◇ BenchmarkLanguages
Python asyncio docs: 79.7% fewer tokens.
The asyncio landing page from the official Python documentation. Read through the Lyrenth index, the page becomes one clean AIDocument of 1,251 tokens instead of 6,175 tokens of raw HTML: 4.9x smaller for every agent that reads it. Numbers straight from the API's economics block, measured 2026-07-05.
Raw HTML · 6,175 tokens
AIDocument · 1,251 tokens
| Cost to ingest raw HTML | $0.019 |
| Cost to ingest the AIDocument | $0.0038 |
| Saved, per read, per agent | $0.015 |
Basis: $3.00 per 1M input tokens (Claude Sonnet / GPT-4 Turbo class), as reported in the API's economics block. Source page: https://docs.python.org/3/library/asyncio.html
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://docs.python.org/3/library/asyncio.html"}'