Skip to main content
The Model tab allows you to choose the Large Language Model (LLM) that powers your AI agent. The selected model directly affects response quality, speed, context size, reasoning capability, and credit consumption.

​
Temperature

The Temperature setting controls how deterministic or creative the AI’s responses are.
  • Reserved (0) – Produces factual, consistent, and predictable responses. Recommended for customer support, FAQs, lead qualification, and business workflows.
  • Creative (>0) – Generates more diverse and creative responses. Ideal for brainstorming, content generation, and open-ended conversations.

​
Available Models

ChatzyAI supports models from multiple AI providers.

​
OpenAI

  • GPT-4.1 1M – High-quality model with a 1 million token context window.
  • GPT-4.1 Mini 1M – Faster and more cost-efficient version of GPT-4.1.
  • GPT-4o 128K – Fast, multimodal model suitable for most conversational tasks.
  • GPT-4o Mini 128K – Lightweight version of GPT-4o for high-volume workloads.
  • GPT-5 400K – Advanced reasoning model with a large context window.
  • GPT-5 Mini 400K – Faster and lower-cost version of GPT-5.
  • GPT-5.4 1M – Large-context model designed for complex workflows.
  • GPT-5.4 Mini 272K – Cost-efficient GPT-5.4 variant.
  • GPT-5.6 Luna 1M – Optimized for high-quality conversational experiences.
  • GPT-5.6 Terra 1M – Enterprise-grade model with excellent reasoning and context handling.
  • O4 Mini 200K – Optimized reasoning model for analytical and multi-step tasks.

​
Anthropic

  • Claude Haiku 4.5 200K – Extremely fast and efficient for lightweight conversations.
  • Claude Sonnet 4.6 1M – Powerful reasoning model with a large context window.

​
Google

  • Gemini 2.5 Flash 1M – Balanced model offering excellent speed and reasoning.
  • Gemini 2.5 Flash Lite 1M – Lightweight and cost-efficient Flash model.
  • Gemini 3.1 Flash Lite 1M – Faster generation for high-volume use cases.
  • Gemini 3.5 Flash 1M – Google’s latest Flash model with improved reasoning and performance.

​
Choosing the Right Model

Different models are optimized for different workloads.
Tip: Larger context windows allow the AI to reference more conversation history and larger knowledge bases, but may consume more credits depending on the selected model.