OpenAI announced the expansion of GPT-4 availability to all paid API users and the retirement of older embedding models. This change gives developers the ability to create even more powerful software and plug-ins than is currently available.
What is the GPT-4 API and why is it important?
API stands for Application Programming Interface, a way for two programs to interact with each other.
It works as a secure bridge between two software programs that allows them to pass information between the two programs.
The GPT-4 API allows developers to create new software that can apply the power of GPT-4 in useful contexts.
This means that more powerful interactions will become available to consumers as more developers gain access to them.
Availability of GPT-4 for API users
OpenAI’s announcement 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 rely on the API will be more powerful and able to do more.
According to OpenAI:
“GPT-4 is our most capable model. Millions of developers have requested access to the GPT-4 API since March, and the range of innovative products using GPT-4 is growing every day.
Currently, all existing API developers with a successful payment history can access the GPT-4 API with 8K context.
We plan to open access to new developers later this month and then begin increasing rate limits based on computing availability.
Based on the stability and readiness of these models for production-scale use, we are also making the GPT-3.5 Turbo, DALL·E, and Whisper APIs generally available.
We are working to safely enable tuning for GPT-4 and GPT-3.5 Turbo and expect this feature to be available later this year.”
Chat Completion API
The announcement indicates that OpenAI will be deprecating the older completions API and encourages moving to the new chat completions API.
The Chat Completion API, introduced in March 2023, enables more powerful interactions and now accounts for 97% of the API’s GPT usage.
An article published in average described the importance of chat completions as revolutionary:
“This feature allows developers to describe functions in AI models, which can then intelligently decide to output a JSON object containing arguments for calling those functions.
…It opens up a world of possibilities to create more interactive and dynamic applications”.
OpenAI’s announcement explained why chat completions will become the default:
“… the chat completions API’s structured interface (eg, system messages, function calls) and multi-turn conversational capabilities allow developers to create conversational experiences and a wide range of completion tasks .
It also helps reduce the risk of rapid injection attacks, as user-supplied content can be structurally separated from instructions.”
OpenAI will retire the old models in six months, and in January 2024 the older completion models will no longer be available.
This is intended to allow developers to update their products and services using the old models to take advantage of the new ones. The same applies to developers using the previous embedding models.
OpenAI will cover the financial cost of the change
OpenAI’s statement acknowledges that the shift from older models represents a significant change.
They promised:
“We will cover the financial cost of users re-embedding content with these new models.
We will be contacting affected users over the next few days.”
OpenAI continues to innovate and improve
OpenAI continues to stay ahead of any competition, enabling the creation and improvement of new products and services by companies.
This means that downstream consumers will have more powerful tools at their disposal.
These changes are important because they will allow users to do more with GPT-4 access.
Read the OpenAI announcement:
General availability of the GPT-4 API and deprecation of old models in the Completions API
Featured image by Shutterstock/Lotus_studio
[ad_2]
Source link
