YFarmX logoYFarmXIntelligence for an accelerating worldBriefings
YFarmX logoYFarmX
YFarmX

AI Desk · AI Fingerprinting · Compare

Anthropic: Claude 3 Haiku · Anthropic: Claude Fable 5.1

Identity similarity: lowDivergent fingerprints · 15/49These models tokenise differently. The rows that part here are the English prose, whitespace, digit, CJK, emoji and non-Latin script strings. Divergence on high-information strings separates unrelated vocabularies within a handful of samples.

Anthropic: Claude 3 Haiku recordAnthropic: Claude Fable 5.1 recordOpen in the interactive bench

View all 50 test strings15 matched · 34 different · 1 excluded

String-by-string results

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

15 of 49 clean strings agree

Showing all 50 strings.

Test stringAnthropic: Claude 3 HaikuAnthropic: Claude Fable 5.1Result
English sentenceen-prose
Exact text
The quick brown fox jumps over the lazy dog near the riverbank.
1524≠ Different
Long English sentenceen-long
Exact text
Attribution of a stealth model requires evidence that the model cannot choose to withhold.
1728≠ Different
20 spacesspaces-20
Exact text
a                    b
Show whitespace marks

· = space, ⇥ = tab, ↵ = line break

a····················b
44✓ Matched
60 spacesspaces-60
Exact text
a                                                            b
Show whitespace marks

· = space, ⇥ = tab, ↵ = line break

a····························································b
66✓ Matched
20 tabstabs-20
Exact text
a																				b
Show whitespace marks

· = space, ⇥ = tab, ↵ = line break

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



















b
Show whitespace marks

· = space, ⇥ = tab, ↵ = line break

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

· = space, ⇥ = tab, ↵ = line break

a·⇥↵
··⇥↵
···b
99✓ Matched
9 digitsdigits-9
Exact text
123456789
43≠ Different
12 digitsdigits-12
Exact text
123456789012
54≠ Different
30 repeated digitsdigits-30
Exact text
111111111111111111111111111111
1110≠ Different
Formatted numberdigits-sep
Exact text
1,234,567.89
87≠ Different
Long decimalfloat-long
Exact text
3.14159265358979323846
109≠ Different
Chinese sentencezh-common
Exact text
这是一个用于测试分词器行为的中文句子
1918≠ 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
2524≠ Different
Rare Chinese characterszh-rare
Exact text
龘齉齾爩鱻麤靐飝鞻
2120≠ Different
Japanese kanaja-kana
Exact text
これはトークナイザーのテストです
1212✓ Matched
Japanese kanjija-kanji
Exact text
日本語の漢字と仮名の混在文章
1716≠ Different
Koreanko
Exact text
한국어 토크나이저 테스트 문장입니다
2019≠ Different
Russianru
Exact text
Проверка токенизатора на кириллице
1414✓ Matched
Arabicar
Exact text
اختبار المحلل اللغوي للنصوص العربية
2121✓ Matched
Hebrewhe
Exact text
בדיקת מנתח אסימונים בעברית
1818✓ Matched
Hindihi
Exact text
यह टोकनाइज़र परीक्षण वाक्य है
2323✓ Matched
Thaith
Exact text
นี่คือประโยคทดสอบตัวแบ่งคำ
2525✓ Matched
Greekel
Exact text
Δοκιμή του τμηματοποιητή κειμένου
2222✓ Matched
Basic emojiemoji-basic
Exact text
😀😃😄😁😆
1110≠ Different
Emoji skin tonesemoji-skin
Exact text
👍🏻👍🏼👍🏽👍🏾👍🏿
2625≠ Different
Joined family emojiemoji-zwj-family
Exact text
👨‍👩‍👧‍👦
1514≠ Different
Repeated family emojiemoji-zwj-x3
Exact text
👨‍👩‍👧‍👦👨‍👩‍👧‍👦👨‍👩‍👧‍👦
4342≠ Different
Flag emojiemoji-flags
Exact text
🇬🇧🇺🇸🇨🇳🇯🇵
2524≠ Different
Profession emojiemoji-prof
Exact text
👩🏽‍💻👨🏿‍🚀🧑‍🔬
2827≠ Different
Mathematical symbolsmath
Exact text
∀x∈ℝ ∃y∈ℚ : x⊕y ≡ ∅ ∧ ∇²φ = 0
4746≠ Different
Box-drawing charactersboxdraw
Exact text
┌─┬─┐│├┼┤└┴┘╔═╗╚╝
2928≠ Different
Combining accentscombining
Exact text
áêĩōü
66✓ Matched
Extended Chinese characterscjk-ext-b
Exact text
𠀀𠀁𠀂𪛖
1716≠ Different
Styled Unicode letterssurrogates
Exact text
𝕳𝖊𝖑𝖑𝖔 𝓦𝓸𝓻𝓵𝓭 𝟙𝟚𝟛
5554≠ Different
Layered combining markszalgo
Exact text
h̸̢̛e̵̛�݃l̷̨͐l̸̛͝o̶̧͝
3636✓ Matched
Mixed writing directionsrtl-mix
Exact text
hello שלום world مرحبا
1011≠ 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]
3030✓ Matched
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
1919✓ Matched
JSON objectjson
Exact text
{"model":"ox-alpha","context_length":1048576,"top_p":0.95}
2329≠ Different
HTML markuphtml
Exact text
<div class="row"><span id="a">x</span></div>
1718≠ Different
Regular expressionregex
Exact text
^(?:[a-z0-9!#$%&*+/=?^_`{|}~-]+)@(?:[a-z0-9](?:[a-z0-9-]*)?\.)+$
5263≠ Different
Camel-case identifiercamel
Exact text
getUserAccountBalanceByIdentifier
716≠ Different
Snake-case identifiersnake
Exact text
get_user_account_balance_by_identifier
1114≠ Different
Repeated long wordrare-word-x5
Exact text
antidisestablishmentarianism antidisestablishmentarianism antidisestablishmentarianism antidisestablishmentarianism antidisestablishmentarianism
4155≠ 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
2160≠ Different
Base64 textbase64
Exact text
SGVsbG8gV29ybGQhIFRoaXMgaXMgYSB0ZXN0IHN0cmluZy4=
43ExcludedExcluded
Hexadecimal texthex
Exact text
deadbeefcafebabe0123456789abcdef
1418≠ Different
URL texturl
Exact text
https://openrouter.ai/api/v1/models?limit=100&offset=0
2226≠ Different
UUIDuuid
Exact text
3f2504e0-4f89-11d3-9a0c-0305e82c3301
2827≠ 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.

