modelbenchmark.io

kat-coder-pro

kat-coder-pro

Compare

KAT-Coder-Pro V2 by KwaiKAT is a non-reasoning model optimized for agentic coding. It delivers strong performance on reasoning-style tasks while requiring significantly fewer output tokens than peer models. With the 1210 release, it achieved a score of 64 on the Artificial Analysis Intelligence Index, placing it in the global Top 10 and ranking first among all non-reasoning models.

Specification

most-agreed values

Context
256K
Max output
256K
Released
2026-03-27
Knowledge cutoff
—
Retires
—
Open weights
no
Input
text
Output
text

Price

US dollars per million tokens · most-agreed

Input
$0.30
Output
$1.20
Cache read
$0.06

Available from 2 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
novita$0.30$1.20$0.06—256K128K—
requesty$0.30$1.20——256K256K—

Price history

append-only observations · a listing writes a row only when its price moves

DateHostField$/M
2026-09-19openrouterCache read$0.06
2026-09-23openrouterCache read$0.15
2026-09-19openrouterInput$0.30
2026-09-23openrouterInput$0.74
2026-09-19openrouterOutput$1.20
2026-09-23openrouterOutput$2.96