KwaiPilot API
Access KwaiPilot instantly with Puter.js, and add AI to any app in a few lines of code without backend or API keys.
// npm install @heyputer/puter.js
import { puter } from '@heyputer/puter.js';
puter.ai.chat("Explain AI like I'm five!", {
model: "kwaipilot/kat-coder-pro-v2"
}).then(response => {
console.log(response);
});
<html>
<body>
<script src="https://js.puter.com/v2/"></script>
<script>
puter.ai.chat("Explain AI like I'm five!", {
model: "kwaipilot/kat-coder-pro-v2"
}).then(response => {
console.log(response);
});
</script>
</body>
</html>
List of KwaiPilot Models
KAT-Coder-Pro V2
kwaipilot/kat-coder-pro-v2
KAT-Coder-Pro V2 is the flagship agentic coding model from Kwaipilot (Kuaishou's AI research division), built for enterprise-grade software engineering and SaaS integration. It uses a Mixture-of-Experts architecture with 72B active parameters and offers a 256K token context window. The model achieves a 79.6% solve rate on SWE-Bench Verified, placing it among the top code generation models globally. It scores 44 on the Artificial Analysis Intelligence Index, well above the median of 15 for comparable non-reasoning models in its price tier, and generates output at roughly 109 tokens per second. KAT-Coder-Pro V2 is designed for large-scale production environments, multi-system coordination, and agentic coding workflows. It also supports tool use, function calling, and web aesthetics generation for producing landing pages and presentation decks.
ChatKAT-Coder-Pro V1
kwaipilot/kat-coder-pro
KAT-Coder-Pro V1 is KwaiKAT's most advanced agentic coding model, built by Kuaishou's Kwaipilot team and designed specifically for real-world software engineering tasks. It achieves a 73.4% solve rate on SWE-Bench Verified, reflecting strong performance on practical code generation and bug-fixing scenarios. The model has been optimized for tool-use capability, multi-turn interaction, and instruction following through a multi-stage training pipeline that includes supervised fine-tuning, reinforcement fine-tuning, and agentic RL. KAT-Coder-Pro V1 supports multi-tool parallel invocation, enabling it to complete complex agentic workflows with fewer interaction rounds. It offers a 256K-token context window and up to 128K output tokens. It's a text-only, non-reasoning model — so expect direct responses without chain-of-thought overhead, well-suited for coding agents and automated engineering pipelines.
Frequently Asked Questions
The KwaiPilot API gives you access to models for AI chat. Through Puter.js, you can start using KwaiPilot models instantly with zero setup or configuration.
Puter.js supports a variety of KwaiPilot models, including KAT-Coder-Pro V2 and KAT-Coder-Pro V1. Find all AI models supported by Puter.js in the AI model list.
With the User-Pays model, users cover their own AI costs through their Puter account. This means you can build apps without worrying about infrastructure expenses.
Puter.js is a JavaScript library that provides access to AI, storage, and other cloud services directly from a single API. It handles authentication, infrastructure, and scaling so you can focus on building your app.
Yes — the KwaiPilot API through Puter.js works with any JavaScript framework, Node.js, or plain HTML. Just include the library and start building. See the documentation for more details.