Open WebUI OpenAI-Compatible API Setup with Base URL and API Key

Before you start

You need a RutaAPI account, a prepaid credit pack, and an API key. Make sure your account has credits before making requests — requests without sufficient credits will return a 401 or 403 error.

How to start with RutaAPI

curl https://api.rutaapi.com/v1/models \
  -H "Authorization: Bearer YOUR_RUTAAPI_KEY"

Base URL: https://api.rutaapi.com/v1
API key: YOUR_RUTAAPI_KEY

curl https://api.rutaapi.com/v1/chat/completions \
  -H "Authorization: Bearer YOUR_RUTAAPI_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "MODEL_NAME",
    "messages": [
      {"role": "user", "content": "Hello from RutaAPI"}
    ]
  }'

Who this guide is for

This guide is for Open WebUI users who want to connect their self-hosted chat interface to an OpenAI-compatible API gateway provided by RutaAPI.

It helps if you are familiar with Base URL, API key, model ID, and the Open WebUI admin settings panel.

Who should not use this setup

• Users whose Open WebUI version does not support OpenAI-compatible provider connections.
• Users whose Open WebUI instance is configured to block external providers.
• Users who require official OpenAI-only features.

Testing before you start chatting

Before starting a chat session in Open WebUI, send a simple request from the terminal to confirm your key, Base URL and model IDs all work together. This rules out configuration issues before you begin.

If the first request succeeds, the Open WebUI connection should also work. If it fails, fix the terminal request first — that gives you clearer error messages than the Open WebUI UI.

How to find model IDs

Model IDs are returned by the GET /v1/models endpoint. Copy one or more of the model id values from the response.

If Open WebUI auto-detects models from /v1/models, you may not need to enter them manually. If auto-detection does not work, add the copied IDs to the Model IDs field in the connection settings.

Model availability is per-account. If a model ID is not in your /v1/models response, it is not active in your account — add more credits or contact support.

Common mistakes

• Using https://rutaapi.com as the Base URL — that is the marketing site, not the API root.
• Using https://app.rutaapi.com as the Base URL — that is for account management, not the API.
• Using https://api.rutaapi.com without /v1 when Open WebUI expects an OpenAI-compatible /v1 endpoint.
• Pasting https://api.rutaapi.com/v1/chat/completions as the Base URL — that is an endpoint, not the root.
• Setting a RutaAPI key but keeping another provider's URL.
• Setting the Base URL correctly but using an API key from another platform.
• Guessing model IDs instead of using /v1/models.
• Forgetting to save or reconnect after changing settings.
• Exposing API keys in screenshots or public repositories.

Common errors

401 Unauthorized / invalid API key

The API key is missing, incorrect, or sent to the wrong Base URL. Verify the API key and Base URL both come from RutaAPI. Run /v1/models to confirm the key is valid.

403 Forbidden

The key exists but lacks permission. Check credits and model access in your RutaAPI account.

404 Model not found

The model ID is not in your account. Run GET /v1/models and copy a returned model id.

429 Too Many Requests

Rate or concurrency limit. Lower the number of concurrent requests and retry.

503 Service Unavailable

The provider route is temporarily unavailable. Try a short request, check model availability, contact support if persistent.

Visible FAQ

How do I connect Open WebUI to an OpenAI-compatible API?

Open WebUI connects to an OpenAI-compatible API when you add the provider connection, enter the Base URL, paste the API key, and confirm the model ID returned by /v1/models.

What Base URL should I use in Open WebUI?

Use https://api.rutaapi.com/v1. Do not use the marketing site, dashboard URL, or a direct endpoint like /v1/chat/completions.

Where do I enter the API key in Open WebUI?

Paste the key into the API key field inside the OpenAI-compatible provider settings or connection form in Open WebUI.

Why does Open WebUI show connection error, 401, or model not found?

These errors usually mean the Base URL, API key, and model ID do not belong to the same provider, or the model is not returned by /v1/models.

Should the Base URL include /v1?

Yes. Open WebUI expects the OpenAI-compatible API root, so the Base URL should include /v1.

Related setup and troubleshooting guides

• API Key and Base URL explained
• Unified Base URL for AI coding tools
• Cloudflare 503 AI API error troubleshooting
• LobeChat custom OpenAI API setup guide
• NextChat custom API setup guide
• Pricing and credit packs