LLM Fundamentals
How large language models work, how to choose a model, and how to handle keys and billing safely.
3 articles · about 48 minutes of reading
- How LLMs Work: Tokens, Context Windows, Statelessness, and ReasoningA developer's mental model of LLMs: tokens, next-token prediction, the context window, why the API is stateless, and how reasoning works, with runnable code.Difficulty: Beginner18 min read
- Choosing LLMs and Providers: Capability vs Cost vs LatencyHow to pick an LLM per feature by capability, cost, and latency: the current Claude lineup, effort levels, routing, and a harness to benchmark your own tasks.Difficulty: Beginner15 min read
- LLM API Keys, Billing, and Security for Web DevelopersKeep LLM API keys server-side, understand token-based billing, compute the cost of every call, and enforce per-user budgets, timeouts, and retries in Node.js.Difficulty: Beginner15 min read