YFarmX logoYFarmX

AI Desk · AI Fingerprinting · Compare

Amazon: Nova Premier 1.0 · XingChen: Xing4.0 29B A4B (free)

Identity similarity: lowDivergent fingerprints · 20/50These models tokenise differently. The rows that part here are the English prose, whitespace, CJK, non-Latin script and emoji strings. Divergence on high-information strings separates unrelated vocabularies within a handful of samples.

Amazon: Nova Premier 1.0 recordXingChen: Xing4.0 29B A4B (free) recordOpen in the interactive bench

View all 50 test strings20 matched · 30 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.

20 of 50 clean strings agree

Showing all 50 strings.

Test stringAmazon: Nova Premier 1.0XingChen: Xing4.0 29B A4B (free)Result
English sentenceen-prose
Exact text
The quick brown fox jumps over the lazy dog near the riverbank.
1314≠ Different
Long English sentenceen-long
Exact text
Attribution of a stealth model requires evidence that the model cannot choose to withhold.
1517≠ Different
20 spacesspaces-20
Exact text
a                    b
Show whitespace marks

· = space, ⇥ = tab, ↵ = line break

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

· = space, ⇥ = tab, ↵ = line break

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

· = space, ⇥ = tab, ↵ = line break

a⇥⇥⇥⇥⇥⇥⇥⇥⇥⇥⇥⇥⇥⇥⇥⇥⇥⇥⇥⇥b
2222✓ Matched
20 line breaksnewlines-20
Exact text
a



















b
Show whitespace marks

· = space, ⇥ = tab, ↵ = line break

a↵
↵
↵
↵
↵
↵
↵
↵
↵
↵
↵
↵
↵
↵
↵
↵
↵
↵
↵
↵
b
2222✓ Matched
Mixed whitespacemixed-ws
Exact text
a 	
  	
   b
Show whitespace marks

· = space, ⇥ = tab, ↵ = line break

a·⇥↵
··⇥↵
···b
99✓ Matched
9 digitsdigits-9
Exact text
123456789
1010✓ Matched
12 digitsdigits-12
Exact text
123456789012
1313✓ Matched
30 repeated digitsdigits-30
Exact text
111111111111111111111111111111
3131✓ Matched
Formatted numberdigits-sep
Exact text
1,234,567.89
1313✓ Matched
Long decimalfloat-long
Exact text
3.14159265358979323846
2323✓ Matched
Chinese sentencezh-common
Exact text
这是一个用于测试分词器行为的中文句子
179≠ 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
2411≠ Different
Rare Chinese characterszh-rare
Exact text
龘齉齾爩鱻麤靐飝鞻
2828✓ Matched
Japanese kanaja-kana
Exact text
これはトークナイザーのテストです
99✓ Matched
Japanese kanjija-kanji
Exact text
日本語の漢字と仮名の混在文章
1314≠ Different
Koreanko
Exact text
한국어 토크나이저 테스트 문장입니다
1914≠ Different
Russianru
Exact text
Проверка токенизатора на кириллице
1411≠ Different
Arabicar
Exact text
اختبار المحلل اللغوي للنصوص العربية
1013≠ Different
Hebrewhe
Exact text
בדיקת מנתח אסימונים בעברית
1415≠ Different
Hindihi
Exact text
यह टोकनाइज़र परीक्षण वाक्य है
1117≠ Different
Thaith
Exact text
นี่คือประโยคทดสอบตัวแบ่งคำ
2216≠ Different
Greekel
Exact text
Δοκιμή του τμηματοποιητή κειμένου
1716≠ Different
Basic emojiemoji-basic
Exact text
😀😃😄😁😆
521≠ Different
Emoji skin tonesemoji-skin
Exact text
👍🏻👍🏼👍🏽👍🏾👍🏿
1441≠ Different
Joined family emojiemoji-zwj-family
Exact text
👨‍👩‍👧‍👦
2020✓ Matched
Repeated family emojiemoji-zwj-x3
Exact text
👨‍👩‍👧‍👦👨‍👩‍👧‍👦👨‍👩‍👧‍👦
5858✓ Matched
Flag emojiemoji-flags
Exact text
🇬🇧🇺🇸🇨🇳🇯🇵
2433≠ Different
Profession emojiemoji-prof
Exact text
👩🏽‍💻👨🏿‍🚀🧑‍🔬
3036≠ Different
Mathematical symbolsmath
Exact text
∀x∈ℝ ∃y∈ℚ : x⊕y ≡ ∅ ∧ ∇²φ = 0
3149≠ Different
Box-drawing charactersboxdraw
Exact text
┌─┬─┐│├┼┤└┴┘╔═╗╚╝
4040✓ Matched
Combining accentscombining
Exact text
áêĩōü
914≠ Different
Extended Chinese characterscjk-ext-b
Exact text
𠀀𠀁𠀂𪛖
1717✓ Matched
Styled Unicode letterssurrogates
Exact text
𝕳𝖊𝖑𝖑𝖔 𝓦𝓸𝓻𝓵𝓭 𝟙𝟚𝟛
5555✓ Matched
Layered combining markszalgo
Exact text
h̸̢̛e̵̛�݃l̷̨͐l̸̛͝o̶̧͝
3436≠ Different
Mixed writing directionsrtl-mix
Exact text
hello שלום world مرحبا
86≠ Different
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]
2928≠ 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
1918≠ 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>
1617≠ Different
Regular expressionregex
Exact text
^(?:[a-z0-9!#$%&*+/=?^_`{|}~-]+)@(?:[a-z0-9](?:[a-z0-9-]*)?\.)+$
5351≠ Different
Camel-case identifiercamel
Exact text
getUserAccountBalanceByIdentifier
67≠ Different
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 
2031≠ Different
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 
4041≠ Different
Base64 textbase64
Exact text
SGVsbG8gV29ybGQhIFRoaXMgaXMgYSB0ZXN0IHN0cmluZy4=
3636✓ Matched
Hexadecimal texthex
Exact text
deadbeefcafebabe0123456789abcdef
1619≠ Different
URL texturl
Exact text
https://openrouter.ai/api/v1/models?limit=100&offset=0
2323✓ Matched
UUIDuuid
Exact text
3f2504e0-4f89-11d3-9a0c-0305e82c3301
3737✓ Matched

