GPT-4.1
Overview
GPT-4.1 is a large language model developed by OpenAI, released on April 14, 2025. It is designed to excel in instruction following and tool calling, with a broad knowledge base across various domains. The model features a context window of 1,047,576 tokens and supports up to 32,768 tokens in output. Notably, GPT-4.1 operates with low latency and does not require a reasoning step, making it efficient for tasks that demand quick responses. The model is multimodal, accepting text and image inputs, and providing text outputs. It is available through OpenAI's API and Developer Playground, with pricing set at $2.00 per million input tokens and $8.00 per million output tokens. GPT-4.1 is proprietary, with commercial use subject to OpenAI's terms and conditions. The model was retired on February 13, 2026, and is succeeded by GPT-5.1 and GPT-5.2, which offer enhanced capabilities and address user feedback regarding conversational style and warmth. GPT-4.1's retirement reflects OpenAI's commitment to advancing its AI offerings and meeting evolving user needs.