GPT-4.1, released by OpenAI in April 2025, is a multimodal large language model that advances the GPT-4 series with major improvements in coding, reasoning, and instruction following. It accepts both text and images, supports tool calling and structured outputs, and features an expanded context window of up to ~1 million tokens—enabling it to process very large documents, multi-file codebases, or long conversations in a single prompt. Its knowledge is current through June 2024.
The GPT-4.1 family includes standard, mini, and nano variants, offering trade-offs between performance, cost, and latency. While parameter counts remain undisclosed, the series improves efficiency and responsiveness compared to GPT-4, making it suitable for both enterprise-scale tasks and cost-sensitive applications. Common use cases include software development, technical research, knowledge management, multimodal analysis, and high-context enterprise assistants.