To configure Cursor with an OpenAI-compatible API provider, the API key and Base URL must come from the same platform. For RutaAPI, use https://api.rutaapi.com/v1 as the Base URL, create an API key in the RutaAPI dashboard, verify the key with /v1/models, and copy one returned model name into Cursor as the model name. Do not paste the website URL, dashboard URL or a full chat completions endpoint as the Base URL.
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.
What Cursor asks for When you configure Cursor to use a custom OpenAI-compatible provider, Cursor typically asks for three things: a Base URL, an API key, and a model name. All three must belong to the same provider. If you enter a Base URL from one platform and an API key from another, the connection will fail with a 401 error.
What the API key means The API key is a secret token that identifies your account. It is generated by the provider and must be kept private. Never paste it into screenshots or shared scripts. If the key is exposed, rotate it immediately from the provider dashboard.
What the Base URL means The Base URL is the root address of the API gateway. It tells Cursor where to send requests. The correct RutaAPI Base URL is https://api.rutaapi.com/v1 — it ends in /v1 and points to the API root, not the dashboard or the marketing site.
What the model name means The model name identifies which AI model handles your request. It must match one of the models returned by /v1/models for your account. Do not guess the model name — identifiers differ between providers. Always copy from the /v1/models response.
Cursor version caveat Cursor UI, model settings and external provider behaviour can change by version and plan. Some third-party integration docs show the pattern of overriding the OpenAI Base URL and adding a custom model, but users should verify the current Cursor UI and behaviour in their own version before relying on a setup.
RutaAPI disclaimer RutaAPI is an OpenAI-compatible API gateway. It is not an official OpenAI, Cursor, Anthropic, Google or Microsoft service. Model availability and rates depend on your account configuration and upstream providers.
How to start with RutaAPI
Step 1 — Create a RutaAPI account
Register at app.rutaapi.com. No credit card is required to sign up.
Step 2 — Add prepaid credits
Purchase a credit pack from the billing section. Credits are added immediately after payment. Requests without sufficient credits return 401 or 403.
Step 3 — Create an API key
Go to the Tokens section and create a new key. Copy it right away — it is shown only once at creation.
Security: Never paste your full API key into screenshots or shared scripts. If exposed, rotate it immediately from the dashboard.
Step 4 — Verify /v1/models
Before configuring Cursor, confirm the key works by calling /v1/models:
A 200 response with a model list means the key is valid. A 401 response means the key is wrong or revoked.
curl https://api.rutaapi.com/v1/models \
-H "Authorization: Bearer YOUR_RUTAAPI_KEY"Step 5 — Copy a returned model name
Use one of the model id values from the /v1/models response as MODEL_NAME. Do not guess — identifiers differ between providers.
Run /v1/models and copy the exact id string. The model field in Cursor must match one of the returned model identifiers.
Step 6 — Configure Cursor
In Cursor settings, look for API key or model provider settings related to OpenAI-compatible or custom OpenAI API usage. If your Cursor version provides an option such as Override OpenAI Base URL or Custom API Base URL, enter:
Then paste your RutaAPI API key where the OpenAI-compatible API key is expected, and add or select the model name returned by /v1/models. Do not use https://rutaapi.com, https://app.rutaapi.com, or https://api.rutaapi.com/v1/chat/completions as the Base URL.
https://api.rutaapi.com/v1Step 7 — Send a small test request
Before running any coding tasks, send a simple request to confirm end-to-end connectivity:
A successful response confirms the key, Base URL, model name and credits are all working correctly.
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 developers and AI users who want to configure Cursor or Cursor Composer to use an OpenAI-compatible API gateway provided by RutaAPI.
It helps if you are familiar with API keys, Base URLs and making HTTP requests from a terminal.
Who should not use this setup
- Users whose Cursor plan does not support external OpenAI-compatible provider configuration.
- Users who require official OpenAI or Anthropic-only features not exposed by the gateway.
