kwaipilot/kat-coder-pro-v2

LLM

PRO

KAT Coder Pro V2 API by Kwai

kwaipilot/kat-coder-pro-v2

Kat-coder-pro-v2

KAT Coder Pro is KwaiKAT's most advanced agentic coding model in the KAT-Coder series. Designed specifically for agentic coding tasks, it excels in real-world software engineering scenarios, achieving 73.4% solve rate on the SWE-Bench Verified benchmark.

Parameters

Code Example
import os
from openai import OpenAI

client = OpenAI(
    api_key=os.getenv("ATLASCLOUD_API_KEY"),
    base_url="https://api.atlascloud.ai/v1"
)

response = client.chat.completions.create(
    model="kwaipilot/kat-coder-pro-v2",
    messages=[
    {
        "role": "user",
        "content": "hello"
    }
],
    max_tokens=1024,
    temperature=0.7
)

print(response.choices[0].message.content)

Install

Install the required package for your language.

pip install requests

Authentication

All API requests require authentication via an API key. You can get your API key from the Atlas Cloud dashboard.

export ATLASCLOUD_API_KEY="your-api-key-here"

HTTP Headers

import os

API_KEY = os.environ.get("ATLASCLOUD_API_KEY")
headers = {
    "Content-Type": "application/json",
    "Authorization": f"Bearer {API_KEY}"
}

Keep your API key secure

Never expose your API key in client-side code or public repositories. Use environment variables or a backend proxy instead.

Submit a request

import requests

url = "https://api.atlascloud.ai/v1/chat/completions"
headers = {
    "Content-Type": "application/json",
    "Authorization": "Bearer $ATLASCLOUD_API_KEY"
}
data = {
    "model": "your-model",
    "messages": [{"role": "user", "content": "Hello"}],
    "max_tokens": 1024
}

response = requests.post(url, headers=headers, json=data)
print(response.json())

Input Schema

The following parameters are accepted in the request body.

Total: 9Required: 2Optional: 7

modelstringrequired

The model ID to use for the completion.

Example: "kwaipilot/kat-coder-pro-v2"

messagesarray[object]required

A list of messages comprising the conversation so far.

rolestringrequired

The role of the message author. One of "system", "user", or "assistant".

systemuserassistant

contentstringrequired

The content of the message.

max_tokensinteger

The maximum number of tokens to generate in the completion.

Default: 1024Min: 1

temperaturenumber

Sampling temperature between 0 and 2. Higher values make output more random, lower values more focused and deterministic.

Default: 0.7Min: 0Max: 2

top_pnumber

Nucleus sampling parameter. The model considers the tokens with top_p probability mass.

Default: 1Min: 0Max: 1

streamboolean

If set to true, partial message deltas will be sent as server-sent events.

Default: false

stoparray[string]

Up to 4 sequences where the API will stop generating further tokens.

frequency_penaltynumber

Penalizes new tokens based on their existing frequency in the text so far. Between -2.0 and 2.0.

Default: 0Min: -2Max: 2

presence_penaltynumber

Penalizes new tokens based on whether they appear in the text so far. Between -2.0 and 2.0.

Default: 0Min: -2Max: 2

Example Request Body

{
  "model": "kwaipilot/kat-coder-pro-v2",
  "messages": [
    {
      "role": "user",
      "content": "Hello"
    }
  ],
  "max_tokens": 1024,
  "temperature": 0.7,
  "stream": false
}

Output Schema

The API returns a ChatCompletion-compatible response.

idstringrequired

Unique identifier for the completion.

objectstringrequired

Object type, always "chat.completion".

Default: "chat.completion"

createdintegerrequired

Unix timestamp of when the completion was created.

modelstringrequired

The model used for the completion.

choicesarray[object]required

List of completion choices.

indexintegerrequired

Index of the choice.

messageobjectrequired

The generated message.

finish_reasonstringrequired

The reason generation stopped.

stoplengthcontent_filter

usageobjectrequired

Token usage statistics.

prompt_tokensintegerrequired

Number of tokens in the prompt.

completion_tokensintegerrequired

Number of tokens in the completion.

total_tokensintegerrequired

Total tokens used.

Example Response

{
  "id": "chatcmpl-abc123",
  "object": "chat.completion",
  "created": 1700000000,
  "model": "model-name",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Hello! How can I assist you today?"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 10,
    "completion_tokens": 20,
    "total_tokens": 30
  }
}

Atlas Cloud Skills

Atlas Cloud Skills integrates 300+ AI models directly into your AI coding assistant. One command to install, then use natural language to generate images, videos, and chat with LLMs.

