Documentation is being updated. Some sections may not reflect the latest features.
Looking for step-by-step guides? Explore Tutorials →

Model Node

Connect to any major LLM provider with a unified interface.

Overview

The Model Node allows you to send prompts to AI language models and receive responses. It supports multiple providers including OpenAI, Anthropic, Google, Meta, and Mistral.

Configuration

Field Description Required
Model Select the LLM model to use (GPT-4o, Claude 3.5, Gemini, etc.) Yes
System Instructions The system prompt that defines the AI's behavior and context No
User Prompt The user input variable (default: {{prompt}}) Yes
Output Variable Variable name to store the response for use in other nodes No
Images For vision models, select an image variable from previous nodes No

Advanced Options

Field Description Default
Temperature Controls randomness. Higher = more creative, Lower = more focused (0-2) 0.7
Max Tokens Maximum response length (100-8192) 2048

Using Variables

You can use variables from previous nodes in your prompts using the {{variable_name}} syntax:

Analyze the following data:
{{scraped_content}}

Provide a summary in 3 bullet points.

Output

The LLM response is stored in the output variable you specify. Access it in subsequent nodes using:

{{llm_response}}

Supported Models

  • OpenAI: GPT-4o, GPT-4, GPT-3.5 Turbo
  • Anthropic: Claude 3.5 Sonnet, Claude 3 Opus, Claude 3 Haiku
  • Google: Gemini Pro, Gemini Ultra
  • Meta: Llama 3
  • Mistral: Mistral Large, Mistral Medium
AI AssistantPowered by Ubex
Beta
Ask me anything about Ubex workflows, nodes, or the API.