kat-dev · Qwen
KAT-Dev (32B) is an open-source 32B parameter model specifically designed for software engineering tasks. It achieved a 62.4% resolution rate on the SWE-Bench Verified benchmark, ranking fifth among all open-source models of various scales. The model is optimized through multiple stages, including intermediate training, supervised fine-tuning (SFT) and reinforcement fine-tuning (RFT), as well as large-scale agent reinforcement learning (RL). Based on Qwen3-32B, its training process lays the foundation for subsequent fine-tuning and reinforcement learning stages by enhancing fundamental abilities such as tool usage, multi-turn interaction, and instruction following. During the fine-tuning phase, the model not only learns eight carefully curated task types and programming scenarios but also innovatively introduces a reinforcement fine-tuning (RFT) stage guided by human engineer-annotated “teacher trajectories.” The final agent reinforcement learning phase addresses scalability challenges through multi-level prefix caching, entropy-based trajectory pruning, and efficient architecture.
KAT-Dev (32B) is an open-source 32B parameter model specifically designed for software engineering tasks. It achieved a 62.4% resolution rate on the SWE-Bench Verified benchmark, ranking fifth among all open-source models of various scales. The model is optimized through multiple stages, including intermediate training, supervised fine-tuning (SFT) and reinforcement fine-tuning (RFT), as well as large-scale agent reinforcement learning (RL). Based on Qwen3-32B, its training process lays the foundation for subsequent fine-tuning and reinforcement learning stages by enhancing fundamental abilities such as tool usage, multi-turn interaction, and instruction following. During the fine-tuning phase, the model not only learns eight carefully curated task types and programming scenarios but also innovatively introduces a reinforcement fine-tuning (RFT) stage guided by human engineer-annotated “teacher trajectories.” The final agent reinforcement learning phase addresses scalability challenges through multi-level prefix caching, entropy-based trajectory pruning, and efficient architecture.
Kat Dev has a 128,000 token context window.
On AIHubMix, Kat Dev costs $0.137 per million input tokens and $0.548 per million output tokens.
Kat Dev accepts text input.
Kat Dev supports tool calling. Per-protocol parameter support is listed in the capability table on this page.
Kat Dev is available through the AIHubMix unified API. The API is OpenAI-compatible: point your OpenAI SDK at https://aihubmix.com/v1, use your AIHubMix API key, and set the model name to kat-dev — no other code changes needed.
Kat Dev is developed by Qwen. AIHubMix aggregates it alongside models from other providers behind one API and one bill.
Qwen3.8 Omni Flash is Alibaba Cloud Qwen's next-generation native multimodal model…
Alibaba Cloud has launched the decision model decision-model-preview. This structured…
Qwen3.8-27b is an Alibaba-released dense vision-language model with open-source weights…
Qwen3.8-Max-0902 (also known as qwen3.8-max-2026-09-02) is a snapshot version of Alibaba…
Qwen3.8 Flash is Alibaba Cloud Qwen’s flagship native vision-language model for coding…
Wan 3.0 (Tongyi Wanxiang 3.0) is an integrated video generation and editing model…
Use Kat Dev via the AIHubMix unified API — one interface for every major LLM.