Under the ‘LLM’ tab in the agent configuration, administrators can select the Large Language Model (LLM) that best aligns with the agent’s objectives. The selected model will dictate the agent’s responses to user queries.
Large Language Models are AI systems that understand and generate human language, enabling tasks like text generation, question answering, and translation in a specific way.
Currently, you can select from the following LLM options: Mindset Recommended, GPT4o, GPT 4.1, GPT 5, GPT 5 Thinking, GPT 5 Mini, Claude Sonnet 4, or Gemini 2.5 Pro. Brief descriptions of each LLM can be found below their respective labels in the ‘LLM’ tab.
Mindset Recommended (GPT-4.1): Recommended for the right balance between cost, intelligence and speed. Great for everyday work. Handles most text tasks well - writing, answering questions, and coding. Good at remembering long conversations and following instructions carefully.
GPT 4o: Older generation LLM but a crowd favourite, fast and reliable intelligence. Quick responses with good quality. Solid choice when you need fast, consistent answers for most text-based tasks.
GPT 4.1: Great for everyday work. Handles most text tasks well - writing, answering questions, and coding. Good at remembering long conversations and following instructions carefully.
GPT 5: Very smart and fast. High-performance model that’s faster than Thinking mode while still being very intelligent. Good balance when you need advanced capability without the wait.
GPT 5 Thinking: The absolute best. Most capable model available. Takes time to think deeply through problems but gives the most accurate, comprehensive answers. Use when you need the highest quality, as responses are slower.
GPT 5 Mini: Smart but affordable. Good intelligence at lower cost. Faster than full GPT-5 while still being very capable.
Claude Sonnet 4: Thoughtful and creative. Very good at writing and analysis. Known for careful, well-reasoned responses and being the most creative.
Gemini 2.5 Pro: Top-tier reasoning and coding. Google’s most advanced model with exceptional reasoning abilities. Leads in math, science, and coding benchmarks. Handles massive context (1M+ tokens) for big or complex projects.
We advise you to first trial each of these models in the ‘Preview’ tab to evaluate their performance and ensure satisfaction with the generated response outputs.
Additional information on these Large Language Model options can be found by contacting your Customer Success Representative.