AI Desk · Model Identity · Evidence object

Tokenizer signature tk_9f84b5fb

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 MiniMax group.

Members
7
First observed
21 August 2026
Last observed
21 August 2026
Group
MiniMax

Models with this signature

The measured vector

Marginal prompt-token cost per string, as measured on MiniMax: MiniMax-01
All 50 rows

English and whitespace

en-prose14
en-long16
spaces-203
spaces-603
tabs-204
newlines-204
mixed-ws6

Digits

digits-93
digits-124
digits-3010
digits-sep7
float-long9

CJK

zh-common10
zh-long11
zh-rare18
ja-kana7
ja-kanji9
ko11

Other scripts

ru14
ar9
he21
hi20
th25
el22

Emoji

emoji-basic10
emoji-skin12
emoji-zwj-family11
emoji-zwj-x333
emoji-flags16
emoji-prof18

Rare Unicode

math27
boxdraw25
combining6
cjk-ext-b16
surrogates41
zalgo34
rtl-mix9

Code

py-code25
py-indent15
json20
html16
regex45
camel6
snake6

Repetition and encodings

rare-word-x531
repeat-tok41
base6432
hex11
url17
uuid27

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