Model
Determine which GPT model to use with your assistant.
The Model section in the Agent Settings allows you to select the Large Language Model (LLM) that best suits your assistant’s requirements.
Below is an overview of the models currently available:
GPT-4o Mini
The lightweight version of GPT-4o, offering faster performance and cost-efficiency. Best suited for simple queries and applications prioritizing speed and affordability.
GPT-4o
An optimized version of GPT-4, providing high-quality responses with reduced latency. Ideal for scenarios requiring both accuracy and responsiveness.
GPT-4
The most advanced model for generating high-quality, detailed responses. Recommended for complex tasks requiring precision and contextual understanding.
GPT-3.5 (0125)
An enhanced version of GPT-3.5 with optimizations for stability and specific use cases. Offers a balance between performance and cost-effectiveness.
GPT-3.5
A reliable and cost-efficient option for applications where speed and affordability are the primary considerations. Suitable for straightforward interactions and real-time responses.
Configuring the model
To configure the model for your assistant:
- Navigate to the Large Language Model section in Agent Settings.
- Select the desired model from the dropdown list.
- Save your settings to apply the changes.
For more detailed information on each model, refer to the OpenAI Model Documentation.