OpenAI unveils new updates to API models and function calling capabilities

OpenAI has recently announced exciting updates to its API offerings. These updates bring enhanced functionalities and more control to developers utilizing their models. Earlier this year, OpenAI introduced gpt-3.5-turbo and gpt-4, which have already proven to be invaluable tools for developers in creating groundbreaking applications.

One of the notable updates is the inclusion of function calling capabilities in the Chat Completions API. This groundbreaking feature allows developers to describe functions to the models and receive JSON objects as output. By enabling function calling, OpenAI empowers developers to seamlessly integrate ChatGPT capabilities with external tools and APIs, providing the opportunity to obtain structured data directly from the models.

As we mentioned at the beginning, they have also released updated and more steerable versions of gpt-4 and gpt-3.5-turbo, allowing for even greater control and fine-tuning of the models. Additionally, a new 16k context version of gpt-3.5-turbo has been introduced, surpassing the previous 4k limit. This extended context option offers developers the ability to process longer pieces of text and extract more comprehensive insights from the models.

To make their services more accessible, OpenAI has taken steps to reduce costs. The company has lowered the price of their state-of-the-art embeddings model by an impressive 75%. Additionally, the cost of input tokens for gpt-3.5-turbo has been reduced by 25%, allowing developers to create even more cost-effective applications while leveraging the power of OpenAI's models. The company has also provided a clear deprecation timeline for earlier versions of their models. Both gpt-3.5-turbo-0301 and gpt-4-0314 will be deprecated, ensuring that developers have a smooth transition to the updated versions without any disruptions.

Crucially, OpenAI emphasizes data privacy and security. They guarantee that customer data is not used for training, and customers retain ownership of all outputs generated from their requests. This commitment to data privacy and security establishes trust and enables developers to confidently build applications powered by OpenAI's models.

The introduction of function calling brings a myriad of possibilities for developers. From creating chatbots that seamlessly interact with external tools to converting natural language into API calls or database queries, and even extracting structured data from text, function calling opens up new horizons for application development with OpenAI's models.

With these updates, OpenAI continues to push the boundaries of AI innovation, enabling developers to unlock the full potential of their API models. The integration of function calling, expanded context options, and cost reductions paves the way for the creation of even more sophisticated and cost-effective applications, while maintaining a strong focus on data privacy and security.