AI Desk · Model Identity · Evidence object
Tokenizer signature tk_a17bbc1d
An exact tokenizer signature: every model listed below returned the same marginal prompt-token count on all 50 test strings. Sharing a signature is strong evidence of a shared vocabulary. This signature sits in the Grok · group A group.
- Members
- 3
- First observed
- 3 September 2026
- Last observed
- 3 September 2026
- Group
- Grok · group A
Models with this signature
The measured vector
Marginal prompt-token cost per string, as measured on SpaceXAI: Grok 4.20All 50 rows
English and whitespace
en-prose14
en-long16
spaces-203
spaces-603
tabs-203
newlines-204
mixed-ws6
Digits
digits-93
digits-124
digits-3010
digits-sep7
float-long9
CJK
zh-common9
zh-long13
zh-rare18
ja-kana9
ja-kanji10
ko11
Other scripts
ru11
ar16
he14
hi13
th13
el15
Emoji
emoji-basic10
emoji-skin14
emoji-zwj-family11
emoji-zwj-x333
emoji-flags16
emoji-prof20
Rare Unicode
math27
boxdraw24
combining10
cjk-ext-b16
surrogates40
zalgo35
rtl-mix6
Code
py-code25
py-indent15
json20
html16
regex42
camel6
snake6
Repetition and encodings
rare-word-x526
repeat-tok22
base6433
hex10
url17
uuid27
Method: tokenizer fingerprinting, v1-50.