YFarmX logoYFarmX

Kwaipilot: KAT-Coder-Pro V2

kwaipilot/kat-coder-pro-v2 · KwaipilotTokenizer lineage measured
Tokenizer lineage (measured)
Qwen
Entered catalogue
27 March 2026
Last tested
21 August 2026
Evidence confidence
High

Why high: one template-boundary shift from a group whose members all declare the same family.

Evidence
  • ✓ tokenizer signature one template-boundary shift from 6 models

Identity statement

Kwaipilot: KAT-Coder-Pro V2 is Kwaipilot's model. Its measured tokenizer sits with the Qwen group, which is evidence that it builds on the Qwen tokenizer. Tokenizer reuse is normal engineering, open vocabularies travel between labs, and this says nothing against Kwaipilot's authorship of the model itself.

What we checked

Four different kinds of evidence, and what each one showed
We checkedWhat we foundWhere it came from
How it counts tokensCounted cleanly, and no other model in the catalogue counts the same waytk_e60ca14a
How its API is set upA combination of settings no other listing in the catalogue usesapi_f460bcfd
How much it can read and writeReads up to 262,144 tokens at once, writes up to 144,000its own listing
Who served our requestsAtlasCloudwe measured it, 21 August 2026

Shares this fingerprint

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

Closest measured models

Agreement across the mutually clean test strings

Click a row to open the full comparison.

The measured fingerprint

What each test string cost this model, in tokens

We sent Kwaipilot: KAT-Coder-Pro V2 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

English and whitespace

en-prose14
en-long16
spaces-203
spaces-603
tabs-203
newlines-204
mixed-ws5

Digits

digits-99
digits-1212
digits-3030
digits-sep12
float-long22

CJK

zh-common9
zh-long10
zh-rare18
ja-kana7
ja-kanji10
ko13

Other scripts

ru12
ar10
he14
hi20
th12
el13

Emoji

emoji-basic9
emoji-skin30
emoji-zwj-family18
emoji-zwj-x354
emoji-flags24
emoji-prof29

Rare Unicode

math29
boxdraw28
combining5
cjk-ext-b13
surrogates40
zalgo36
rtl-mix6

Code

py-code26
py-indent18
json25
html16
regex44
camel5
snake6

Repetition and encodings

rare-word-x531
repeat-tok22
base6436
hex17
url19
uuid36

Overhead subtracted: 19 prompt tokens.

Declared record

What the catalogue claims about this model

KAT-Coder-Pro V2 is the latest high-performance model in KwaiKAT’s KAT-Coder series, designed for complex enterprise-grade software engineering and SaaS integration. It builds on the agentic coding strengths of earlier versions,...

Modalities
text->text
Declared tokenizer
Other
Prompt price
$0.30 / M tokens
Completion price
$1.20 / M tokens

Supported parameters

frequency_penaltylogit_biasmax_tokensmin_ppresence_penaltyrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_p

defaults: {"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null}

Catalogue entry

History

Every observation, kept as taken
  • 27 March 2026Enters 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 Qwen family, high confidence.

* Kwaipilot: KAT-Coder-Pro V2 no longer appears in the OpenRouter catalogue, first absent from the snapshot of 5 October 2026. The record stays because the measurements above were real when they were taken and this address has been published.