Actions24
- Agent Chat
- Generate
- Image Edit
- Virtual Try-On
- Chat Completions (OpenAI-Compatible)
- Messages (Anthropic-Compatible)
- Count Tokens (Anthropic-Compatible)
- List Models
- Conversations: Delete
- Conversations: List or Get
- Conversations: Save
- Knowledge Graph: Delete Node
- Knowledge Graph: List Graphs
- Knowledge Graph: Process
- Knowledge Graph: Query
- Knowledge Graph: Update Node
- Leads: Discover and Analyze
- Live Token: Mint Ephemeral Token
- SEO: Analyze Topic
- SEO: Generate Output
- SEO: Generate Subtopics
- SEO: Refine Output
- Video: Get Status
- Video: List
Messages (Anthropic-Compatible)
AI-generatedSummary
Sends raw Anthropic Messages API requests to the AI Hub’s /v1/messages endpoint using the selected model, message array, and token limit. Use it to pass provider-native conversation data, such as messages built in another node or by an SDK.
Inputs
- Model Name or ID (required) — Select or enter a Gemini, Claude, or Amazon Nova model ID.
- Messages (required) — JSON array of message objects in the endpoint’s raw Anthropic-compatible wire format. Can be passed in with an expression.
- Max Tokens (required) — Maximum number of tokens to generate; defaults to 1024.
- Options — Optional request fields: Stream (defaults to false), System prompt as JSON, Tool Choice as JSON, and Tools as a JSON array. Fields are sent when populated.
- Simplify Output — Defaults to true. Controls whether the response is cleaned up or returned in its raw form.
Output shape
A single n8n item per input item containing the API response in json.
With Simplify Output enabled, the response is simplified according to the operation’s response handler; otherwise the raw response is returned. JSON-typed inputs may be supplied as JSON strings or objects/arrays; invalid JSON strings raise an error before the request.
Examples
Example 1: Send a conversation built upstream
Provide the selected model, a JSON messages array, and Max Tokens. Optionally pass system instructions and tool definitions through Options.
