引入GPT-4.1 AI模型家族

Openai推出了其最新的旗舰人工智能模型GPT-4.1家族，其中包括主要的GPT-4.1模型

OpenAI is rolling out a new family of flagship GPT models: GPT-4.1, Mini, and Nano.

Openai正在推出一个新的旗舰GPT型号：GPT-4.1，Mini和Nano。

The models, which are now available through OpenAI’s API, are designed to serve a range of developer needs, from handling large-scale codebases to delivering fast, low-latency responses for simpler tasks.

现在可以通过OpenAI的API获得这些模型，旨在满足一系列开发人员需求，从处理大型代码库到​​提供快速，低延迟响应以实现更简单的任务。

The standout feature of the GPT-4.1 models is their ability to process up to 1 million tokens of context in a single call. This is a huge increase over previous models like GPT-4, which supported up to 128,000 tokens.

GPT-4.1模型的出色功能是它们在单个呼叫中最多可处理100万个令牌的能力。这比以前的型号（如GPT-4）巨大增长，该模型支持多达128,000个令牌。

The expanded context window allows the models to work with entire code repositories, lengthy documents, and complex workflows without losing track of what’s relevant.

扩展的上下文窗口允许模型与整个代码存储库，冗长的文档和复杂的工作流程一起使用，而不会失去相关内容。

OpenAI says that GPT-4.1 shows a 21% improvement in coding abilities over GPT-4 and a 27% improvement over GPT-4.5. The models also use 26% less computing power than GPT-4.

OpenAI表示，GPT-4.1的编码能力比GPT-4的提高了21％，比GPT-4.5提高了27％。与GPT-4相比，模型还使用了26％的计算能力。

The new family is particularly good at editing large files, following instructions, and understanding images, putting it ahead of previous models on several benchmarks.

新家庭特别擅长编辑大型文件，按照说明和理解图像，将其领先于以前的模型。

With this release, OpenAI is phasing out the GPT-4.5 Preview, which will be turned off in the API on July 14, 2025. The company says that GPT-4.1 offers similar or better performance at a lower cost and with less latency.

有了此版本，OpenAI将逐步淘汰GPT-4.5预览，该预览将于2025年7月14日在API中关闭。该公司表示，GPT-4.1的性能以较低的成本和延迟较小。

The models are trained on data up to June 2024, making them the most up-to-date among OpenAI’s offerings.

截至2024年6月，这些模型对数据进行了培训，使其成为Openai产品中最新的。

GPT-4.1, Mini, and Nano are available exclusively via the API and are not integrated into the ChatGPT interface. OpenAI has worked closely with the developer community to optimize these models for real-world coding and instruction-following tasks.

GPT-4.1，Mini和Nano可通过API独家提供，并且不集成到ChatGpt接口中。 OpenAI与开发人员社区紧密合作，以优化这些模型，以实现实际编码和指导遵守任务。

The Nano version is the fastest and most cost-effective, making it suitable for classification and autocompletion, while the full-size model excels at handling complex, multi-turn agent workflows.

纳米版本是最快，最具成本效益的，使其适合分类和自动完成，而全尺寸型号则在处理复合物，多转动代理工作流程方面表现出色。