◇ BenchmarkWeb fundamentals
MDN: Overview of HTTP: 91.0% fewer tokens.
MDN's HTTP overview, the reference page for the protocol itself. Read through the Lyrenth index, the page becomes one clean AIDocument of 5,085 tokens instead of 56,692 tokens of raw HTML: 11x smaller for every agent that reads it. Numbers straight from the API's economics block, measured 2026-07-05.
Raw HTML · 56,692 tokens
AIDocument · 5,085 tokens
| Cost to ingest raw HTML | $0.170 |
| Cost to ingest the AIDocument | $0.015 |
| Saved, per read, per agent | $0.155 |
Basis: $3.00 per 1M input tokens (Claude Sonnet / GPT-4 Turbo class), as reported in the API's economics block. Source page: https://developer.mozilla.org/en-US/docs/Web/HTTP/Guides/Overview
Reproduce it
One call, same numbers.
Every AIDocument response carries its own economics block, so this benchmark reproduces itself:
curl -X POST https://api.lyrenth.com/v1/aidocument \
-H "Authorization: Bearer $LYRENTH_KEY" \
-H "Content-Type: application/json" \
-d '{"url":"https://developer.mozilla.org/en-US/docs/Web/HTTP/Guides/Overview"}'