AI Desk · Model Identity · Evidence object

Tokenizer signature tk_c670dac9

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 Meituan group.

Members
1
First observed
21 August 2026
Last observed
21 August 2026
Group
Meituan

Models with this signature

The measured vector

Marginal prompt-token cost per string, as measured on Meituan: LongCat 2.0
All 50 rows

English and whitespace

en-prose14
en-long17
spaces-203
spaces-603
tabs-204
newlines-204
mixed-ws6

Digits

digits-99
digits-1212
digits-3030
digits-sep12
float-long22

CJK

zh-common9
zh-long10
zh-rare18
ja-kana9
ja-kanji10
ko17

Other scripts

ru15
ar14
he29
hi34
th26
el27

Emoji

emoji-basic10
emoji-skin14
emoji-zwj-family10
emoji-zwj-x330
emoji-flags16
emoji-prof18

Rare Unicode

math31
boxdraw24
combining13
cjk-ext-b16
surrogates40
zalgo36
rtl-mix11

Code

py-code25
py-indent15
json25
html16
regex45
camel6
snake6

Repetition and encodings

rare-word-x531
repeat-tok41
base6435
hex18
url19
uuid36

Method: tokenizer fingerprinting, v1-50. Raw data: fingerprints.json · index.json · test-strings.json.