Quick Start
Deploy ModelRouter, configure model channels and tokens, and make your first AI API call.
ModelRouter is an open-source AI gateway and model API management system. Follow these steps to go from deployment to application integration.
Start using ModelRouter
1. Deploy your instance
Start ModelRouter with Docker, a management panel, or a cluster.
2. Configure a channel
Add a model provider, credentials, and available models.
3. Create an API token
Create a token for your application and call the unified AI API.
Choose a deployment method
Docker Compose
Run ModelRouter alongside services such as MySQL and Redis.
Docker single container
Get started with a Docker image for evaluation or small deployments.
Need a management panel, cluster, or local development environment? See all deployment methods.
Explore the documentation
User guide
Manage your instance, channels, tokens, and models.
API reference
Find request parameters, response formats, and examples.
AI applications
Connect AI clients and development tools.
Skills
Use and manage ModelRouter with AI coding agents.
Help & support
Find answers, troubleshoot, and join the community.
Business cooperation
Learn about collaboration and commercial services.
Explore the project and ecosystem on the ModelRouter official website.
Last updated on