Spatial transcriptomic technologies enable measuring gene expression profile and spatial information of cells in tissues simultaneously. Clustering of captured cells/spots in the spatial transcriptomic data is crucial for understanding tissue niches and uncovering disease-related changes.Current methods to cluster spatial transcriptomic data encounter obstacles, including inefficiency in handling multi-replicate data, lack of prior knowledge incorporation, and producing uninterpretable cluster labels.We introduce a novel approach, LLMiniST, to identify spatial niche using a zero-shot large language models (LLMs) by transforming spatial transcriptomic data into spatial context prompts, leveraging gene expression of neighboring cells/spots, cell type composition, tissue information, and external knowledge. The model was further enhanced using a two-stage fine-tuning strategy for improved generalizability. We also develop a user-friendly annotation tool to accelerate the creation of well-annotated spatial dataset for fine-tuning.Comprehensive method performance evaluations showed that both zero-shot and fine-tunned LLMiniST had superior performance than current non-LLM methods in many circumstances. Notably, the two-stage fine-tuning strategy facilitated substantial cross-subject generalizability. The results demonstrate the feasibility of LLMs for tissue niche identification using spatial transcriptomic data and the potential of LLMs as a scalable solution to efficiently integrate minimal human guidance for improved performance in large-scale datasets.