Supported Clients

Claude Code

OpenAI Codex

Gemini CLI

Cursor

Windsurf

VS Code

Trae

GitHub Copilot

Cline

Roo Code

Amp

Goose

Replit

40+ supported clients

Install

npx skills add AtlasCloudAI/atlas-cloud-skills

Setup API Key

Get your API key from the Atlas Cloud dashboard and set it as an environment variable.

export ATLASCLOUD_API_KEY="your-api-key-here"

Capabilities

Once installed, you can use natural language in your AI assistant to access all Atlas Cloud models.

Image GenerationGenerate images with models like Nano Banana 2, Z-Image, and more.

Video CreationCreate videos from text or images with Kling, Vidu, Veo, etc.

LLM ChatChat with Qwen, DeepSeek, and other large language models.

Media UploadUpload local files for image editing and image-to-video workflows.

Learn more

github.com/AtlasCloudAI/atlas-cloud-skills

MCP Server

Atlas Cloud MCP Server connects your IDE with 300+ AI models via the Model Context Protocol. Works with any MCP-compatible client.

Supported Clients

Cursor

VS Code

Windsurf

Claude Code

OpenAI Codex

Gemini CLI

Cline

Roo Code

100+ supported clients

Install

npx -y atlascloud-mcp

Configuration

Add the following configuration to your IDE's MCP settings file.

{
  "mcpServers": {
    "atlascloud": {
      "command": "npx",
      "args": [
        "-y",
        "atlascloud-mcp"
      ],
      "env": {
        "ATLASCLOUD_API_KEY": "your-api-key-here"
      }
    }
  }
}

Available Tools

atlas_generate_imageGenerate images from text prompts.

atlas_generate_videoCreate videos from text or images.

atlas_chatChat with large language models.

atlas_list_modelsBrowse 300+ available AI models.

atlas_quick_generateOne-step content creation with auto model selection.

atlas_upload_mediaUpload local files for API workflows.

Learn more

github.com/AtlasCloudAI/mcp-server

Elite AI Coding

KAT-Coder: Elite AI Code Generation

73.4% SWE-Bench Verified - Surpassing Industry Leaders

KAT-Coder is the flagship closed-source AI coding model by Kwaipilot (Kuaishou's AI research division), representing the pinnacle of agentic code generation technology. Powered by a Mixture-of-Experts architecture with 72B active parameters and trained through large-scale agentic reinforcement learning, KAT-Coder achieves a 73.4% score on SWE-Bench Verified, ranking among the best code generation models globally alongside GPT-5 High and Claude Sonnet 4.5.

73.4%

SWE-Bench Verified

256K

Context Window

72B

Active Parameters

Industry-Leading Performance

KAT-Coder competes with the world's best code generation models on SWE-Bench Verified, the industry standard benchmark for real-world software engineering tasks

🥇

Claude Sonnet 4.5

77.2%

🥈

GPT-5 High

74.9%

🥉

KAT-Coder Pro

73.4%

* Based on SWE-Bench Verified benchmark scores. Performance may vary across different code generation tasks.

Core Capabilities

Mixture-of-Experts Architecture

Leverages advanced MoE design with 72B active parameters out of over 1 trillion total, delivering state-of-the-art performance on complex software engineering tasks.

72B active parameters for optimal efficiency
Built on Qwen model family foundation
Optimized for enterprise-scale codebases

Agentic Reinforcement Learning

Trained through multi-stage pipeline including large-scale agentic RL, enabling autonomous completion of complex software engineering tasks.

Shared prefix trajectory optimization
Entropy shaping advantage mechanism
Training on real Git commits and PRs

Multi-Tool Integration

Built-in capabilities for interacting with thousands of tools through real sandbox execution data, enabling practical software development workflows.

Interaction data from thousands of tools
Real execution in sandbox environments
Seamless API and CLI integration

256K Context Window

Extensive context support enables handling sophisticated multi-turn coding interactions and managing large-scale codebases effectively.

Handle multiple files simultaneously
Maintain long conversational history
Cross-file reasoning and refactoring

Git-Native Training

Trained on real Git commit and PR data from enterprise repositories, understanding version control workflows natively.

Real repository commit patterns
Pull request best practices
Code review and collaboration patterns

Enterprise-Grade Quality

High-quality domain-specific data including instruction following across 30+ categories and general reasoning capabilities.

