Elon Musk’s‘s xAI launched an application programming interface (API) for Grok on Monday. The billionaire entrepreneur promised to turn the native artificial intelligence (AI) chatbot developed by xAI into an API in August, and now, users can access and use it. The API key can be generated using the xAI console and users can further customise how to use it. Notably, the pricing for input and output tokens have been kept higher than competitors. Currently, only one AI model is available to use via the API.
xAI API Launched
In a post on X (formerly known as Twitter), Musk announced that the API version of the AI model is now live for all users. An API is essentially a set of rules that allow different systems to communicate with each other. The tool is useful for developers who can then build apps and platforms by using data and other information from APIs.
In this particular case, the Grok API can allow developers to create various kinds of chatbot-style apps (or integrate the chatbot capability within an app) which are all powered by the Grok AI models.
Currently, only one large language model (LLM) dubbed “grok-beta” is available via the API. Notably, no details around the AI model is available. It is also not certain if it is a distilled model derived from the recently released Grok-2 or not. The AI model only supports text generation.
The xAI API costs $5 (roughly Rs. 420) per million input tokens and $15 (roughly Rs. 1261) per million output tokens. Notably, one million tokens is approximately 7,50,000 words. Notably, the pricing is kept on the higher end compared to rivals such as OpenAI’s ChatGPT and Google’s Gemini. Those interested in trying out the new xAI API can do so via the xAI Console.
The API supports function calling which is essential for any AI model-based API. Function calling allows users to make clear requests to the system and the interface fetches the required data. In xAI’s case, the API can connect with Grok AI model which is an Internet-enabled chatbot, and find responses to specific prompts and queries.