Users can use generative AI to create and edit content directly from within Marketpath CMS. All generated content comes from third-party service providers, however, and the quality of the content - as well as the cost to generate it - is dependent on the model of the service provider. For most purposes, the default provider and model will provide the best balance of cost and quality. However, if desired, the user may choose to select a different model from the ones supported by Marketpath. Read on to learn more about generative AI and the models and providers supported by Marketpath.
This is the default model, which generally provides good results at a cost-effective rate. Every prompt sent to the GPT-4o Mini model costs one token regardless of the prompt and response lengths or whether or not it is part of a chat.
This is the more powerful version of the GPT-4o Mini model. It is capable of generating more complicated and higher-quality responses to your prompts, but that comes at a cost. Prompts sent to the GPT-4o model cost a minimum of 2 tokens and may cost more if the prompt and/or response are long. When sending the prompt as part of a chat, the entire chat history is sent along with the prompt, which may increase the cost as the chat grows longer.
Generative AI refers the ability to use technology to create new content based on patterns and examples from existing data. It is capable of answering questions, creating and editing content, and in some cases performing simple actions. The specific capability of generative AI depends on the "model" it uses.
An AI model is a mathematical representation or algorithm that is trained to perform specific tasks. Most significantly, this includes the task of creating new content based on data previously analyzed by that model - a process known as "training". Most models are trained on large datasets composed of publicly-available information, which it uses both to "understand" and respond to prompts. The content that generative AI can produce is limited to the data available when the model is trained, and while AI providers release regular updates to their models there is always a delay between when an event in real life happens and when information about that event becomes available to various AI models.
It takes a lot of time, expertise, and resources to create, train, and maintain an AI model, and there are already a number of companies who do it well. An AI Provider is simply a company who has already taken on the responsibility of providing one or more AI models for public consumption. How each provider handles data and programs their models is different.
Generative AI is still a young technology and is rapidly evolving. The models, and even the providers, that are available are likely to change over time. Furthermore, each provider and model has its own pricing model. In order to keep things simple for Marketpath users and to be able to utilize multiple providers and models to generate content, Marketpath CMS tracks the cost to generate content using "AI Tokens". Each prompt sent to an AI model costs one or more AI Tokens, with more powerful models and longer requests costing more tokens than simpler models and shorter requests. On it's own each token does not cost much, but over time that cost can add up, so it is helpful to consider your needs and resources when selecting a provider and model.