This is an n8n community node. It lets you use CometAPI in your n8n workflows.
CometAPI is a powerful AI language model service that provides OpenAI-compatible API endpoints for various large language models, enabling developers to integrate advanced AI capabilities into their applications.
n8n is a fair-code licensed workflow automation platform.
Installation
Operations
Credentials
Compatibility
Usage
Resources
Follow the installation guide in the n8n community nodes documentation.
The CometAPI node supports chat completions using various AI language models:
- Model Selection: Choose from available models (default: gpt-4o-mini)
- Message Management: Support for multi-turn conversations with user, assistant, and system roles
-
Advanced Parameters:
- Temperature: Control randomness (0-2, default: 0.7)
- Max Tokens: Set maximum response length (up to 32,768 tokens)
- Top P: Control diversity via nucleus sampling (0-1, default: 1)
- Frequency Penalty: Reduce repetition (-2 to 2, default: 0)
- Presence Penalty: Encourage new topics (-2 to 2, default: 0)
- Stream: Enable streaming responses (default: false)
To use this node, you need to authenticate with CometAPI:
- Sign up for a CometAPI account at CometAPI Console
- Generate an API key from your console dashboard
- In n8n, create new CometAPI credentials and enter your API key
- API Key: Bearer token authentication using your CometAPI API key
- Minimum n8n version: 1.0.0
- Node.js version: 20.15 or higher
- Tested with: Latest stable versions of n8n
This node is compatible with all n8n deployment methods including:
- Self-hosted n8n instances
- n8n Cloud
- Docker deployments
- Add the CometAPI node to your workflow
- Configure your CometAPI credentials
- Set up your messages:
- System message: Define the AI's behavior (optional)
- User message: Your prompt or question
- Choose your preferred model (e.g., gpt-4o-mini)
- Execute the workflow
- Content Generation: Create articles, summaries, or creative content
- Data Analysis: Analyze and interpret data with AI assistance
- Customer Support: Build intelligent chatbots and support systems
- Code Review: Get AI feedback on code quality and suggestions
- Translation: Translate text between different languages
For more control over the AI responses, you can adjust:
- Temperature: Lower values (0.1-0.3) for more focused responses, higher values (0.7-1.0) for more creative outputs
- Max Tokens: Limit response length to control costs and response time
- Frequency/Presence Penalty: Fine-tune repetition and topic diversity