OpenAI o3-mini is the latest inference model introduced by OpenAI, optimized for science, technology, engineering, and mathematics (STEM) applications. It provides powerful inference capabilities while maintaining low costs and low latency, excelling particularly in mathematics, science, and programming. This model supports various developer features, such as function calls and structured outputs, and allows users to select different inference strengths based on their needs. The launch of o3-mini further reduces the cost of using inference models, making it more suitable for a wide range of application scenarios.