@lbono/n8n-nodes-litellm

Overview

Wraps the LiteLLM proxy gateway, a unified interface for managing multiple LLM providers. This node enables n8n workflows to interact with a LiteLLM gateway to perform chat completions, text generation, embeddings, image creation, and audio processing.

Nodes & Operations

LiteLLM

Sends requests to a LiteLLM gateway for chat completions, text generation, embeddings, image creation, and audio tasks, and returns the API's JSON or binary responses as n8n items.

• Chat · Chat Completion — Sends a chat completion request to a LiteLLM gateway's /chat/completions endpoint with a model name and a list of role-tagged messages, and returns the gateway's full JSON response as one item per input item.
• Completion · Text Completion — Sends a text completion request to the LiteLLM gateway using a model and prompt, with optional sampling controls. Returns the gateway response as one n8n item.
• Embedding · Create Embedding — Creates an embedding for the provided text by sending the selected model and input to the LiteLLM /embeddings endpoint. Returns each item in the response’s data array as a separate n8n output item.
• Image · Generate Image — Generates images from a text prompt by sending a request to the LiteLLM image generation endpoint. Returns one output item per image, with each image’s response data in the item’s JSON.
• Audio · Text-to-Speech — Converts input text to spoken audio via the LiteLLM gateway's /audio/speech endpoint and returns the result as a binary audio file on the output item.
• Audio · Transcription — Transcribes an audio file from the incoming item’s binary data by sending it to the LiteLLM audio transcription endpoint.
• Model · List Models — Fetches the models available from the configured LiteLLM gateway. The operation sends an authenticated GET request to /models and returns each model as a separate n8n item.
• Moderation · Classify Text — Submit text to the LiteLLM moderation endpoint for content classification, optionally choosing a moderation model. The operation returns the endpoint response as one n8n item per input item.

Installation

Install as an n8n community node: in n8n, open Settings → Community nodes → Install and enter @lbono/n8n-nodes-litellm.

Links

• n8n community nodes installation guide