OpenAI has released the new versions of its text-generating AI models GPT-3.5-turbo and GPT-4, with a capability called function calling.
“Developers can now describe functions to GPT-4-0613 and GPT-3.5-turbo-0613 and have the model intelligently choose to output a JSON object containing arguments to call those functions. This is a new way to more reliably connect GPT’s capabilities with external tools and APIs,” OpenAI said in a blog post on Tuesday.
With the function calling capability, developers can create chatbots that answer questions by calling external tools (e.g., ChatGPT Plugins).
For instance, convert queries such as “Email Anya to see if she wants to get coffee next Friday” to a function call like send_email(to string, body: string), or “What’s the weather like in Boston?” to get_current_weather(location: string, unit: ‘celsius’ – ‘Fahrenheit’).
The company said it will begin the upgrade and deprecation process for the initial versions of GPT-4 and GPT-3.5-turbo which it announced in March.
Applications using the stable model names (GPT-3.5-turbo, GPT-4, and GPT-4-32k) will automatically be upgraded to the new models listed above on June 27.
Moreover, the company said that it is reducing pricing for GPT-3.5-turbo by 25 percent.
Developers can now use the model for $0.0015 per 1,000 input tokens and $0.002 per 1,000 output tokens, resulting in approximately 700 pages per dollar.
Text-embedding-ada-002, one of OpenAI’s most popular text embedding models, is also getting a price cut.
Text embeddings are commonly used for search (where results are ranked based on relevance to a query string) and recommendations (where items with related text strings are recommended).
Text-embedding-ada-002 now costs $0.0001 per 1,000 tokens, which is 75 percent less than the previous price.
