KwaiPilot: KAT-Coder-Exp-72B-1010
This model is no longer available.Add AI to your application with Puter.js.
Explore Other Models
Model Card
KAT-Coder-Exp-72B-1010 is an experimental 72B coding model from Kwaipilot, Kuaishou's AI coding team, released October 10, 2025 as a reinforcement-learning research snapshot of the KAT-Coder line. Kwaipilot published it to show the large-scale agentic RL training behind its production KAT-Coder models.
It scores 74.6% on SWE-Bench Verified under the SWE-agent scaffold, which Kwaipilot reported as the top result among open models at release. The model is built for repository-level software engineering, reading and editing real codebases, resolving GitHub-style issues, and operating inside agent scaffolds over long trajectories.
It supports tool calling, covers more than 20 programming languages, and works with coding agents such as Claude Code and Cline. As an experimental snapshot rather than a production release, it fits low-cost agentic coding experiments and evaluation, while the KAT-Coder-Pro line remains Kwaipilot's production option.
Context Window 256K
tokens
Max Output 33K
tokens
Input Cost $0.1
per million tokens
Output Cost $0.2
per million tokens
Tool Use Yes
Release Date Oct 10, 2025
Code Example
Add AI to your app with the Puter.js AI API — no API keys or setup required.
// npm install @heyputer/puter.js
import { puter } from '@heyputer/puter.js';
puter.ai.chat("Explain quantum computing in simple terms").then(response => {
document.body.innerHTML = response.message.content;
});
<html>
<body>
<script src="https://js.puter.com/v2/"></script>
<script>
puter.ai.chat("Explain quantum computing in simple terms").then(response => {
document.body.innerHTML = response.message.content;
});
</script>
</body>
</html>
More AI Models From KwaiPilot
KAT-Coder-Pro V2.5
KAT-Coder-Pro V2.5 is Kwaipilot's (Kuaishou's AI research division) successor to KAT-Coder-Pro V2, an agentic coding model built on a Mixture-of-Experts architecture with 72B active parameters. It offers a 256K token context window with up to 80K output tokens, and is trained through large-scale agentic reinforcement learning using reconstructed, verifiable repository environments rather than scale alone. On repository-level software engineering benchmarks, KAT-Coder-Pro V2.5 scores 65.2 on SWE-Bench Pro, ranking second only to Opus 4.8 (69.2). It posts the best agentic tool-use result among tested models on PinchBench (94.9), reflecting strength in long-horizon, multi-step tasks. The model is designed to take on an entire issue or business workflow autonomously, locating problems, making changes, and completing tasks inside real repositories. It also has a lighter sibling variant, KAT-Coder-Air V2.5, for lower-cost workloads.
ChatKAT-Coder-Air V2.5
KAT-Coder-Air V2.5 is a coding-focused agentic model from Kwaipilot (Kuaishou's AI research division), released July 10, 2026 as the faster, lower-cost sibling to KAT-Coder-Pro V2.5. It shares Pro's 256K context window and 80K max output tokens, priced at $0.15 per 1M input tokens and $0.60 per 1M output tokens, roughly a fifth of Pro's $0.74/$2.96 rates. The model is built for agent and tool-use workflows inside real, executable repositories, handling issue localization, code modification, and test execution as part of an end-to-end development loop. Kwaipilot designed it for interactive development and rapid iteration rather than single-shot generation, with integration into toolchains such as Claude Code and OpenHands. It supports function calling, tool use, structured JSON output, and prompt caching. KAT-Coder-Air V2.5 targets teams running high-volume coding agents and workflow automation where speed and cost per request matter, while KAT-Coder-Pro V2.5 remains Kwaipilot's higher-capability option for complex software engineering tasks.
ChatKAT-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.
Frequently Asked Questions
KAT-Coder-Exp-72B-1010 is no longer available through Puter.js. Explore other AI models for alternatives.
| Price per 1M tokens | |
|---|---|
| Input | $0.1 |
| Output | $0.2 |
KAT-Coder-Exp-72B-1010 was created by KwaiPilot and released on Oct 10, 2025.
KAT-Coder-Exp-72B-1010 supports a context window of 256K tokens. For reference, that is roughly equivalent to 512 pages of text.
KAT-Coder-Exp-72B-1010 can generate up to 33K tokens in a single response.
Yes, KAT-Coder-Exp-72B-1010 supports tool use (function calling), allowing it to interact with external tools, APIs, and data sources as part of its response flow.
Yes — the KAT-Coder-Exp-72B-1010 API works with any JavaScript framework, Node.js, or plain HTML through Puter.js. Just include the library and start building. See the documentation for more details.
Get started with Puter.js
Add AI to your application without worrying about API keys or setup.
Explore Models View Tutorials