Developer OpenAI Enhances GPT-3.5-Turbo and GPT-4 with AI Text Generation Features and Function Calling Capabilities

Microsoft-owned company OpenAI has updated its text-generating AI models, GPT-3.5-turbo and GPT-4, with a new capability called function calling. With this new feature, developers can describe functions to GPT-4-0613 and GPT-3.5-turbo-0613 and allow the model to intelligently output a JSON object containing arguments to call those functions. This could help to more reliably connect GPT’s capabilities with external tools and APIs. In addition, developers can create chatbots by calling external tools, which can be handy for responding to questions. OpenAI stated that it will start upgrading and deprecating the initial versions of GPT-4 and GPT-3.5-turbo. Applications using the stable model names will be automatically upgraded to the new models at a later date. Furthermore, the company has reduced the pricing for GPT-3.5-turbo by 25%. Developers can now use the model for $0.0015 per 1,000 input tokens and $0.002 per 1,000 output tokens, which is around 700 pages per dollar. Additionally, Text-embedding-ada-002, one of OpenAI’s most popular text-embedding models, is getting a price cut of 75%. The model now costs $0.0001 per 1,000 tokens.