Model Selection
By default, NinjaCat Agents are driven by OpenAI GPT-4o, which offers strong reasoning, speed, and versatility for most tasks. However, depending on your Agent’s specific needs—whether for faster response times or enhanced reasoning—you can choose an alternative model.
Available Model Options Supported Today
OpenAI Models
- OpenAI ChatGPT-4o – Fast, versatile, and high-intelligence model suitable for most Agents.
- OpenAI o3-mini (with Low Reasoning) – Optimized for speed, but with limited reasoning capabilities.
- OpenAI o3-mini (with Medium Reasoning) – Balanced performance between reasoning depth and response speed.
- OpenAI o3-mini (with High Reasoning) – Stronger reasoning ability, ideal for complex, multi-step tasks, but slower response times.
- GPT 4.1 - OpenAI's Flagship GPT Model for complex tasks (an upgrade to GPT-4o)
- GPT 4.1-mini - Balanced for intelligence, speed and cost
- GPT 4.1-nano - Fastest, most cost-effective GPT 4.1 model
- o4-mini (w/ Low, Medium and High reasoning levels) - smaller model optimized for fast, cost-efficient reasoning
- o3 (w/ Low, Medium and High reasoning levels) - most powerful reasoning model
Anthropic Models
- Claude 3.7 Sonnet
- Claude 3.7 Sonnet- Thinking
How to Choose the Right Model
ChatGPT-4o was previously our default model for Agents, however we have seen better performance from Claude 3.7 Sonnet as well as the newest OpenAI models: GPT 4.1 and o3. Because of this, we have adjusted the default model driving new Agents to Claude 3.7 Sonnet, but users are still encouraged to test out different models for their specific goal and configuration.
AI models are continuously improving, and what is "the best" today may be surpassed in a few months. NinjaCat will continue evaluating and adding models that demonstrate better intelligence, efficiency, or performance.
For the latest information, check the following provider help documentation:
Note: When switching between models, prompt adjustments may be required to maintain optimal Agent performance. We will provide further guidance on necessary prompt modifications as we continue testing and learning.
Updated 19 days ago