Large language models are neural networks trained on enormous text corpora — books, articles, code, and web content. They learn statistical patterns of language and can predict the next token in a sequence, which enables them to generate coherent text, answer questions, summarize documents, and follow instructions when fine-tuned or prompted correctly.

Models like Claude, GPT, and Llama vary in size, capability, and cost. Smaller models run faster and cheaper but may lack nuance; larger models handle complex reasoning but require more compute. For production systems, the choice depends on latency requirements, accuracy needs, and budget. LLMs are the foundation of most current AI applications.