Cross-city urban flow prediction is critical for democratizing smart application benefits in data-scarce developing cities. However, existing methods face an inherent performance ceiling, constrained by both the inevitably finite samples from the source city and the distributional gap between cities. In this paper, we present PLM-CUP, the first theoretically-grounded framework that breaks this bottleneck by leveraging a pre-trained language model (PLM) as an additional source domain. Through an information-theoretic analysis of the generalization error bound, we reveal that the key challenge lies in constructing a semantic bridge encoder and a task-specific adapter to enable cross-domain alignment when incorporating a PLM. Accordingly, PLM-CUP adopts a three-stage architecture, including a semantic bridge encoder that transforms spatiotemporal flow patterns into languagealigned representations via trend-periodicity decomposition, a PLM fine-tuned for knowledge transfer, and a task adapter with spatiotemporal self-attention to conduct multi-step prediction. We further introduce GDAConv, a graph convolution module with dual activation functions that enhances spatial modeling throughout the framework. Experiments on real-world datasets demonstrate that PLM-CUP significantly outperforms state-of-the-art baselines, validating the effectiveness of the proposed PLM enhanced cross-city transfer paradigm for urban flow prediction.