Short answer: Drop the "Anthropic → Create Message" action anywhere in your workflow, map the inputs from upstream nodes, and publish.
Every field can be mapped from an upstream trigger, AI step, table row, or hard-coded literal.
| Field | Type | Required | Description |
|---|---|---|---|
Model model | options | Required | Which Claude model to use |
Message message | string | Required | The user message to send to Claude |
System Prompt system | string | Optional | Instructions that shape how Claude responds |
Max Tokens max_tokens | string | Required | Maximum number of tokens in the response (required by Anthropic API) |
Temperature temperature | string | Optional | Controls randomness (0 = deterministic, 1 = creative). Default is 1. |
{"model": "{{trigger.model}}","message": "e.g. Summarize this document...","system": "e.g. You are a helpful assistant that responds concisely.","max_tokens": "1024","temperature": "e.g. 0.7"}
{"id": "msg_abc123","role": "assistant","type": "message","model": "claude-sonnet-4-20250514","usage": {"input_tokens": 10,"output_tokens": 25},"content": [{"text": "Hello! How can I help you?","type": "text"}],"stop_reason": "end_turn"}
Use these fields in downstream nodes for routing, logging, or error handling.
Any of these apps can fire this action as part of a workflow.
Triggered by anything in the catalog. Free tier available. No credit card.