This document explains the Categorizer node, which uses AI to classify text into custom categories.
Required Fields
- Input: Text to categorize
- Categories: Define your classification groups:
- Category Name: Label for the category
- Category Description: Explain what belongs in this category
Optional Fields
- Include Justification: Get AI’s reasoning for selections
- Additional Context: Extra guidance for categorization
- Temperature: Controls AI decision-making (0-1)
- 0: More focused, consistent
- 1: More creative, varied
- Cache Response: Save responses for reuse
The node allows you to configure certain parameters as dynamic inputs. You can enable these in the “Configure Inputs” section:
-
include_justification: Boolean
- true/false to include explanation for category assignment
-
Additional Context: String
- Extra information to guide the categorization process
- Example: “These items are different types of software bugs”
-
model_preference: String
- Name of the AI model to use
- Accepted values: “Claude 4.5 Sonnet”, “Claude 4.5 Haiku”, “GPT-5”, “GPT-4.1”, etc.
-
Cache Response: Boolean
- true/false to enable/disable response caching
- Helps reduce API calls for identical inputs
-
Temperature: Number
- Value between 0 and 1
- Controls categorization consistency
When enabled as inputs, these parameters can be dynamically set by previous nodes in your workflow. If not enabled, the values set in the node configuration will be used.
AI Model Fallback
Under Show More Options, configure automatic fallback when your selected AI model is unavailable. Fallback is enabled by default.
When an error occurs (rate limits, provider outages, timeouts), the system retries based on severity, then falls back to the next model. Fallback models are always from different providers for true redundancy.
| Error Type | Retries Before Fallback |
|---|
| Rate Limit | 2 |
| Provider 5xx | 1 |
| Network Error | 0 (immediate) |
| Timeout | 1 |
- Expert → Claude Opus 4.5 → Gemini 3 Pro → GPT-5.2
- Fastest → Gemini 3 Flash → Claude Haiku 4.5 → GPT-4.1
- Recommended → Claude Sonnet 4.5 → Gemini 3 Flash → GPT-5.2
Override: Enable to manually select up to 2 fallback models with drag-and-drop priority.
Disabling fallback means your node will fail if the primary model is unavailable.
Node Output
- Selected Category: Chosen category name
- Justification: AI’s reasoning (if enabled)
Node Functionality
The Categorizer node:
- Analyzes input text
- Matches to best category
- Provides reasoning (optional)
- Handles batch processing
- Supports custom categories
Available AI Models
| Tier | Models |
|---|
| Expert | GPT-5.2, GPT-5.1, GPT-5, OpenAI o3, Claude 4.5/4.1/4 Opus, Claude 3.7 Sonnet Thinking, Gemini 3 Pro, Grok 4 |
| Advanced | GPT-4.1, OpenAI o4-mini, Claude 4.5/4/3.7 Sonnet, Gemini 2.5 Pro, Grok 3, Perplexity Sonar Pro, LLaMA 3 405B |
| Standard | GPT-4.1 Mini/Nano, GPT-5 Mini/Nano, Claude 4.5 Haiku, Gemini 3/2.5 Flash, Grok 3 Mini, DeepSeek V3/R1, Mixtral 8x7B |
| Special | Auto-Select, Azure OpenAI (requires credentials) |
Auto-Select uses third-party routing to choose models based on cost and performance. Not ideal when consistent behavior is required.
AI Model Selection Guide
When choosing an AI model for your task, consider these key factors:
| Model Type | Ideal Use Cases | Considerations |
|---|
| Standard Models | General content creation, basic Q&A, simple analysis | Lower cost, faster response time, good for most everyday tasks |
| Advanced Models | Complex analysis, nuanced content, specialized knowledge domains | Better quality but higher cost, good balance of performance and efficiency |
| Expert & Thinking-Enabled Models | Complex reasoning, step-by-step problem-solving, coding, detailed analysis, math problems, technical content | Highest quality but most expensive, best for complex and long-form tasks, longer response time |
- Task complexity and required accuracy
- Response time requirements
- Cost considerations
- Consistency needs across runs
- Specialized knowledge requirements
For more detailed information on AI models with advanced reasoning capabilities, you can refer to:
Example Use Cases
- Sentiment Analysis:
Categories:
- Positive: "Expresses satisfaction or approval"
- Negative: "Shows dissatisfaction or criticism"
- Neutral: "States facts without emotion"
- Support Tickets:
Categories:
- Bug Report: "Technical issues or errors"
- Feature Request: "New functionality suggestions"
- Account Issue: "Login or access problems"
- Content Classification:
Categories:
- News: "Current events and reporting"
- Opinion: "Personal views and analysis"
- Tutorial: "How-to guides and instructions"
Loop Mode
Input: List of customer feedback
Process: Categorize each item
Output: Category per item + justifications
Important Considerations
- Expert models (OpenAI o3) cost 30 credits, advanced models (GPT-4.1, Claude 3.7 & Grok 4) cost 20 credits, and standard models cost 2 credits per run
- You can drop the credit cost to 1 by providing your own API key under the credentials page
- Write clear category descriptions for accurate outputs
- Enable justification for important decisions
- Use additional context for complex rules
Video Tutorial
In summary, the Categorizer node helps organize text into meaningful groups using AI, with optional explanations for each decision. 
