Unverified50% confidenceBenchmarkExact time
The raw HTML of the 20 pages totaled more than 3.71 million tokens, full-page-to-text conversion was about 243,000 tokens, main-content-only Markdown was about 110,000 tokens, and LLM Markdown was about 95,000 tokens.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/13/2026
First Seen
Valid until: 1/11/2027
Sources
Related Entities
Related Claims
UnverifiedWebFetch previously silently discarded page content exceeding 100,000 characters; after the update it notifies users of the amount not read and supports continued reading via an offset.68% similarUnverifiedChrome's official documentation recommends that the total number of DOM nodes on a page not exceed approximately 1,500.68% similarUnverifiedA typical HTML document may consume 2–5 times more tokens compared to equivalent Markdown content68% similarUnverifiedThe LLM-oriented Markdown form saves 98% of tokens compared with raw HTML at the median and 63% compared with full-page-to-text conversion.67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1021867API
curl https://kongchang.com/api/v1/knowledge/claims/1021867MCP
get_claim(id=1021867)