SkyClaw-v1.0 is a high-performance agent model by Skywork AI, optimized for complex tool use, multi-turn agent workflows, and cost-sensitive production tasks. Available in two variants:
| Model | Input (CNY/M) | Output (CNY/M) | Best For |
|---|---|---|---|
| SkyClaw-v1.0 | 0.5 | 4.0 | Strongest agent performance |
| SkyClaw-v1.0-lite | 0.3 | 2.0 | Speed & cost-sensitive tasks |
🎉 Free for a limited time: Both SkyClaw-v1.0 and SkyClaw-v1.0-lite are currently free to use.
What's New
Multimodal Image Input (2026-06-10)
SkyClaw now supports multimodal image input. Provide a UI screenshot as the visual prompt and ask SkyClaw to understand the layout, identify content, and rebuild the interface as working code — end to end.
|
📥 Input Reference screenshot 
|
📤 Output Generated HTML (interactive) 
|
| Given a Netflix mobile UI mockup, SkyClaw parsed the layout, identified 18 title posters, replaced SVG placeholders with real theatrical photos, and generated a fully interactive HTML clone with tab navigation, horizontal scroll rows, and animated profile bubble. | |
Benchmarks
SkyClaw-v1.0 outperforms Minimax 2.7, DeepSeek V4 Flash, and Qwen 3.6 series across all major agent benchmarks, while approaching larger proprietary models on Claw-related tasks.
Showcase
The release page features locally rendered screenshots and short videos, showcasing real generated demos across UI applications and interactive games.
Static Previews
| Flight & Travel | Instagram-style | Xiaohongshu-style |
 |  |  |
Interactive Demos
| Bouncing Balls Play | Bingo Match Play | 2048 Puzzle Play |
| Tetris Play | Super Mario Play | Airplane Battle Play |
| Chess Play | Texas Hold'em Play | Financial Terminal Open |
| Tank Roguelike Play | Slay the Spire (杀戮尖塔) Play |
Citation
If you reference SkyClaw-v1.0 in your work, please use the following citation:
@misc{skyclaw2026,
title={SkyClaw-v1.0: A Million-Context Agent Model at Ultra-Low Cost},
author={Peiyu Wang and Min Zou and Liang Zeng and Wei Shen and Peng Cheng and Haoran Zhang and Yu Cheng and Yang Liu},
year={2026},
month={May},
howpublished={\url{https://skyworkai.github.io/skyclaw/}},
url={https://skyworkai.github.io/skyclaw/},
}Corresponding authors: Yu Cheng, Yang Liu