- Users whose tool does not support custom API endpoints.
Testing before you start coding
Before running any Cursor coding tasks, send a simple request from the terminal to confirm your key, Base URL and model name all work together. This rules out configuration issues before you start a real session.
If the first request succeeds, the Cursor configuration should also work. If it fails, fix the terminal request first — that gives you clearer error messages than the Cursor UI.
How to pick a model name
Model names are returned by the GET /v1/models endpoint. Copy one of the model id values from the response and use it as the model field in your request and in Cursor settings.
Model availability is per-account. If a model name is not in your /v1/models response, it is not active in your account — add more credits or contact support.
Common errors
401 Unauthorized / invalid API key
The API key is missing, incorrect, or sent to the wrong Base URL. Verify the 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 name 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 or contact support if persistent.
When RutaAPI may be a good fit
- You need an OpenAI-compatible Base URL
- You want prepaid API credits
- You want to verify available models with /v1/models
- You need Cursor, Codex CLI and Claude Code setup docs
- You want usage visibility before scaling
When RutaAPI may not be the right fit
- Cursor does not support external provider configuration in your version or plan
- You require official OpenAI-only features
- The selected model is unavailable upstream
Related setup guides
- Codex CLI setup with RutaAPI
- Claude Code setup with RutaAPI
- Unified Base URL guide
- Available models
- Pricing and credit packs
FAQ
What Base URL should I use for RutaAPI in Cursor?
Use https://api.rutaapi.com/v1 — the /v1 path is the OpenAI-compatible API root. Always include /v1. Do not use https://rutaapi.com, https://app.rutaapi.com, or any path ending in /chat/completions.
Should the Cursor Base URL include /v1?
Yes. The correct RutaAPI Base URL is https://api.rutaapi.com/v1. Without /v1, you are pointing to a non-API endpoint and will get 404 or 401 errors.
Can I use https://rutaapi.com as the Base URL?
No. https://rutaapi.com is the marketing site, not the API root. Using it as the Base URL will result in errors. Always use https://api.rutaapi.com/v1.
Where do I get my RutaAPI API key?
Create one from the RutaAPI dashboard at https://app.rutaapi.com in the Tokens section. Keys are shown only once at creation — copy and store them securely.
How do I know which model name to use?
Run GET /v1/models with your API key and use one of the model id values from the response. Do not guess — model identifiers differ between providers.
Why does Cursor show invalid API key?
An invalid_api_key or 401 error usually means the API key does not match the Base URL, or it was sent to the wrong endpoint. Verify that both the key and Base URL come from the same platform. Run /v1/models to confirm the key is valid.
Can a wrong Base URL cause 401?
Yes. If the Base URL belongs to a different provider than the API key, the provider rejects the key with 401. The key and Base URL must come from the same platform.
What does 403 mean?
HTTP 403 means the key exists but lacks permission. Check that your account has enough prepaid credits and that the model is enabled for your account tier.
What does 404 model not found mean?
HTTP 404 means the model name is not recognised at that endpoint. Run /v1/models and use one of the returned model id values as the model name. Do not guess.
What does 429 mean?
HTTP 429 means you have hit a rate or concurrency limit. Lower the number of concurrent requests, pause parallel tasks and retry after a short pause.
What does 503 mean?
HTTP 503 means the provider route is temporarily unavailable. Try a short request, check model availability, and contact support if the issue persists.
Is RutaAPI an official Cursor or OpenAI service?
No. RutaAPI is an OpenAI-compatible API gateway operated by BDR FIDUCIARY LLC. It is not an official service of Cursor, OpenAI, Anthropic, Google or Microsoft.
Should I paste my API key into screenshots?
No. Never share your full API key in screenshots, forum posts or any public or shared channel. If exposed, rotate it immediately from the dashboard.
What should I send to support?
Include: request time (UTC), model name, error code, Base URL, any request ID from response headers, and approximate request size. Do not share your full API key. Describe the key prefix if needed.