LLM Reference

KAT Coder Pro V2

Released
2026-03-27
Last refreshed
2026-05-22
Status
Researched 20d ago
ProprietaryCommercial use with conditionsCodingRAGAgentsLong contextClassificationJSON / Tool use

KAT Coder Pro V2 is worth evaluating for coding, rag, and agents when its provider route and context window match the workload.

Use it for

  • Teams evaluating coding, rag, and agents
  • Workloads that can use a 256k context window
  • Buyers comparing 3 tracked provider routes

Do not use it for

  • Vision or document-understanding workloads
Specifications
Family
KAT
Released
2026-03-27
Context
256k
Architecture
Decoder Only
Specialization
code
Openness
Proprietary
License
ProprietaryCommercial use with conditions
Training
pretrained
Created by

Kuaishou's AI coding division behind the KAT model family

Beijing, China
Website
Pricing
Output / 1M
$1.20
Input / 1M
$0.300

Cheapest of 3 routes · Novita AI

About

KAT-Coder-Pro V2 is Kwaipilot's flagship agentic coding model, achieving 79.6% on SWE-Bench Verified (March 2026). Designed for complex enterprise software engineering tasks, multi-system coordination, and SaaS integration. Uses a 'Specialize-then-Unify' training paradigm with five specialized expert domains. Context: 256K tokens. Max output: 256K tokens (on Streamlake endpoint). Available via Vercel AI Gateway and OpenRouter.

KAT Coder Pro V2 is a proprietary model in the KAT family. The structured metadata tracks a 256k-token context window, function calling, tool use, structured outputs, and code execution. This page tracks provider routes through OpenRouter, Vercel AI Gateway, and Novita AI, with the cheapest tracked route listed at $0.3 input and $1.2 output per 1M tokens. No headline benchmark score is tracked for KAT Coder Pro V2 yet.

Top use-case fit: coding, agents, and build tasks

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

Compare all 3

Compare API pricing across 3 providers for input and output tokens, batch, and cached reads when available.

ProviderInput / 1MOutput / 1MCacheRoute
Novita AI$0.300$1.20-
Serverless
OpenRouter$0.300$1.20-
Serverless
Vercel AI Gateway$0.300$1.20read $0.060
Serverless

Capabilities

Function CallingTool UseStructured OutputsCode Execution

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.