YFarmX logoYFarmXIntelligence for an accelerating worldBriefings
YFarmX logoYFarmX
YFarmX

AI Desk · AI Fingerprinting · Compare

Google: Gemini 3.7 Flash · NVIDIA: Nemotron 3.5 Content Safety (free)

Identity similarity: lowDivergent fingerprints · 22/50These models tokenise differently. The rows that part here are the English prose, whitespace, digit, CJK, non-Latin script and emoji strings. Divergence on high-information strings separates unrelated vocabularies within a handful of samples.

Google: Gemini 3.7 Flash recordNVIDIA: Nemotron 3.5 Content Safety (free) recordOpen in the interactive bench

View all 50 test strings22 matched · 28 different · 0 excluded

String-by-string results

Expand a string to read or copy its exact text. Each row compares the two models’ token counts.

22 of 50 clean strings agree

Showing all 50 strings.

Test stringGoogle: Gemini 3.7 FlashNVIDIA: Nemotron 3.5 Content Safety (free)Result
English sentenceen-prose
Exact text
The quick brown fox jumps over the lazy dog near the riverbank.
1414✓ Matched
Long English sentenceen-long
Exact text
Attribution of a stealth model requires evidence that the model cannot choose to withhold.
1615≠ Different
20 spacesspaces-20
Exact text
a                    b
Show whitespace marks

· = space, ⇥ = tab, ↵ = line break

a····················b
32≠ Different
60 spacesspaces-60
Exact text
a                                                            b
Show whitespace marks

· = space, ⇥ = tab, ↵ = line break

a····························································b
42≠ Different
20 tabstabs-20
Exact text
a																				b
Show whitespace marks

· = space, ⇥ = tab, ↵ = line break

a⇥⇥⇥⇥⇥⇥⇥⇥⇥⇥⇥⇥⇥⇥⇥⇥⇥⇥⇥⇥b
32≠ Different
20 line breaksnewlines-20
Exact text
a



















b
Show whitespace marks

· = space, ⇥ = tab, ↵ = line break

a↵
↵
↵
↵
↵
↵
↵
↵
↵
↵
↵
↵
↵
↵
↵
↵
↵
↵
↵
↵
b
32≠ Different
Mixed whitespacemixed-ws
Exact text
a 	
  	
   b
Show whitespace marks

· = space, ⇥ = tab, ↵ = line break

a·⇥↵
··⇥↵
···b
92≠ Different
9 digitsdigits-9
Exact text
123456789
910≠ Different
12 digitsdigits-12
Exact text
123456789012
1213≠ Different
30 repeated digitsdigits-30
Exact text
111111111111111111111111111111
3031≠ Different
Formatted numberdigits-sep
Exact text
1,234,567.89
1213≠ Different
Long decimalfloat-long
Exact text
3.14159265358979323846
2223≠ Different
Chinese sentencezh-common
Exact text
这是一个用于测试分词器行为的中文句子
1011≠ Different
Long Chinese sentencezh-long
Exact text
人工智能模型的归属需要可验证的证据而不是自我报告
1214≠ Different
Rare Chinese characterszh-rare
Exact text
龘齉齾爩鱻麤靐飝鞻
2526≠ Different
Japanese kanaja-kana
Exact text
これはトークナイザーのテストです
77✓ Matched
Japanese kanjija-kanji
Exact text
日本語の漢字と仮名の混在文章
910≠ Different
Koreanko
Exact text
한국어 토크나이저 테스트 문장입니다
1111✓ Matched
Russianru
Exact text
Проверка токенизатора на кириллице
1212✓ Matched
Arabicar
Exact text
اختبار المحلل اللغوي للنصوص العربية
109≠ Different
Hebrewhe
Exact text
בדיקת מנתח אסימונים בעברית
1312≠ Different
Hindihi
Exact text
यह टोकनाइज़र परीक्षण वाक्य है
88✓ Matched
Thaith
Exact text
นี่คือประโยคทดสอบตัวแบ่งคำ
1010✓ Matched
Greekel
Exact text
Δοκιμή του τμηματοποιητή κειμένου
1313✓ Matched
Basic emojiemoji-basic
Exact text
😀😃😄😁😆
55✓ Matched
Emoji skin tonesemoji-skin
Exact text
👍🏻👍🏼👍🏽👍🏾👍🏿
1010✓ Matched
Joined family emojiemoji-zwj-family
Exact text
👨‍👩‍👧‍👦
78≠ Different
Repeated family emojiemoji-zwj-x3
Exact text
👨‍👩‍👧‍👦👨‍👩‍👧‍👦👨‍👩‍👧‍👦
2122≠ Different
Flag emojiemoji-flags
Exact text
🇬🇧🇺🇸🇨🇳🇯🇵
89≠ Different
Profession emojiemoji-prof
Exact text
👩🏽‍💻👨🏿‍🚀🧑‍🔬
1112≠ Different
Mathematical symbolsmath
Exact text
∀x∈ℝ ∃y∈ℚ : x⊕y ≡ ∅ ∧ ∇²φ = 0
2626✓ Matched
Box-drawing charactersboxdraw
Exact text
┌─┬─┐│├┼┤└┴┘╔═╗╚╝
1718≠ Different
Combining accentscombining
Exact text
áêĩōü
1010✓ Matched
Extended Chinese characterscjk-ext-b
Exact text
𠀀𠀁𠀂𪛖
1617≠ Different
Styled Unicode letterssurrogates
Exact text
𝕳𝖊𝖑𝖑𝖔 𝓦𝓸𝓻𝓵𝓭 𝟙𝟚𝟛
2728≠ Different
Layered combining markszalgo
Exact text
h̸̢̛e̵̛�݃l̷̨͐l̸̛͝o̶̧͝
2222✓ Matched
Mixed writing directionsrtl-mix
Exact text
hello שלום world مرحبا
55✓ Matched
Python codepy-code
Exact text
def f(x):
    return [i**2 for i in range(x) if i % 3 == 0]
Show whitespace marks

