AI Desk · Model Identity · Evidence object
Tokenizer signature tk_0da8a999
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 Mistral · group A group.
- Members
- 13
- First observed
- 21 August 2026
- Last observed
- 21 August 2026
- Group
- Mistral · group A
Models with this signature
Mistral: Codestral 2508mistralai/codestral-2508Mistral AIMistral: Ministral 3 14B 2512mistralai/ministral-14b-2512Mistral AIMistral: Ministral 3 3B 2512mistralai/ministral-3b-2512Mistral AIMistral: Ministral 3 8B 2512mistralai/ministral-8b-2512Mistral AIMistral: Mistral Nemomistralai/mistral-nemoMistral AIMistral: Sabamistralai/mistral-sabaMistral AIMistral: Mistral Small 4mistralai/mistral-small-2603Mistral AIMistral: Mistral Small 3.1 24Bmistralai/mistral-small-3.1-24b-instructMistral AIMistral: Mistral Small 3.2 24Bmistralai/mistral-small-3.2-24b-instructMistral AIMistral: Voxtral Small 24B 2507mistralai/voxtral-small-24b-2507Mistral AINVIDIA: Nemotron 3 Nano 30B A3Bnvidia/nemotron-3-nano-30b-a3bNVIDIANVIDIA: Nemotron 3 Supernvidia/nemotron-3-super-120b-a12bNVIDIANVIDIA: Nemotron 3.5 Lightningnvidia/nemotron-3.5-lightningNVIDIA
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 Mistral: Codestral 2508All 50 rows
English and whitespace
en-prose14
en-long18
spaces-203
spaces-603
tabs-204
newlines-207
mixed-ws7
Digits
digits-99
digits-1212
digits-3030
digits-sep12
float-long22
CJK
zh-common16
zh-long20
zh-rare20
ja-kana11
ja-kanji13
ko13
Other scripts
ru12
ar9
he10
hi14
th17
el13
Emoji
emoji-basic20
emoji-skin40
emoji-zwj-family19
emoji-zwj-x357
emoji-flags32
emoji-prof35
Rare Unicode
math33
boxdraw30
combining14
cjk-ext-b16
surrogates53
zalgo36
rtl-mix6
Code
py-code25
py-indent15
json25
html16
regex49
camel6
snake7
Repetition and encodings
rare-word-x536
repeat-tok41
base6439
hex19
url19
uuid36
Method: tokenizer fingerprinting, v1-50. Raw data: fingerprints.json · index.json · test-strings.json.