This document presents a study that uses deep learning models like LSTM and GRU to predict cryptocurrency prices. It analyzes daily price data for Bitcoin, Ethereum, and Cosmos from 2013-2021. Both LSTM and GRU recurrent neural networks are trained on the data, with GRU found to converge faster and produce more accurate predictions based on error metrics. Specifically, the GRU model outperforms the LSTM model in forecasting closing prices for the majority of cryptocurrencies examined based on mean absolute percentage error and root mean square error. The document concludes the GRU-based forecasting model is more appropriate than LSTM for predicting cryptocurrency prices due to high volatility.