In this study, we propose an API-enhanced ChatGPT structure that incorporates stock price and news data to improve stock price movement predictions. By integrating external data sources and prompt engineering techniques, our approach demonstrates a significant improvement in predictive performance compared to using only stock price data. The inclusion of news data alongside stock prices results in an approximately 10% increase in accuracy and F1 scores, as well as a 20% improvement in risk-adjusted returns, as measured by Sharpe ratios and information ratios. Our findings highlight the potential of leveraging conversational AI and large language models for stock market analysis, while also identifying areas for further research and optimization, such as addressing stock-specific challenges and developing cost-effective strategies for implementation. This study contributes to the limited body of literature on the application of large language models in finance and paves the way for future research in enhancing the capabilities of AI-driven investment decision-making tools