{
 "product": "YFarmX Model Identity",
 "method": "tokenizer fingerprinting v1-50",
 "updated": "2026-08-22",
 "note": "Marginal prompt-token cost is measured per string: prompt_tokens minus the per-provider baseline overhead, provider-pinned, with caching-corrupt rows excluded.",
 "strings": [
  {
   "name": "en-prose",
   "text": "The quick brown fox jumps over the lazy dog near the riverbank."
  },
  {
   "name": "en-long",
   "text": "Attribution of a stealth model requires evidence that the model cannot choose to withhold."
  },
  {
   "name": "spaces-20",
   "text": "a                    b"
  },
  {
   "name": "spaces-60",
   "text": "a                                                            b"
  },
  {
   "name": "tabs-20",
   "text": "a\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\tb"
  },
  {
   "name": "newlines-20",
   "text": "a\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nb"
  },
  {
   "name": "mixed-ws",
   "text": "a \t\n  \t\n   b"
  },
  {
   "name": "digits-9",
   "text": "123456789"
  },
  {
   "name": "digits-12",
   "text": "123456789012"
  },
  {
   "name": "digits-30",
   "text": "111111111111111111111111111111"
  },
  {
   "name": "digits-sep",
   "text": "1,234,567.89"
  },
  {
   "name": "float-long",
   "text": "3.14159265358979323846"
  },
  {
   "name": "zh-common",
   "text": "这是一个用于测试分词器行为的中文句子"
  },
  {
   "name": "zh-long",
   "text": "人工智能模型的归属需要可验证的证据而不是自我报告"
  },
  {
   "name": "zh-rare",
   "text": "龘齉齾爩鱻麤靐飝鞻"
  },
  {
   "name": "ja-kana",
   "text": "これはトークナイザーのテストです"
  },
  {
   "name": "ja-kanji",
   "text": "日本語の漢字と仮名の混在文章"
  },
  {
   "name": "ko",
   "text": "한국어 토크나이저 테스트 문장입니다"
  },
  {
   "name": "ru",
   "text": "Проверка токенизатора на кириллице"
  },
  {
   "name": "ar",
   "text": "اختبار المحلل اللغوي للنصوص العربية"
  },
  {
   "name": "he",
   "text": "בדיקת מנתח אסימונים בעברית"
  },
  {
   "name": "hi",
   "text": "यह टोकनाइज़र परीक्षण वाक्य है"
  },
  {
   "name": "th",
   "text": "นี่คือประโยคทดสอบตัวแบ่งคำ"
  },
  {
   "name": "el",
   "text": "Δοκιμή του τμηματοποιητή κειμένου"
  },
  {
   "name": "emoji-basic",
   "text": "😀😃😄😁😆"
  },
  {
   "name": "emoji-skin",
   "text": "👍🏻👍🏼👍🏽👍🏾👍🏿"
  },
  {
   "name": "emoji-zwj-family",
   "text": "👨‍👩‍👧‍👦"
  },
  {
   "name": "emoji-zwj-x3",
   "text": "👨‍👩‍👧‍👦👨‍👩‍👧‍👦👨‍👩‍👧‍👦"
  },
  {
   "name": "emoji-flags",
   "text": "🇬🇧🇺🇸🇨🇳🇯🇵"
  },
  {
   "name": "emoji-prof",
   "text": "👩🏽‍💻👨🏿‍🚀🧑‍🔬"
  },
  {
   "name": "math",
   "text": "∀x∈ℝ ∃y∈ℚ : x⊕y ≡ ∅ ∧ ∇²φ = 0"
  },
  {
   "name": "boxdraw",
   "text": "┌─┬─┐│├┼┤└┴┘╔═╗╚╝"
  },
  {
   "name": "combining",
   "text": "áêĩōü"
  },
  {
   "name": "cjk-ext-b",
   "text": "𠀀𠀁𠀂𪛖"
  },
  {
   "name": "surrogates",
   "text": "𝕳𝖊𝖑𝖑𝖔 𝓦𝓸𝓻𝓵𝓭 𝟙𝟚𝟛"
  },
  {
   "name": "zalgo",
   "text": "h̸̢̛e̵̛�݃l̷̨͐l̸̛͝o̶̧͝"
  },
  {
   "name": "rtl-mix",
   "text": "hello שלום world مرحبا"
  },
  {
   "name": "py-code",
   "text": "def f(x):\n    return [i**2 for i in range(x) if i % 3 == 0]"
  },
  {
   "name": "py-indent",
   "text": "if a:\n        if b:\n                if c:\n                        return 1"
  },
  {
   "name": "json",
   "text": "{\"model\":\"ox-alpha\",\"context_length\":1048576,\"top_p\":0.95}"
  },
  {
   "name": "html",
   "text": "<div class=\"row\"><span id=\"a\">x</span></div>"
  },
  {
   "name": "regex",
   "text": "^(?:[a-z0-9!#$%&*+/=?^_`{|}~-]+)@(?:[a-z0-9](?:[a-z0-9-]*)?\\.)+$"
  },
  {
   "name": "camel",
   "text": "getUserAccountBalanceByIdentifier"
  },
  {
   "name": "snake",
   "text": "get_user_account_balance_by_identifier"
  },
  {
   "name": "rare-word-x5",
   "text": "antidisestablishmentarianism antidisestablishmentarianism antidisestablishmentarianism antidisestablishmentarianism antidisestablishmentarianism "
  },
  {
   "name": "repeat-tok",
   "text": "lorem lorem lorem lorem lorem lorem lorem lorem lorem lorem lorem lorem lorem lorem lorem lorem lorem lorem lorem lorem "
  },
  {
   "name": "base64",
   "text": "SGVsbG8gV29ybGQhIFRoaXMgaXMgYSB0ZXN0IHN0cmluZy4="
  },
  {
   "name": "hex",
   "text": "deadbeefcafebabe0123456789abcdef"
  },
  {
   "name": "url",
   "text": "https://openrouter.ai/api/v1/models?limit=100&offset=0"
  },
  {
   "name": "uuid",
   "text": "3f2504e0-4f89-11d3-9a0c-0305e82c3301"
  }
 ]
}