AI Desk · AI FingerprintingNew arrival

ScaleDown: Summarize

scaledown/summarize · ScaleDownUnmeasurable

Declared family: Unknown
Entered catalogue: 13 October 2026
Last tested: 17 October 2026
Measurement: Unmeasurable: prompt caching corrupts its token accounting
Evidence confidence: Unknown

Compare with Qwen: Qwen3.8 27B

Report a correction

What we checked

Four different kinds of evidence, and what each one showed

We checked	What we found	Where it came from
How it counts tokens	Not measured yet	we measured it
How its API is set up	A combination of settings no other listing in the catalogue uses	api_06c08ce5
How much it can read and write	Reads up to 1,000,000 tokens at once, writes up to 4,000	its own listing
Who served our requests	ScaleDown	we measured it, 17 October 2026

Closest measured models

Agreement across the mutually clean test strings

Qwen: Qwen3.8 27Bqwen/qwen3.8-27b39/39 · 100%Kwaipilot: KAT-Coder-Air V2.5kwaipilot/kat-coder-air-v2.539/39 · 100%Qwen: Qwen3.6 35B A3Bqwen/qwen3.6-35b-a3b39/39 · 100%Qwen: Qwen3.6 27Bqwen/qwen3.6-27b39/39 · 100%Apodex: Apodex 1.1 Mini (free)apodex/apodex-1.1-mini:free39/39 · 100%Nex AGI: Nex-N2.5-Pronex-agi/nex-n2.5-pro39/39 · 100%

Click a row to open the full comparison.

The measured fingerprint

What each test string cost this model, in tokens

We sent ScaleDown: Summarize fifty short pieces of text and recorded what each one cost it in tokens. The bars below are those costs. Two models built on the same tokenizer produce the same bars; a model built on a different one produces a different set, which is what makes this a fingerprint.

All 50 rows, 11 excluded as corrupt

English and whitespace

en-prose14

en-long16

spaces-203

spaces-603

tabs-203

newlines-204

mixed-wsx

Digits

digits-99

digits-1212

digits-3030

digits-sep12

float-long22

CJK

zh-common9

zh-long10

zh-rarex

ja-kana7

ja-kanji10

ko13

Other scripts

ru12

ar10

he14

hi20

th12

el13

Emoji

emoji-basicx

emoji-skinx

emoji-zwj-familyx

emoji-zwj-x3x

emoji-flagsx

emoji-profx

Rare Unicode

mathx

boxdrawx

combining5

cjk-ext-bx

surrogates40

zalgo36

rtl-mix6

Code

py-code26

py-indent18

json25

html16

regex44

camel5

snake6

Repetition and encodings

rare-word-x530

repeat-tok21

base6436

hex17

url19

uuid36

An x marks a row excluded as corrupt (caching or provider interference detected during measurement). Overhead subtracted: 117 prompt tokens.

Declared record

What the catalogue claims about this model

Summarize is an abstractive summarization model from ScaleDown. It condenses long text and documents into a fluent, faithful rewrite rather than lifting sentences from the source, and is suited for...

Modalities: text+image+file->text
Declared tokenizer: Other
Prompt price: $0.04 / M tokens
Completion price: $0 / M tokens

Supported parameters

max_tokens

Default settings

No values declared

Catalogue entry

History

Every observation, kept as taken

13 October 2026Enters the OpenRouter catalogue with no declared family.
17 October 2026Fingerprinted in the YFarmX catalogue sweep · 39 of 50 strings measured clean.