Self-host with Docker ยท Yantr
Bifrost
High-performance AI gateway with a web UI and OpenAI-compatible API.
1
Ports
2
Notes
3
Use Cases
About
What Bifrost does
Bifrost is a self-hosted AI gateway that routes requests across many model providers through a single OpenAI-compatible API. It includes a built-in web UI for configuration, monitoring, failover, load balancing, and caching so teams can manage LLM traffic from one place.
Install Flow
How to self-host Bifrost
Bifrost can be deployed with standard Docker Compose using the Yantr app catalog. This page collects the basic information searchers usually need first: what Bifrost does, which Docker image Yantr uses, default ports, deployment notes, and where to find the original compose template.
After deployment, Yantr lets you publish additional ports from the stack page using Docker-style syntax. Use 8080:8080 for a fixed host port or just 8080 to let Docker assign a random port.
Use Cases
What people run it for
- Route OpenAI-compatible traffic across multiple LLM providers from one endpoint.
- Configure providers, budgets, and fallbacks through the built-in web UI.
- Add observability, caching, and failover to self-hosted AI workloads.
Technical Details
Ports, image, and service metadata
Ports
| Port | Protocol | Label |
|---|---|---|
| 8080 | HTTP | Web UI |
Docker Image
maximhq/bifrost:latest
Service Name
bifrost
Notes
Things to know before you deploy
- Provider API keys still need to be configured after deployment.
- App data is stored in a Docker volume mounted at /app/data.
Related Apps
More tools you might pair with Bifrost
Page generated 2026-07-27T04:28:00.415Z