AAnthropic: Claude 3 Haiku
BAnthropic: Claude Fable 5.1

Context window

Different

Total token capacity per request

A200,000 tokens
B1,000,000 tokens

Maximum reply

Different

Published output limit in tokens

A4,096 tokens
B128,000 tokens

Input price

Different

US dollars per 1 million input tokens

AUS$0.25 / 1M tokens
BUS$10.00 / 1M tokens

Output price

Different

US dollars per 1 million output tokens

AUS$1.25 / 1M tokens
BUS$50.00 / 1M tokens

What you can send and receive

Different

AClaude 3 Haiku

Accepts
textimage
Produces
text

BClaude Fable 5.1

Accepts
textimagefile
Produces
text

Developer settings

Open a section to compare the complete declarations.

Supported API settingsShared controls and the settings unique to each model4 shared · 10 model-specific

AOnly Claude 3 Haiku 3

  • Temperaturetemperature
  • Top ktop_k
  • Top ptop_p

BOnly Claude Fable 5.1 7

  • Include reasoninginclude_reasoning
  • Maximum completion tokensmax_completion_tokens
  • Reasoningreasoning
  • Reasoning effortreasoning_effort
  • Response formatresponse_format
  • Structured outputsstructured_outputs
  • Verbosityverbosity
4 settings supported by both models
  • Maximum tokensmax_tokens
  • Stop sequencesstop
  • Tool choicetool_choice
  • Toolstools
Reasoning settingsEffort levels and reasoning behaviour3 different · 0 shared
AUnspecifiedB3 declared fields
SettingAClaude 3 HaikuBClaude Fable 5.1
Reasoning requiredUnspecifiedYes
Effort levelsUnspecifiedmaxxhighhighmediumlow
Default effortUnspecifiedhigh
Default settingsValues used when a request leaves a setting openDeclarations available below
ANo values declaredBNo values declared

Both models’ declarations are shown above.

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.