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
Generate
AI-generatedSummary
Generate text or image output from a prompt, optionally using a selected model, attachments, conversation messages, and generation settings. The node sends one request per input item to the AI Hub and can return a simplified response or attach generated images as binary data.
Inputs
- Mode (required) — Choose Text (default) or Image generation. In Image mode, select an image-capable model; the prompt is sent as a user message.
- Model Name or ID — Select a model from the list or provide its ID with an expression. Leaving it empty lets the API decide for text generation; image mode requires an image model.
- Prompt — Prompt for generation. In text mode it is sent as the prompt; in image mode it becomes a user message when Advanced Messages are not supplied.
- Attachments — Add images or files such as PDFs by URL, Base64 data with a MIME type, or an input binary field (default
data). Attachments are added to the latest user message, or create one if there are no messages. - Aspect Ratio — Set the image output aspect ratio. For image generation, an unset Auto value is sent as
1:1; this setting is omitted for text mode. - Options — Optional generation settings: Batch JSON, JSON Schema and response format (text or JSON), maximum tokens, multi-turn Messages, streaming, and temperature. Added messages take precedence over Prompt. JSON Schema is used with JSON response format.
- Simplify Output — Defaults to true. Returns a cleaned result with generated text or image and related fields; turn off to receive the full API response.
- Return Images as Binary — Defaults to false. For image output, attach the generated image as binary data and remove its Base64 payload from the JSON response.
Output shape
One output item per input item, containing the API response in its json field; generated images can optionally also be attached in binary.
With Simplify Output enabled, text responses expose fields such as
text,model,finishReason,usage, and parsedjsonwhen available; image responses expose the image result. Otherwise the raw API response is returned. Array or primitive responses are wrapped underdata. Each request failure follows n8n error handling, including Continue On Fail when enabled.