Otari Gateway is the open-source gateway that puts a single OpenAI-compatible API in front of many LLM providers.
Run it in your own infrastructure. Use it standalone, or connect it to otari.ai for hosted routing, authentication, and usage reporting.
Looking for the hosted product instead? Start with the Otari quickstart.
Gateway at a glance
One API
Route requests to 40+ providers through a single OpenAI-compatible endpoint.
Runs in your infrastructure
Deploy the gateway yourself and keep the request path close to your applications.
Works standalone or with otari.ai
Manage everything locally, or connect the same gateway to otari.ai for hosted routing and usage reporting.
Start here
🚀 Deployment: Run the gateway with Docker in either standalone or connected mode.
📄 Configuration file: Set up config.yml and core gateway settings.
🔑 Environment variables: Override gateway settings and configure credentials with environment variables.
🔌 Configure providers: Add provider credentials and provider-specific settings.
⚙️ Modes: Learn about Otari Gateway operating modes: standalone and connected.
🧠 Models & Providers: See provider support, model formats, and gateway capabilities.