Skip to content

Never stop coding. Free MIT AI gateway: one endpoint, 375 providers (150+ free), 1,400+ models Kimi, Claude, GPT, Gemini, GLM, DeepSeek, MiniMax. Works with Claude Code, Codex, Cursor, OpenCode, Cline & Copilot. Quota-aware auto-fallback, RTK+Caveman compression saves 15-95% tokens, MCP/A2A, Desktop/PWA. Built by 900+ contributors

5.6 KB
Raw Blame

title: "Quick Start: Get OmniRoute Running in 3 Minutes" version: 3.8.50 lastUpdated: 2026-08-06

Quick Start: Get OmniRoute Running in 3 Minutes

TL;DR: Install → Connect an eligible provider → Point your IDE to OmniRoute. Done.


Step 1: Install OmniRoute

Choose your preferred method:

Option A: npm (Recommended)

npm install -g omniroute

Option B: Docker

docker run -d --name omniroute -p 20128:20128 diegosouzapw/omniroute:latest

:latest is the highest published stable SemVer. It does not track git main. Pin diegosouzapw/omniroute:X.Y.Z for GitOps. See Image Tags / Release Channels.

Option C: From Source

git clone https://github.com/diegosouzapw/OmniRoute.git
cd OmniRoute
npm install
npm run dev

Step 2: Start OmniRoute

omniroute

OmniRoute starts at http://localhost:20128. The dashboard opens automatically.


Step 3: Connect an Eligible Provider

Choose a provider whose terms and quota fit your needs. In Dashboard → Providers, connect your own account or API key, then test the connection. Free access and keyless availability are not guaranteed.

auto excludes providers marked tos: avoid, including Kiro, by default. Connecting an account does not change that policy. The opt-in in Dashboard → Combos applies to all auto combos. Review the Free Tiers Guide before choosing a provider.


Step 4: Verify It Works

From API Keys, create a new key. Store this key since it will not appear again. Do note that this key is for tools to access OmniRoute, not to access upstream providers.

curl http://localhost:20128/v1/models -H "Authorization: Bearer YOUR_KEY"

You should see your connected models listed.


Step 5: Point Your IDE or CLI to OmniRoute

In your IDE or CLI tool, set:

Base URL: http://localhost:20128/v1
API Key:  [copy from Dashboard → Endpoints]
Model:    auto

That's it! Your IDE now uses OmniRoute with automatic provider selection.

IDE Example: VSCode/Continue.dev

  1. In VSCode, install the Continue.dev extension.
  2. Update your ~/.continue/config.yaml to add the following lines:
  - name: OmniRoute - Auto
    provider: openai
    model: auto
    apiBase: http://localhost:20128/v1
    apiKey: <YOUR_KEY>
  1. In the Continue.dev chat pane, select OmniRoute - Auto and you will make requests to OmniRoute.
  2. (Optional) Exercise for the reader - have your IDE update the config.yaml with all the other prebuilt configurations 😊

CLI Example: Codex CLI

  1. In your operating system, set the environment variable persistently. For macOS/Linux (add to your ~/.bashrc or ~/.zshrc):
export OMNIROUTE_API_KEY="<YOUR_KEY>"

For Windows (Command Prompt):

setx OMNIROUTE_API_KEY <YOUR_KEY>
  1. Now let's launch Codex, but configured for OmniRoute. Run:
omniroute launch-codex --model auto

You can do this manually via codex and command line parameters to specify endpoint and api key, but with the above command, OmniRoute takes care of everything for you.

The same one-command launch works for other CLIs via the generic launcher — omniroute run <target> supports claude, codex, aider, goose, opencode, qwen, and gemini (see CLI Integrations).

  1. The CLI should be sending requests to OmniRoute now.

Confirm your tool is routing to OmniRoute

You can see the details of the request by clicking Monitoring/Logs from the left sidebar. Clicking through shows you more details. As a side note, you can see what info gets sent up from your favorite harness. This is helpful from an educational and debugging perspective.


What's Next?


Common Questions

"Do I need an API key?"

The OmniRoute API key authenticates your tools. Upstream credentials depend on the provider: some require an API key or account login. Free access is not guaranteed.

"What is auto?"

auto tells OmniRoute to automatically pick the best provider for each request. It considers speed, cost, quality, and availability. See the Auto-Combo Guide for details.

"How much does it cost?"

OmniRoute itself is free and open-source. You only pay for the providers you use. Many providers have free tiers — see the Free Tiers Guide.

"Can I use it with Claude Code / Cursor / Copilot?"

Yes! OmniRoute works with any tool that supports OpenAI format. Just set the base URL to http://localhost:20128/v1. See the CLI Tools Guide for specific setup instructions.

"What if a provider goes down?"

OmniRoute automatically skips failed providers and tries the next one. You don't need to do anything. See the Auto-Combo Guide for details.


Need Help?