Venice: Uncensored

cognitivecomputations/dolphin-mistral-24b-venice-edition · CognitivecomputationsTokenizer lineage measured

Tokenizer lineage (measured): Mistral
Evidence confidence: High
Declared tokenizer tag: Other
Entered catalogue: 9 July 2025
Last tested: 21 August 2026
Measurement: Measured

Evidence

exact tokenizer signature shared with 1 model

Compare with Mistral: Mistral Small 3

Download JSON Report a correction

Identity statement

Venice: Uncensored is Cognitivecomputations's model. Its measured tokenizer sits with the Mistral group, which is evidence that it builds on the Mistral tokenizer. Tokenizer reuse is normal engineering, open vocabularies travel between labs, and this says nothing against Cognitivecomputations's authorship of the model itself.

Evidence stack

Signals of different kinds, weighed together

Signal	Result	Reference
Tokenizer signature	Exact match with 1 other model	tk_ddc193e9
API surface	No other entry shares this exact contract	api_b38ad3f1
Context and output	128,000 context · 8,192 max output	declared
Reasoning contract	None declared	declared
Serving providers observed	Venice	measured 21 August 2026

Shares this fingerprint

Exact signature first; template-boundary shifts of the same signature beneath

Mistral: Mistral Small 3mistralai/mistral-small-24b-instruct-2501exact · 50/50

Closest measured models

Agreement across the mutually clean test strings

Mistral: Mistral Small 3mistralai/mistral-small-24b-instruct-250150/50 · 100%TheDrummer: Cydonia 24B V4.1thedrummer/cydonia-24b-v4.149/49 · 100%Mistral: Mistral Nemomistralai/mistral-nemo48/50 · 96%NVIDIA: Nemotron 3 Nano 30B A3Bnvidia/nemotron-3-nano-30b-a3b48/50 · 96%NVIDIA: Nemotron 3.5 Lightningnvidia/nemotron-3.5-lightning48/50 · 96%NVIDIA: Nemotron 3 Supernvidia/nemotron-3-super-120b-a12b48/50 · 96%

Click a row to open the full comparison.

The measured fingerprint

Marginal prompt-token cost of each test string, grouped by script

All 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

hi17

th18

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

An x marks a row excluded as corrupt (caching or provider interference detected during measurement). Overhead subtracted: 557 prompt tokens.

Declared record

What the catalogue claims about this model

Venice Uncensored Dolphin Mistral 24B Venice Edition is a fine-tuned variant of Mistral-Small-24B-Instruct-2501, developed by dphn.ai in collaboration with Venice.ai. This model is designed as an “uncensored” instruct-tuned LLM, preserving...

Modalities: text->text
Declared tokenizer: Other
Prompt price: $0.20 / M tokens
Completion price: $0.90 / M tokens

Supported parameters

frequency_penaltymax_tokenspresence_penaltyresponse_formatstoptemperaturetop_ktop_p

defaults: {}

Catalogue entry Weights on Hugging Face

History

Every observation, kept as taken

9 July 2025Enters the OpenRouter catalogue with no declared family.
21 August 2026Fingerprinted in the YFarmX catalogue sweep · 50 of 50 strings measured clean.
21 August 2026YFarmX assessment: consistent with the Mistral family, high confidence.

Cite this page as the evidence record for Venice: Uncensored: the URL is stable, measurements are dated, and revisions append to the history above. Method: tokenizer fingerprinting, v1, 50 strings. The raw data behind every figure is on the data page.