Extreme multi-label text classification (XMC) concerns tagging input text with the most relevant labels from an extremely large set. Recently, pretrained language representation models such as BERT (Bidirectional Encoder Representations from Transformers) have been shown to achieve outstanding performance on many NLP tasks including sentence classification with small label sets (typically fewer than thousands). However, there are several challenges in extending BERT to the XMC problem, such as (i) the difficulty of capturing dependencies or correlations among labels, whose features may come from heterogeneous sources, and (ii) the tractability to scale to the extreme label setting because of the Softmax bottleneck scaling linearly with the output space. To overcome these challenges, we propose X-BERT, the first scalable solution to finetune BERT models on the XMC problem. Specifically, X-BERT leverages both the label and input text to build label representations, which induces semantic label clusters to better model label dependencies. At the heart of X-BERT is a procedure to finetune BERT models to capture the contextual relations between input text and the induced label clusters. Finally, an ensemble of the different BERT models trained on heterogeneous label clusters leads to our best final model, which leads to a state-of-the-art XMC method. In particular, on a Wiki dataset with around 0.5 million labels, the precision@1 of X-BERT is 67.87%, a substantial improvement over the neural baseline fastText and a state-of-the-art XMC approach Parabel, which achieve 32.58% and 60.91% precision@1, respectively.