LLM Reference

KAT Coder Pro V1

kat-coder-pro-v1

Researched today

Last refreshed 2026-05-22. Next refresh: weekly.

ProprietaryCodingRAGAgentsLong contextJSON / Tool use

KAT Coder Pro V1 is worth evaluating for coding, rag, and agents when its provider route and context window match the workload.

Decision context: Coding task fit, 1 tracked provider route, and research from 2026-05-22.

Use it for

  • Teams evaluating coding, rag, and agents
  • Workloads that can use a 256K context window
  • Buyers comparing 1 tracked provider route

Do not use it for

  • Vision or document-understanding workloads

Cheapest output

$1.20

Vercel AI Gateway per 1M tokens

Provider routes

1

Tracked API hosts

Quality / dollar

Unknown

No task benchmark coverage yet

Freshness

2026-05-22

Researched today

fresh

Top use-case fit

Coding

Included by capability and metadata signals in the decision map.

RAG

Included by capability and metadata signals in the decision map.

Agents

Included by capability and metadata signals in the decision map.

Provider price ladder

ProviderInput / 1MOutput / 1MCacheRoute
Vercel AI Gateway$0.030$1.20read $0.060
Serverless

Benchmark peer barsfor Coding

No task-mapped benchmark peers are available for this model yet.

Migration checks

No linked migration route is available for this model yet.

About

KAT-Coder-Pro V1 is Kwaipilot's first high-performance agentic coding model, achieving 73.4% on SWE-Bench Verified. It uses a Mixture-of-Experts architecture with approximately 72B active parameters. Context: 256K tokens. Proprietary, available via Vercel AI Gateway and OpenRouter.

KAT Coder Pro V1 has a 256K-token context window.

KAT Coder Pro V1 input tokens at $0.03/1M, output at $1.2/1M.

Capabilities

Function CallingTool Use

Rankings

Specifications

FamilyKAT
Released2025-09-01
Context256K
ArchitectureDecoder Only
Specializationcode
LicenseProprietary

Created by

Kuaishou's AI coding division behind the KAT model family

Beijing, China
Website

Providers(1)