Runpod Public Endpoints

AI & Machine Learning Cloud & Infrastructure

v1.1.0

Last updated Nov 25, 2025

n8n Community Node: Runpod Public Endpoints

6 Weekly Downloads

184 Monthly Downloads

View on NPM GitHub Repository

Included Nodes

Runpod Public Endpoints

Description

n8n Community Nodes: Runpod

A powerful n8n Community Node that provides seamless integration with Runpod's Public Endpoints API. Generate text, images, videos, and audio using cutting-edge AI models with dynamic model discovery and smart categorization.

🚀 Features

🔄 Dynamic Model Discovery – Automatically fetches all available Runpod models via GraphQL API
🎯 Smart Categorization – Models automatically sorted by Text/Image/Video/Audio
⚡ Performance Optimized – 5-minute caching reduces API calls
🛡️ Robust Error Handling – Fallback to hardcoded models if API fails
📝 Built-in Examples – Pre-configured JSON templates for each model type
🔐 Secure Authentication – API key stored securely in n8n credentials
🎨 Clean UI – Custom icon and intuitive interface

📦 Installation

Method 1: npm (Recommended)

npm install @runpod/n8n-nodes

Method 2: n8n Community Nodes

Go to Settings → Community Nodes in your n8n instance
Click Install a community node
Search for @runpod/n8n-nodes
Click Install

Method 3: Manual Installation

# Clone the repository
git clone https://github.com/runpod/n8n-nodes.git
cd n8n-nodes

# Install dependencies
npm install

# Build the node
npm run build

# Link to n8n (for development)
npm link

🔧 Setup

1. Get Your Runpod API Key

Sign up at Runpod
Go to Settings → API Keys
Create a new API key
Copy the key (starts with rpa_)

2. Configure Credentials in n8n

In n8n, go to Credentials → Add Credential
Search for Runpod API
Enter your API key
Test the connection

🎯 Usage

Basic Workflow

Add the Node – Search for "Runpod Public Endpoints" in the nodes panel
Select Operation – Choose from:
- Generate Text – Chat models (Granite, Qwen3, Deep Cogito)
- Generate Image – Diffusion models (Flux, Qwen Image, Seedream)
- Generate Video – Video models (WAN, Seedance, Kling, Sora)
- Generate Audio – Audio models (Whisper, Minimax)
- Get Status – Check async job status
Choose Model – Dropdown automatically shows relevant models
Configure Input – Use built-in examples or customize JSON
Execute – Run your workflow!

Example Operations

Text Generation

{
  "messages": [
    {
      "role": "system",
      "content": "You are a helpful assistant."
    },
    {
      "role": "user",
      "content": "What is Runpod?"
    }
  ],
  "sampling_params": {
    "max_tokens": 512,
    "temperature": 0.7,
    "seed": -1,
    "top_k": -1,
    "top_p": 1
  }
}

Image Generation

{
  "prompt": "A serene mountain landscape at sunset",
  "negative_prompt": "blurry, low quality",
  "width": 1024,
  "height": 1024,
  "num_inference_steps": 20,
  "guidance": 7.5,
  "seed": 42,
  "image_format": "png"
}

Video Generation

{
  "prompt": "A serene morning in an ancient forest, golden sunlight filtering through tall pine trees",
  "num_inference_steps": 30,
  "guidance": 5,
  "negative_prompt": "",
  "size": "1280*720",
  "duration": 5,
  "flow_shift": 5,
  "seed": -1,
  "enable_prompt_optimization": false,
  "enable_safety_checker": true
}

🔄 Async Operations

For long-running tasks (video generation, complex images), use async mode:

Set Wait for Completion to false
Execute – Returns a job ID
Use Get Status operation to check progress
Poll until status is COMPLETED

📚 Supported Models

Text Models

Granite 4.0 H Small – IBM's latest language model
Qwen3 32B AWQ – Alibaba's efficient language model
Deep Cogito v2 Llama 70B – Large-scale reasoning model
InfiniteTalk – Conversational AI model

Image Models

Flux Dev/Schnell – Stability AI's latest diffusion models
Qwen Image – Alibaba's text-to-image model
Seedream 4.0 – Advanced image generation
Nano Banana Edit – Image editing capabilities

Video Models

Sora 2 Pro I2V – OpenAI's latest video model
WAN 2.5 – High-quality video generation
Seedance 1.0 Pro – Professional video creation
Kling v2.1 – Advanced video synthesis

Audio Models

Whisper V3 Large – OpenAI's speech recognition
Minimax Speech 02 HD – High-definition speech synthesis

🛠️ Development

Prerequisites

Node.js 18+
npm or yarn
n8n instance

Setup Development Environment

# Clone repository
git clone https://github.com/runpod/n8n-nodes.git
cd n8n-nodes

# Install dependencies
npm install

# Build the node
npm run build

# Link to n8n for development
npm link

# Start n8n in development mode
n8n dev

Project Structure

src/
├── credentials/
│   └── RunpodApi.credentials.ts    # API key authentication
├── helpers/
│   └── RunpodClient.ts             # API client wrapper
└── nodes/
    └── RunpodPublicEndpoints/
        ├── RunpodPublicEndpoints.node.ts        # Main node logic
        ├── RunpodPublicEndpoints.description.ts # UI configuration
        └── runpod-cube.svg                      # Custom icon

Testing

# Run tests
npm test

# Lint code
npm run lint

# Build for production
npm run build

🤝 Contributing

We welcome contributions! Please see our Contributing Guide for details.

Development Workflow

Fork the repository
Create a feature branch
Make your changes
Add tests if applicable
Submit a pull request

📄 License

This project is licensed under the Apache License 2.0 – see the LICENSE file for details.

🔗 Links

Runpod Documentation: https://docs.runpod.io/hub/public-endpoint-reference
n8n Community Nodes: https://docs.n8n.io/integrations/community-nodes/
GitHub Repository: https://github.com/runpod/n8n-nodes
npm Package: https://www.npmjs.com/package/@runpod/n8n-nodes

🚨 Troubleshooting

Common Issues

1. "Runpod API" credential not showing

Solution: Restart n8n after installing the node
Check: Verify the node appears in Settings → Community Nodes

2. 401 Authentication Error

Solution: Verify your API key is correct and starts with rpa_
Check: Test the credential connection in n8n

3. JSON parsing errors

Solution: Use the built-in examples or validate JSON syntax
Check: Ensure no unescaped newlines in string values

4. Job stuck in IN_QUEUE

Solution: Enable "Wait for Completion" or use async polling
Check: Some models have longer queue times

5. Model dropdown empty

Solution: Check internet connection (uses GraphQL API)
Fallback: Node includes hardcoded models if API fails

Debug Mode

Enable debug logging in n8n to see detailed error messages:

N8N_LOG_LEVEL=debug n8n start

🆘 Support

Issues: GitHub Issues
Discussions: GitHub Discussions
Runpod Support: https://runpod.io/support

🙏 Acknowledgments

Runpod for providing the Public Endpoints API
n8n for the amazing workflow automation platform
Community contributors for feedback and improvements

Made with ❤️ by the Runpod team