Get started
Connect a free LLM to your editor in minutes. Pick how you want to run models, then choose your editor.
Free API
Use Groq or stack Groq + OpenRouter + Gemini. No GPU required.
Open guide →Local model
Run models on your machine with Ollama and point your editor at localhost.
Open guide →Popular next steps
- Stack free API keys
- Free models in Cline, Kilo Code and OpenCode
- Groq retired Llama — replacements
- Install vLLM on Linux
- Llama 3.3 free API
- Gemini 3.8 Flash free API
Install editors
- Install Cursor on Windows
- Install Cursor on macOS
- VS Code + Continue (install steps inside the guide)