Colosseum Wikipedia HTML token count: 118,862 tokens (gpt-5 / o200k_base)

count_colosseum_tokens.ts

import { encoding_for_model, TiktokenModel } from "tiktoken";

const URL = "https://en.wikipedia.org/wiki/Colosseum";
const MODEL = "gpt-5" as TiktokenModel;

const response = await fetch(URL);
const html = await response.text();

const encoding = encoding_for_model(MODEL);
const tokens = encoding.encode(html);

console.log(`HTML length: ${html.length.toLocaleString()} characters`);
console.log(`Token count (${MODEL}): ${tokens.length.toLocaleString()}`);

encoding.free();