API and local models · 1x1labs.ai

Learn the two ways a developer uses an LLM: (1) API — send a request, pay per token, no GPU needed; (2) local — download an open model and run it with Ollama on your laptop (free and private, but smaller and slower). Many tools, including Ollama, use the same OpenAI-style API, so code can switch between them easily. Store API keys in environment variables, never in code.