AI LLM Node (Claude / GPT / Gemini)
Call any major AI model — Anthropic Claude, OpenAI GPT-4o, or Google Gemini — from an automation step. Supports system prompts, temperature, and variable output.
The AI LLM node sends a prompt to a large language model and stores the response as a variable. It supports three providers — Anthropic Claude, OpenAI GPT, and Google Gemini — configurable per node so you can mix providers within the same automation.
---
| Field | Type | Required | Description | ||
|---|---|---|---|---|---|
provider | enum | Yes | claude | openai | gemini |
model | string | No | Specific model ID. Defaults: Claude → claude-sonnet-4-6, GPT → gpt-4o, Gemini → gemini-1.5-pro | ||
system | string | No | System / persona prompt. Supports {{variables}} | ||
prompt | string | Yes | The user-turn prompt. Supports {{variables}} and {{lead.*}} | ||
maxTokens | integer | No | Max output tokens (default: 1024) | ||
temperature | float | No | 0.0–1.0 (default: 0.7). Lower = more deterministic | ||
outputVar | string | No | Variable name to store the response text (default: llmResponse) |
---
| Variable | Description |
|---|---|
{{variables.llmResponse}} | The model's text response (or your custom outputVar) |
---
json
{
"provider": "claude",
"system": "You are a lead qualification assistant. Respond with a single word only.",
"prompt": "Classify this email as one of: hot / warm / cold / spam.\n\nEmail: {{email.bodyText}}",
"outputVar": "leadTemperature",
"maxTokens": 10,
"temperature": 0.1
}
Then use a logic.if node downstream: {{variables.leadTemperature}} equals hot.
---
json
{
"provider": "openai",
"model": "gpt-4o",
"system": "You are {{lead.businessName}}'s account manager. Write in a friendly, concise tone.",
"prompt": "Draft a 3-sentence reply to this inbound message. Propose a 15-minute call.\n\nMessage: {{email.bodyText}}",
"outputVar": "draftReply",
"maxTokens": 300
}
Pipe {{variables.draftReply}} into a Send Email node's body field.
---
| Provider | Best for | Speed | Cost |
|---|---|---|---|
| Claude | Nuanced reasoning, long documents, code | Fast | Medium |
| GPT-4o | Broad capability, multimodal, function calling | Fast | Medium |
| Gemini 1.5 Pro | Very long contexts (1M tokens), multilingual | Medium | Low |
---
- Set
temperature: 0.1for classification tasks — you want consistent labels, not creative variation - Use the
systemfield to fix the persona and response format; it saves tokens on the prompt itself - Chain two LLM nodes: first extract structured data (
ai.extract), then generate copy using the extracted values - The node stores raw text. If you need JSON, add
"Respond with valid JSON only".to your system prompt, then parse with adata.codenode