Cursor

Cursor ▸ Settings ▸ Models:
1. Paste your key into "OpenAI API Key": <YOUR_API_KEY>
2. Enable "Override OpenAI Base URL" → https://api.groq.com/openai/v1
3. Add a custom model name → llama-3.3-70b-versatile
4. Click "Verify", then enable the model.

Note: Cursor's override expects an OpenAI-compatible endpoint.

You are being set up to use a free LLM API as your model backend.

Provider:     Groq
Base URL:     https://api.groq.com/openai/v1
Model:        llama-3.3-70b-versatile
Auth:         Bearer token (OpenAI-compatible)
Key env var:  GROQ_API_KEY

Task:
1. Configure Cursor to call the endpoint above using the OpenAI Chat Completions format.
2. Read the API key from the GROQ_API_KEY environment variable. Do NOT
   ask me to paste the key in plain text in this chat — I will set it in my env.
3. If a setting requires a base URL, use exactly: https://api.groq.com/openai/v1
4. Send one short test message ("ping") and report back whether the call
   succeeded, including the model name and latency.

If anything is missing (e.g. an account ID for the base URL), ask me for just
that value and nothing else.