9Router
Self-hosted AI model router that rotates requests across 40+ providers with automatic fallback, exposing an OpenAI-compatible endpoint for coding agents.
How to deploy
Deploy 9Router on Notploy
- Install Notploy on your server if you haven't already.
- In your Notploy panel, open a project and click Create Service → Template.
- Search for 9Router and click Create — Notploy configures domains, environment variables, and volumes for you.
Alternatively, create a Compose service, go to Advanced → Import from Base64, and paste this payload:
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
Reference files
Configuration
The exact Docker Compose and template configuration this template deploys.
More like this
Related Templates
FreeLLMAPI
Version v0.8.4
FreeLLMAPI aggregates free tiers from 29 LLM providers into a single OpenAI-compatible endpoint with smart routing, automatic failover, per-key rate tracking, and encrypted key storage.
Corsfix
Version 8899bb15e71c7238285ccefc4c95a0cd47daeaf0
Corsfix is an open source CORS proxy platform for fetching APIs from browser applications, with origin and target allowlists, encrypted API secrets, response caching, and a management dashboard.
Engram
Version 1.16.3
Persistent memory for AI coding agents — self-hosted Engram Cloud sync server with a web dashboard, backed by PostgreSQL.
Junctio
Version 0.2.1
Self-hosted MCP gateway that puts stdio, Docker and remote MCP servers behind one endpoint per client, with API key or OAuth downstream auth and upstream tokens refreshed before they expire.
LiteLLM
Version main-stable
LiteLLM is a lightweight OpenAI API-compatible proxy for managing multiple LLM providers with a single endpoint.
Multica
Version latest
Multica is an open-source managed agents platform for teams. Assign tasks to AI coding agents (Claude Code, Codex, OpenClaw and more) that execute autonomously, report progress, and build reusable skills over time.
Free and open source
Self-host 9Router in minutes
Notploy is a free, open source deployment platform. Deploy 9Router and 571+ other templates on your own infrastructure with a single click.