AI Desk · Model Identity · Evidence object

Tokenizer signature tk_caaaa531

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 Cohere · group B group.

Members
1
First observed
21 August 2026
Last observed
21 August 2026
Group
Cohere · group B

Models with this signature

The measured vector

Marginal prompt-token cost per string, as measured on Cohere: North Mini Code (free)
All 50 rows

English and whitespace

en-prose14
en-long15
spaces-203
spaces-603
tabs-203
newlines-204
mixed-ws6

Digits

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

CJK

zh-common10
zh-long13
zh-rare18
ja-kana7
ja-kanji9
ko10

Other scripts

ru12
ar11
he10
hi11
th9
el13

Emoji

emoji-basic10
emoji-skin10
emoji-zwj-family9
emoji-zwj-x327
emoji-flags12
emoji-prof13

Rare Unicode

math24
boxdraw22
combining9
cjk-ext-b16
surrogates35
zalgo33
rtl-mix6

Code

py-code25
py-indent15
json20
html16
regex39
camel6
snake6

Repetition and encodings

rare-word-x520
repeat-tok20
base6432
hex10
url17
uuid27

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