AI Desk · Model Identity · Evidence object
Tokenizer signature tk_73c4f0dc
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 DeepSeek group.
- Members
- 10
- First observed
- 20 August 2026
- Last observed
- 21 August 2026
- Group
- DeepSeek
Models with this signature
DeepSeek: DeepSeek V3deepseek/deepseek-chatDeepSeekDeepSeek: DeepSeek V3 0324deepseek/deepseek-chat-v3-0324DeepSeekDeepSeek: DeepSeek V3.1 Terminusdeepseek/deepseek-v3.1-terminusDeepSeekDeepSeek: DeepSeek V3.2deepseek/deepseek-v3.2DeepSeekDeepSeek: DeepSeek V3.2 Expdeepseek/deepseek-v3.2-expDeepSeekDeepSeek: DeepSeek V4 Flash 0423deepseek/deepseek-v4-flashDeepSeekDeepSeek: DeepSeek V4 Flash 0731deepseek/deepseek-v4-flash-0731DeepSeekDeepSeek: DeepSeek V4 Pro 0813deepseek/deepseek-v4-pro-0813DeepSeekStepFun: Step 3.5 Flashstepfun/step-3.5-flashStepFunStepFun: Step 3.7 Flashstepfun/step-3.7-flashStepFun
Template variants of the same tokenizer
These signatures differ from this one by a uniform one-token shift on the affected strings: the same vocabulary behind a different chat template.
The measured vector
Marginal prompt-token cost per string, as measured on DeepSeek: DeepSeek V3All 50 rows
English and whitespace
en-prose14
en-long16
spaces-203
spaces-603
tabs-204
newlines-204
mixed-ws7
Digits
digits-93
digits-124
digits-3010
digits-sep7
float-long9
CJK
zh-common9
zh-long10
zh-rare18
ja-kana9
ja-kanji11
ko13
Other scripts
ru13
ar10
he14
hi18
th11
el16
Emoji
emoji-basic10
emoji-skin14
emoji-zwj-family11
emoji-zwj-x333
emoji-flags16
emoji-prof19
Rare Unicode
math22
boxdraw27
combining10
cjk-ext-b16
surrogates33
zalgo36
rtl-mix6
Code
py-code25
py-indent15
json20
html16
regex47
camel7
snake8
Repetition and encodings
rare-word-x526
repeat-tok41
base6434
hex12
url17
uuid27
Method: tokenizer fingerprinting, v1-50. Raw data: fingerprints.json · index.json · test-strings.json.