A Model lets the Ardent platform know which AI model should handle requests made to your agent. We currently have support for all popular models from the three major providers, and will be adding support for open source models (eg. Llama, DeepSeek) as well. Each model has its own strengths and weaknesses, and the more powerful models tend to cost more. If you aren’t sure where to begin, the default model for each provider will give you a good starting point. You can experiment with the different models until you find one that provides the right balance of cost to performance. During early access, you are required to supply your own API key for the model provider that you’d like to use. To get an API key for a model provider, you’ll have to create an account with the provider, and possibly provide them with payment information.