AI Desk · Model Identity · Evidence object
Tokenizer signature tk_cb7f8e86
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 B group.
- Members
- 1
- First observed
- 3 September 2026
- Last observed
- 3 September 2026
- Group
- Grok · group B
Models with this signature
The measured vector
Marginal prompt-token cost per string, as measured on SpaceXAI: Grok 4.5All 50 rows
English and whitespace
en-prose14
en-long15
spaces-203
spaces-603
tabs-204
newlines-204
mixed-ws6
Digits
digits-93
digits-124
digits-3010
digits-sep7
float-long9
CJK
zh-common13
zh-long13
zh-rare17
ja-kana7
ja-kanji10
ko12
Other scripts
ru11
ar8
he13
hi11
th10
el13
Emoji
emoji-basic5
emoji-skin5
emoji-zwj-family1
emoji-zwj-x33
emoji-flags4
emoji-prof3
Rare Unicode
math25
boxdraw17
combining10
cjk-ext-b13
surrogates15
zalgo22
rtl-mix6
Code
py-code28
py-indent15
json24
html16
regex47
camel6
snake11
Repetition and encodings
rare-word-x521
repeat-tok41
base6435
hex11
url20
uuid27
Method: tokenizer fingerprinting, v1-50.