pages it can only then read as full HTML. Discovery without cheap retrieval. - No
llms-full.txt. Bulk ingestion means crawling every page at full HTML cost. /robots.txtreturns 404. Crawlers get no directives at all, so there is no way to steer them away from superseded pages.- 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.
- Hydration overhead. Up to half of each page is a duplicate copy of its own content in JSON.
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 -1Token counts used cl100k_base via tiktoken. Figures were taken on 2 September 2026; the live site changes, so re-run rather than trusting them.