O4 Mini

O4 Mini is OpenAI's compact reasoning model, a generation beyond O3 Mini with strong performance for its size and cost. It excels in mathematics and competitive programming, reaching 99.5 percent pass@1 on AIME 2025 when given access to a Python interpreter, and outperforms O3 Mini across STEM and non-STEM tasks including data science work. The model combines efficient reasoning with practical strengths in coding and visual understanding. It accepts text and image input, with a 200,000 token context window and up to 100,000 output tokens, and supports structured outputs, function calling, and streaming. O4 Mini can use tools within its reasoning, including web search, Python execution, image and file analysis, and image generation. It sustains higher usage limits than larger reasoning models, making it a strong choice for high-throughput applications that need reliable reasoning at lower cost.