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
Chat Completions (OpenAI-Compatible)
AI-generatedSummary
Send raw OpenAI-compatible chat messages and optional generation or tool-calling settings to the selected model, then return the API response. Use this operation when you need to pass messages in the endpoint’s native JSON format rather than assemble them with a message builder.
Inputs
- Model Name or ID (required) — Select a model ID from the API list or provide one with an expression. The UI description identifies Gemini, Claude, and Amazon Nova model IDs.
- Messages (required) — A JSON array of message objects in the endpoint’s expected wire format. You can pass through messages created by another node or SDK.
- Options — Optional request fields: Max Tokens (omitted at 0), Stream (defaults to false), Temperature (defaults to 0.7), Tool Choice (JSON), and Tools (JSON array). Fields are sent when added.
- Simplify Output — Defaults to true; controls whether the node returns a cleaned result or the full raw API response.
Output shape
One output item per input item, containing the API response in its JSON data.
With Simplify Output enabled, the response is cleaned; with it disabled, the raw response is returned. A streaming response is requested when Stream is enabled.