Large language models

Live Hub provides the following pre-deployed large language models that can be used in AI Agents:

Model

Pros & Cons

gpt-4o-mini

gpt-4.1-mini

gpt-5-mini

  • Fast and cost-effective models from OpenAI

  • Provide adequate performance for typical AI Agent scenarios

  • May struggle with complex multi-step instructions

gpt-4o

gpt-4.1

gpt-5

  • Powerful models from OpenAI for complex tasks

  • Effectively follow complex instructions

gpt-4.1-nano

gpt-5-nano

  • Most cost-effective models from OpenAI

  • Recommended only for simple tasks

gemini-2.0-flash

gemini-2.5-flash

  • Powerful models from Google

  • Great performance across wide range of tasks

  • Significant cost savings compared to gpt-4o / gpt-4.1 / gpt-5

gemini-2.0-flash-lite

gemini-2.5-flash-lite

  • Cost-efficient models from Google

  • May struggle with complex multi-step instructions

gpt-mini-realtime

  • Cost-effective real-time models from OpenAI

  • Supports voice and text modalities

  • Extremely low latency and natural conversation experience

gpt-realtime

  • Flagship real-time model from OpenAI

  • Supports voice and text modalities

In addition to the above, you may bring your own large language models from different providers by configuring corresponding API Keys in the Models screen. For details, see Models.