OpenAI announced the extension of GPT-4 availability to all paying API users and the deprecation of legacy embed models. This change gives developers the opportunity to create even more powerful software and plugins than are available today.
What the GPT-4 API is and why it matters
API stands for Application Programming Interface, a way to let two software programs interact with each other.
It works like a secure bridge between two software programs, allowing them to pass information between the two software programs.
The GPT-4 API allows developers to create new software that can leverage the power of GPT-4 in useful contexts.
This means that more powerful interactions are available to consumers as more developers gain access.
Availability of GPT-4 for API users
The announcement of OpenAI means that all developers in good standing with OpenAI have access to the more powerful GPT-4 API.
This development is important because it means that services and products that depend on the API will themselves become more powerful and able to do more.
According to OpenAI:
“GPT-4 is our most powerful model. Millions of developers have requested access to the GPT-4 API since March, and the range of innovative products leveraging GPT-4 is growing every day.
Today, all existing API developers with a track record of payments can access the GPT-4 API with 8K context.
We plan to open access to new developers by the end of this month and then start increasing rate limits based on compute availability.
Based on the stability and readiness of these models for production scale deployment, we are also making the GPT-3.5 Turbo, DALL E, and Whisper APIs generally available.
We are working to safely enable fine tuning for GPT-4 and GPT-3.5 Turbo and expect this feature to be available later this year.”
Chat Closing API
The announcement states that OpenAI will deprecate the older Completions API and recommends a move to the newer Chat Completions API.
Launched in March 2023, the Chat Completions API enables more powerful interactions and now accounts for 97% of API GPT usage.
An article published on Medium described the importance of chat closures as revolutionary:
“This feature allows developers to describe functions to the AI models, which can then intelligently decide to emit a JSON object containing arguments to invoke those functions.
…It opens up a world of possibilities for creating more interactive and dynamic applications.”
OpenAI’s announcement explained why chat completions are becoming the standard:
“…the structured interface (e.g. system messages, function calls) and multi-turn conversation capabilities of the Chat Completions API enable developers to create conversational experiences and a wide range of completion tasks.
It also helps reduce the risk of prompt injection attacks because user-provided content can be structurally separated from instructions.”
OpenAI will phase out older models in six months and by January 2024, older degree models will no longer be available.
This is to allow developers to update their products and services with the old models to take advantage of the new ones. The same goes for developers using the older embedding models.
OpenAI assumes the financial costs of the changeover
OpenAI’s statement acknowledges that moving away from the older models is a significant change.
“We will cover the financial cost of users re-embedding content with these new models.
We will be in touch with affected users in the coming days.”
OpenAI continues to innovate and improve
OpenAI continues to stay ahead of the competition, enabling companies to develop and improve new products and services.
This means more powerful tools are available to downstream consumers.
These changes are important as they allow users to have more access to GPT-4.
Read the OpenAI announcement:
General availability of the GPT-4 API and deprecated models in the Completions API
Featured image from Shutterstock/Lotus_studio