Simple LLM

Generate text with AI

Overview

Call OpenAI’s API to process items with AI. Supports system prompts, user prompts with expressions, configurable model parameters, and optional web search.

Category: AI
Tool Name: simple_llm
Version: 1

Appearance: Icon: brain | Color: #667eea

Node Type

Action — processes input items and produces output

Input / Output

Direction	Port(s)
Input	Input
Output	Output, Error

Credentials

This tool does not require any credentials.

Parameters

Parameter	Type	Required	Default	Description
System Prompt	string	No	You are a helpful assistant.	System message that sets the behavior of the assistant. Supports expressions like {{ $json.field }}.
User Prompt	string	Yes	{{ $json.text }}	The user message to send to the LLM. Supports expressions like {{ $json.field }}.
Model	options	No	gpt-4.1-mini	The OpenAI model to use for completion.
				Options: gpt-5.2, gpt-5, gpt-5-mini, gpt-5-nano, gpt-4.1, gpt-4.1-mini, gpt-4.1-nano
Web Search	boolean	No	false	Enable built-in web search. When true, the model can search the web for up-to-date information before responding.
Max Concurrency	number	No	50	Maximum number of concurrent API calls to OpenAI.
Include Input in Output	boolean	No	true	If true, includes the original input data in the output item.
Response Field Name	string	No	llmResponse	The field name to store the LLM response in the output item.

Output Data

One output item per input item. The generated text is written to the field named by Response Field Name (llmResponse by default), alongside an llmMetadata block. With Include Input in Output on — the default — the original item fields are kept underneath; turn it off to return only the response and its metadata. Binary data is forwarded either way.

{
  "llmResponse": "The article argues that ...",
  "llmMetadata": {
    "model": "gpt-4.1-mini",
    "usage": { "inputTokens": 812, "outputTokens": 143, "totalTokens": 955 },
    "status": "completed",
    "webSearchUsed": false,
    "processedAt": 1765432100000
  }
}

• usage reports the token counts for that single call, which is what the run is billed on.
• webSearchUsed says whether the model actually ran a web search for this item, not merely whether Web Search was enabled. A model given the tool may still answer without it.
• processedAt is a millisecond timestamp taken when the item finished.

Reference the result downstream by expression, e.g. {{ $json.llmResponse }}.

Usage Examples

• generate a summary of the article
• ask AI to write a response email
• use LLM to analyze the feedback
• create a product description
• compose a personalized message

Example Configuration

Send each item’s text field to the model and store the reply on llmResponse:

{
  "type": "simple_llm",
  "parameters": {
    "systemPrompt": "You are a helpful assistant.",
    "userPrompt": "{{ $json.text }}",
    "model": "gpt-4.1-mini",
    "webSearch": false,
    "maxConcurrency": 50,
    "includeInput": true,
    "responseFieldName": "llmResponse"
  }
}

Error Handling

Mode	Behavior
stop	Halts workflow on first error
continue	Skips failed items, passes successful ones through
errorPort	Routes failed items to Error output port

Tips

Sends a prompt to a language model (GPT) and returns the generated text response. Supports optional built-in web search for up-to-date information. Use when you need AI-generated content — summaries, analysis, rewrites, classifications, or any free-text generation task. Produces one item per input item containing the LLM response text.