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.

AAmazon: Nova Premier 1.0
BXingChen: Xing4.0 29B A4B (free)

Context window

Different

Total token capacity per request

A1,000,000 tokens
B262,144 tokens

Maximum reply

Different

Published output limit in tokens

A32,000 tokens
BUnspecified

Input price

Different

US dollars per 1 million input tokens

AUS$2.50 / 1M tokens
BUS$0.00 / 1M tokens

Output price

Different

US dollars per 1 million output tokens

AUS$12.50 / 1M tokens
BUS$0.00 / 1M tokens

Xing4.0 29B A4B (free): OpenRouter's listing shows 235,929 output tokens, which is 90% of the context window, the figure it carries where the provider declares no maximum.

What you can send and receive

Different

ANova Premier 1.0

Accepts
textimage
Produces
text

BXing4.0 29B A4B (free)

Accepts
text
Produces
text

Developer settings

Open a section to compare the complete declarations.

Supported API settingsShared controls and the settings unique to each model6 shared · 10 model-specific

AOnly Nova Premier 1.0 0

All declared settings are shared.

BOnly Xing4.0 29B A4B (free) 10

  • Frequency penaltyfrequency_penalty
  • Include reasoninginclude_reasoning
  • Minimum probabilitymin_p
  • Presence penaltypresence_penalty
  • Reasoningreasoning
  • Repetition penaltyrepetition_penalty
  • Response formatresponse_format
  • Seedseed
  • Structured outputsstructured_outputs
  • Tool choicetool_choice
6 settings supported by both models
  • Maximum tokensmax_tokens
  • Stop sequencesstop
  • Temperaturetemperature
  • Toolstools
  • Top ktop_k
  • Top ptop_p
Reasoning settingsEffort levels and reasoning behaviour2 different · 0 shared
AUnspecifiedB2 declared fields
SettingANova Premier 1.0BXing4.0 29B A4B (free)
Reasoning requiredUnspecifiedNo
Enabled by defaultUnspecifiedYes
Default settingsValues used when a request leaves a setting open4 different · 0 shared
A3 declared fieldsB3 declared fields
SettingANova Premier 1.0BXing4.0 29B A4B (free)
TemperatureUnspecified1
Top pUnspecified0.95
Frequency penaltyUnspecifiedUnspecified
Repetition penaltyUnspecified1.05

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.