LLM Pricing
PricingLeaderboardsToolsProvidersReleasesGuides

© 2026 LLM Pricing

About
·Contact
·Privacy
·RSS
← Model list
ku

KAT-Coder-Pro-V2

kuaishou·kuaishou/kat-coder-pro-v2·GA·Closed
Coding model for repository understanding, refactors, and agentic engineering tasks

KAT-Coder-Pro-V2 by kuaishou is currently listed from a single provider. Its reference price is $0.30 per 1M input tokens and $1.20 per 1M output tokens.

Artificial Analysis rates it 21.7 on the Intelligence Index, with 59.5 for coding. Against its lowest blended price of $0.525 per 1M, that is roughly 41 index points per dollar, which is the value ratio the leaderboards rank on.

The context window is 256,000 tokens, with an output limit of 80,000 tokens. It supports tool use.

Specs & pricing

Input / output per 1M tokens
Reference price·ZenMux
$0.30 / $1.20
Blended $0.53 · Cache read $0.06
Lowest paid·ZenMuxGateway
$0.30 / $1.20
Blended $0.53
Context
256,000
Output limit
80,000
Knowledge cutoff
—
Released / updated
2026-03-30 / 2026-03-30
Capabilities
Reasoning✓ Tool use? Structured output✓ TemperatureAttachments
Modalities
Text

Quality & performanceArtificial Analysis · Intelligence Index v4.3

Intelligence21.7
Value41
Coding59.5
Agentic—
Output speed—
TTFT—
Value formulaIQ 21.7 ÷ min blended $0.525 = 41

Quality is independently evaluated by Artificial Analysis. Speed/latency are model-level medians.

Available at 1 providers1 with public prices

ProviderTierInputOutputCache readCache writeContextOutput limitStatus
ZenMuxGateway$0.30$1.20$0.06—256,00080,000

Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.

Your usage cost

1ZenMux$91.20
The cheapest paid channel is the only channel.

Price historyone sample accumulated per data sync

Input list $0.30Output list $1.20Min blended $0.53

Price history accumulates from each data sync; currently only 1 sample(s) (2026-09-23). Each future sync adds a point, and once accumulated a line is drawn here.

Artificial Analysis evaluations8 items

GPQA Diamond85.5%
Humanity's Last Exam16.1%
Terminal-Bench Hard49.2%
Terminal-Bench 2.170.0%
τ²-Bench Telecom89.5%
τ³-Bench Banking4.5%
AA-LCR73.0%
IFBench66.7%

Individual evaluations run by Artificial Analysis, on the same reasoning tier as the intelligence score above. Each benchmark has its own task set and harness, so rows are not comparable with one another. The Intelligence Index above draws on a different, newer set of evaluations.

Related models

Qwen3-Next 80B-A3B Instructcheaper alternative$0.14 / $0.57Llama-3.1-8B-Instructcheaper alternative$0.15 / $0.45Qwen3 Coder Flashcheaper alternative$0.14 / $0.57Gemma 3 12B ITcheaper alternative$0.27 / $0.27
Data partly from models.dev (MIT) · ZenMux official docs ↗