30+ instruction following categories
Advanced reasoning for edge cases
Production-ready code generation

Multi-Stage Training Pipeline

KAT-Coder's training methodology represents a significant advancement in AI coding models, combining multiple training stages for optimal performance

Mid-Training

Foundation stage with coding knowledge injection and high-quality domain-specific data

→

Supervised Fine-Tuning (SFT)

Instruction following and dialogue training across 30+ categories

→

Reinforcement Fine-Tuning (RFT)

Enhanced reasoning and problem-solving capabilities

→

Agentic Reinforcement Learning

Large-scale RL on enterprise codebases with autonomous task completion

Perfect For

🐛

Complex Debugging

Identify and fix bugs across large codebases with multi-file context understanding

🔧

Large Codebase Refactoring

Systematic refactoring with awareness of architectural patterns and dependencies

📝

Multi-File Code Generation

Generate coherent code across multiple files with proper integration

📚

Repository Understanding

Analyze and comprehend large repositories with deep architectural insights

Technical Specifications

architectureMixture-of-Experts (MoE)

active_parameters~72 Billion

total_parameters>1 Trillion

context_window256,000 tokens

base_modelQwen Family

tool_useThousands of tools

multi_turn_dialogueHundreds of turns

instruction_categories30+ categories

licenseClosed-source (Commercial)

open_source_variantsKAT-Dev-32B, KAT-Dev-72B-Exp

Open-Source Variants

While KAT-Coder Pro is closed-source, Kwaipilot has released open-source alternatives available on HuggingFace under Apache-2.0 license

KAT-Dev-32B

Open Source

Optimized 32B parameter variant with multi-stage training including supervised fine-tuning and reinforcement learning.

Apache-2.0 license for commercial use

Available on HuggingFace

Production-ready performance

KAT-Dev-72B-Exp

Experimental

Experimental 72B parameter variant pushing the boundaries of open-source code generation capabilities.

Larger model for complex tasks

Advanced reasoning capabilities

Research and production use

Experience Elite Code Generation

Start using KAT-Coder today through our API. Join developers worldwide who trust KAT-Coder for mission-critical software engineering tasks.

Industry-leading 73.4% SWE-Bench score

256K context for large codebases

Multi-tool integration support

Explore Similar Models

NEW

HOT

DeepSeek V4 Pro is a state-of-the-art large language model combining efficient sparse attention, strong reasoning, and integrated agent capabilities for robust long-context understanding and versatile AI applications.

LLM

PRO

DeepSeek V4 Pro

Output:$3.38/M tokens

DeepSeek V4 Flash is a state-of-the-art large language model combining efficient sparse attention, strong reasoning, and integrated agent capabilities for robust long-context understanding and versatile AI applications.

LLM

DeepSeek V4 Flash

Output:$0.28/M tokens

Max Output:393.22K

$0.14/0.28M in/out

NEW

No description available.

LLM

OWL

Kimi K2.6 is an advanced large language model with strong reasoning and upgraded native multimodality. It natively understands and processes text and images, delivering more accurate analysis, better instruction following, and stable performance across complex tasks. Designed for production use, Kimi K2.6 is ideal for AI assistants, enterprise applications, and multimodal workflows that require reliable and high-quality outputs.

LLM

Kimi K2.6

Start From 300+ Models,

Explore all models

KAT Coder Pro V2 API by Kwai

Parameters

Code Example

Install

Authentication

HTTP Headers

Submit a request

Input Schema

Example Request Body

Output Schema

Example Response

Atlas Cloud Skills

Supported Clients

Install

Setup API Key

Capabilities

MCP Server

Supported Clients

Install

Configuration

Available Tools

KAT-Coder: Elite AI Code Generation

Industry-Leading Performance

Core Capabilities

Mixture-of-Experts Architecture

Agentic Reinforcement Learning

Multi-Tool Integration

256K Context Window

Git-Native Training

Enterprise-Grade Quality

Multi-Stage Training Pipeline

Mid-Training

Supervised Fine-Tuning (SFT)

Reinforcement Fine-Tuning (RFT)

Agentic Reinforcement Learning

Perfect For

Complex Debugging

Large Codebase Refactoring

Multi-File Code Generation

Repository Understanding

Technical Specifications

Open-Source Variants

KAT-Dev-32B

KAT-Dev-72B-Exp

Experience Elite Code Generation

Explore Similar Models

DeepSeek V4 Pro

DeepSeek V4 Flash

OWL

Kimi K2.6

Start From 300+ Models,

Join our Discord community

Parameters

Code Example

Install

Authentication

HTTP Headers

Submit a request

Input Schema

Example Request Body

Output Schema

Example Response

Atlas Cloud Skills

Supported Clients

Install

Setup API Key

Capabilities

MCP Server

Supported Clients

Install

Configuration

Available Tools