Documentation

Everything you need to get started

Comprehensive guides, API references, and examples to help you deploy AI models on serverless GPUs.

Documentation sections

Deploy your first model in under 5 minutes. Step-by-step tutorial covering installation, configuration, and deployment.

Understand deployments, endpoints, autoscaling, GPU selection, and billing. Architecture deep-dives and best practices.

Complete REST API documentation with code examples in Python, Node.js, and cURL. Authentication, endpoints, and responses.

Command-line interface documentation. Deploy, monitor, debug, and manage your infrastructure from the terminal.

Production-ready examples for popular frameworks. Transformers, Stable Diffusion, LangChain, custom PyTorch models.

Common issues, debugging techniques, performance optimization, and how to get help from our support team.

1
Install the CLI
Install the Демо CLI with pip or npm. Authenticate with your API key and verify your setup.
2
Prepare your model
Write an inference function and create a requirements file. Test locally before deploying.
3
Deploy to production
Use demo deploy to push your model live. Monitor the deployment and verify your endpoint.

Need Help?

Our documentation is continuously updated based on user feedback. Can't find what you need? Reach out to our team.