AI Desk · Model Identity · Evidence object
Tokenizer signature tk_d1411c9d
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 GPT group.
- Members
- 32
- First observed
- 21 August 2026
- Last observed
- 3 September 2026
- Group
- GPT
Models with this signature
OpenAI: GPT-3.5 Turbo (older v0613)openai/gpt-3.5-turbo-0613OpenAIOpenAI: GPT-4.1openai/gpt-4.1OpenAIOpenAI: GPT-4.1 Miniopenai/gpt-4.1-miniOpenAIOpenAI: GPT-4.1 Nanoopenai/gpt-4.1-nanoOpenAIOpenAI: GPT-4o-miniopenai/gpt-4o-miniOpenAIOpenAI: GPT-4o-mini (2024-07-18)openai/gpt-4o-mini-2024-07-18OpenAIOpenAI: GPT-5openai/gpt-5OpenAIOpenAI: GPT-5 Nanoopenai/gpt-5-nanoOpenAIOpenAI: GPT-5.1openai/gpt-5.1OpenAIOpenAI: GPT-5.1-Codexopenai/gpt-5.1-codexOpenAIOpenAI: GPT-5.1-Codex-Maxopenai/gpt-5.1-codex-maxOpenAIOpenAI: GPT-5.1-Codex-Miniopenai/gpt-5.1-codex-miniOpenAIOpenAI: GPT-5.2openai/gpt-5.2OpenAIOpenAI: GPT-5.2-Codexopenai/gpt-5.2-codexOpenAIOpenAI: GPT-5.3-Codexopenai/gpt-5.3-codexOpenAIOpenAI: GPT-5.4openai/gpt-5.4OpenAIOpenAI: GPT-5.4 Miniopenai/gpt-5.4-miniOpenAIOpenAI: GPT-5.4 Nanoopenai/gpt-5.4-nanoOpenAIOpenAI: GPT-5.5openai/gpt-5.5OpenAIOpenAI: GPT-5.6 Lunaopenai/gpt-5.6-lunaOpenAIOpenAI: GPT-5.6 Solopenai/gpt-5.6-solOpenAIOpenAI: GPT-5.6 Terraopenai/gpt-5.6-terraOpenAIOpenAI: GPT Chat Latestopenai/gpt-chat-latestOpenAIOpenAI: gpt-oss-120bopenai/gpt-oss-120bOpenAIOpenAI: gpt-oss-20bopenai/gpt-oss-20bOpenAIOpenAI: gpt-oss-safeguard-20bopenai/gpt-oss-safeguard-20bOpenAIOpenAI: o3 Miniopenai/o3-miniOpenAIOpenAI: o3 Mini Highopenai/o3-mini-highOpenAIOpenAI: o4 Miniopenai/o4-miniOpenAIOpenAI: o4 Mini Highopenai/o4-mini-highOpenAIThinking Machines: Inklingthinkingmachines/inklingThinking MachinesThinking Machines: Inkling Smallthinkingmachines/inkling-smallThinking Machines
The measured vector
Marginal prompt-token cost per string, as measured on OpenAI: GPT-3.5 Turbo (older v0613)All 50 rows
English and whitespace
en-prose14
en-long17
spaces-203
spaces-603
tabs-203
newlines-204
mixed-ws6
Digits
digits-93
digits-124
digits-3010
digits-sep7
float-long9
CJK
zh-common12
zh-long17
zh-rare20
ja-kana10
ja-kanji13
ko11
Other scripts
ru11
ar11
he10
hi11
th11
el14
Emoji
emoji-basic8
emoji-skin13
emoji-zwj-family11
emoji-zwj-x333
emoji-flags16
emoji-prof20
Rare Unicode
math31
boxdraw27
combining11
cjk-ext-b13
surrogates40
zalgo35
rtl-mix5
Code
py-code25
py-indent15
json20
html16
regex44
camel6
snake6
Repetition and encodings
rare-word-x531
repeat-tok22
base6434
hex11
url17
uuid27
Method: tokenizer fingerprinting, v1-50.