Introducing the GPT-4.1 family of AI models

OpenAI has introduced its latest flagship artificial intelligence models, the GPT-4.1 family, which includes the main GPT-4.1 model

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

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.

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.

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.

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

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.

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

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.

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.