· = space, ⇥ = tab, ↵ = line break

def·f(x):↵
····return·[i**2·for·i·in·range(x)·if·i·%·3·==·0]
2826≠ Different
Indented Pythonpy-indent
Exact text
if a:
        if b:
                if c:
                        return 1
Show whitespace marks

· = space, ⇥ = tab, ↵ = line break

if·a:↵
········if·b:↵
················if·c:↵
························return·1
1812≠ Different
JSON objectjson
Exact text
{"model":"ox-alpha","context_length":1048576,"top_p":0.95}
2828✓ Matched
HTML markuphtml
Exact text
<div class="row"><span id="a">x</span></div>
1414✓ Matched
Regular expressionregex
Exact text
^(?:[a-z0-9!#$%&*+/=?^_`{|}~-]+)@(?:[a-z0-9](?:[a-z0-9-]*)?\.)+$
4444✓ Matched
Camel-case identifiercamel
Exact text
getUserAccountBalanceByIdentifier
66✓ Matched
Snake-case identifiersnake
Exact text
get_user_account_balance_by_identifier
1111✓ Matched
Repeated long wordrare-word-x5
Exact text
antidisestablishmentarianism antidisestablishmentarianism antidisestablishmentarianism antidisestablishmentarianism antidisestablishmentarianism
2525✓ Matched
Repeated wordrepeat-tok
Exact text
lorem lorem lorem lorem lorem lorem lorem lorem lorem lorem lorem lorem lorem lorem lorem lorem lorem lorem lorem lorem
2120≠ Different
Base64 textbase64
Exact text
SGVsbG8gV29ybGQhIFRoaXMgaXMgYSB0ZXN0IHN0cmluZy4=
3434✓ Matched
Hexadecimal texthex
Exact text
deadbeefcafebabe0123456789abcdef
1616✓ Matched
URL texturl
Exact text
https://openrouter.ai/api/v1/models?limit=100&offset=0
2323✓ Matched
UUIDuuid
Exact text
3f2504e0-4f89-11d3-9a0c-0305e82c3301
3637≠ Different

Counts show each string’s prompt-token cost after the fixed overhead is subtracted. Excluded readings are kept separate from matched and different results.

Published model settings

Limits, prices and capabilities

Compare the essentials, then open the developer settings for more detail.

AGoogle: Gemini 3.7 Flash
BNVIDIA: Nemotron 3.5 Content Safety (free)

Context window

Different

Total token capacity per request

A1,048,576 tokens
B128,000 tokens

Maximum reply

Different

Published output limit in tokens

A65,536 tokens
B8,192 tokens

Input price

Different

US dollars per 1 million input tokens

AUS$0.75 / 1M tokens
BUS$0.00 / 1M tokens

Output price

Different

US dollars per 1 million output tokens

AUS$3.75 / 1M tokens
BUS$0.00 / 1M tokens

What you can send and receive

Different

AGemini 3.7 Flash

Accepts
textimagefileaudiovideo
Produces
text

BNemotron 3.5 Content Safety (free)

Accepts
textimage
Produces
text

Developer settings

Open a section to compare the complete declarations.

Supported API settingsShared controls and the settings unique to each model6 shared · 6 model-specific

AOnly Gemini 3.7 Flash 6

  • Reasoning effortreasoning_effort
  • Response formatresponse_format
  • Stop sequencesstop
  • Structured outputsstructured_outputs
  • Tool choicetool_choice
  • Toolstools

BOnly Nemotron 3.5 Content Safety (free) 0

All declared settings are shared.

6 settings supported by both models
  • Include reasoninginclude_reasoning
  • Maximum tokensmax_tokens
  • Reasoningreasoning
  • Seedseed
  • Temperaturetemperature
  • Top ptop_p
Reasoning settingsEffort levels and reasoning behaviour3 different · 1 shared
A4 declared fieldsB2 declared fields
SettingAGemini 3.7 FlashBNemotron 3.5 Content Safety (free)
Reasoning requiredYesNo
Enabled by defaultYesYes
Effort levelshighmediumlowUnspecified
Default effortmediumUnspecified
Default settingsValues used when a request leaves a setting open6 different · 0 shared
ANo values declaredB6 declared fields
SettingAGemini 3.7 FlashBNemotron 3.5 Content Safety (free)
TemperatureUnspecifiedUnspecified
Top pUnspecifiedUnspecified
Top kUnspecifiedUnspecified
Frequency penaltyUnspecifiedUnspecified
Presence penaltyUnspecifiedUnspecified
Repetition penaltyUnspecifiedUnspecified

Published API declarations. Prices and limits can vary by provider.

Method: tokenizer fingerprinting, v1, 50 strings. This page is static and dated; the interactive bench compares any two of the 353 measured models.