Openai has announced the phase-out of GPT-4.5 from its developer API to support its new GPT-4.1 model. At launch, Openai described GPT-4.5 By far it is its best and most capable model, partly because it is a more natural dialogueist and has the potential to mimic some concepts of emotional intelligence. Despite its name suggestion, GPT-4.1 should be better and more effective.
Openai said that GPT-4.1 is specifically used by developers to use OpenAI’s API and comes in three sizes of GPT-4.1, GPT-4.1 Mini and GPT-4.1 Nano. This means that if you can’t find it in the public-oriented Chatgpt interface, you can one day interact with an agent that takes advantage of the model improvements. According to Openai, GPT-4.1 should be better at coding and “fiction understanding” and support “up to a million contexts” and world knowledge as of June 2024.
It is important to decide to phase out the GPT-4.5 preview, and GPT-4.1 is also cheaper. Openai said the model is “26% cheaper than median query than GPT-4”. The company imagines developers using GPT-4.1 to build agents that can work in software engineering environments, one of the most popular uses for generating AI. Even if GPT-4.5 will eventually be removed from OpenAI’s API, the Model preview will still be available in Chatgpt if you don’t want to use it.
Openai said the GPT-4.1 family can be used today through the company’s API. GPT-4.5 will be fully basic within three months on July 14, 2025.
