Guides
Shape Help Center
Start typing to search…

Model Selection

By default, NinjaCat Agents are driven by Claude Sonnet 4.5, Anthropic's best model for complex agents and coding. However, depending on your Agent’s specific needs—whether for faster response times or enhanced reasoning—you can choose an alternative model.

NinjaCat will adjust the default model when newer, better models come out after spending time testing that the output is as good or better than the prior default, and if it is more cost efficient. When the default is changed, it only impacts brand new Agents. Users will need to adjust the model for existing Agents if they would like to. NinjaCat will not adjust the model for existing agents to avoid disrupting an already perfectly crafted Agent (sometimes a model change could require tweaks to the prompt).

Available Model Options Supported Today

Anthropic Models

  • Claude Sonnet 4.5 (Default) - Anthropic's best model for complex agents and coding.
  • Claude Sonnet 4.5- Thinking
  • Claude Sonnet 4
  • Claude Sonnet 4- Thinking
  • Claude Haiku 4.5 - Anthropic's fastest, most cost-efficient model, matching Sonnet 4's performance on coding, computer use, and agent tasks - just introduced on 10/15/25, NinjaCat testing out before potentially making the default for new Agents
  • Claude Haiku 4.5- Thinking
  • Claude 3.7 Sonnet
  • Claude 3.7 Sonnet- Thinking

OpenAI Models

  • GPT 5 - Designed for the most complex and demanding tasks, trained w/ developers in mind. Focused on improved tool calling, instruction following and long-context understanding. High reasoning, you may experience slower output. Prompt optimizations encouraged- see OpenAI's Prompting Guide below.
  • GPT 5-mini
  • GPT 5-nano
  • 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
  • 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.
  • 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

How to Choose the Right Model

AI models are continuously improving, and what is "the best" today may be surpassed in a few months (or even a few weeks). NinjaCat will continue evaluating and adding models that demonstrate better intelligence, efficiency, or performance.

For the latest information, check the following provider help documentation:

Claude Sonnet Claude Haiku

OpenAI ChatGPT 5 Prompting Guide: https://cookbook.openai.com/examples/gpt-5/gpt-5_prompting_guide

OpenAI ChatGPT-4o OpenAI o3-mini OpenAI GPT 4.1 OpenAI o3 and o4-mini

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 5 days ago