Overview
This node interacts with the OpenRouter API to send chat messages to a specified chat model. It is useful for automating conversations, generating responses, or integrating AI chat capabilities into workflows. For example, it can be used to create a customer support chatbot, generate creative writing prompts, or assist with information retrieval based on user input.
Use Case Examples
- Sending a user message to an AI chat model and receiving a generated response.
- Setting a system prompt to guide the assistant's behavior before sending user messages.
- Adjusting parameters like temperature and max tokens to control the creativity and length of the responses.
Properties
| Name | Meaning |
|---|---|
| Model Name or ID | Specifies the chat model to use for generating responses. Can be selected from a list or provided as an ID. |
| System Prompt | A system message that sets the behavior or context of the assistant before user messages are processed. |
| Message | The user message to send to the chat model for generating a response. |
| Temperature | Controls the randomness of the output. Higher values produce more creative responses. |
| Additional Fields | Optional parameters to fine-tune the chat completion, including frequency penalty, max tokens, presence penalty, and top_p sampling. |
Output
JSON
response- The generated chat response from the OpenRouter API.
Dependencies
- Requires an API key credential for OpenRouter API authentication.
Troubleshooting
- Common issues include invalid or missing API key, resulting in authentication errors.
- Invalid response format errors may occur if the API response does not contain the expected message content.
- Network or request errors can happen if the OpenRouter API endpoint is unreachable or returns an error status.
Links
- OpenRouter Chat Completions API - Official API endpoint documentation for sending chat messages and receiving completions.
- n8n Expressions Documentation - Guide on how to use expressions in n8n to dynamically set property values.