This paper introduces Usable XAI in the context of Large Language Models (LLMs), focusing on 10 strategies to enhance both LLMs and XAI frameworks. The first category, Usable XAI for LLMs, explores how explanations can improve model performance and usability, including diagnosis, enhancement, and data augmentation. The second category, LLM for Usable XAI, examines how LLMs can enhance XAI frameworks through user-friendly explanations, interpretable workflows, and human-like reasoning. The paper also discusses challenges in applying XAI to LLMs, such as the complexity of LLMs and the need for practical, human-centric explanations. It provides case studies and reviews existing methods, highlighting the importance of usability in XAI for real-world applications. The paper emphasizes the need for further research in explaining LLMs, improving model trustworthiness, and enhancing XAI frameworks through LLM capabilities.This paper introduces Usable XAI in the context of Large Language Models (LLMs), focusing on 10 strategies to enhance both LLMs and XAI frameworks. The first category, Usable XAI for LLMs, explores how explanations can improve model performance and usability, including diagnosis, enhancement, and data augmentation. The second category, LLM for Usable XAI, examines how LLMs can enhance XAI frameworks through user-friendly explanations, interpretable workflows, and human-like reasoning. The paper also discusses challenges in applying XAI to LLMs, such as the complexity of LLMs and the need for practical, human-centric explanations. It provides case studies and reviews existing methods, highlighting the importance of usability in XAI for real-world applications. The paper emphasizes the need for further research in explaining LLMs, improving model trustworthiness, and enhancing XAI frameworks through LLM capabilities.