{"head":{"title":"What Is an LLM (Large Language Model)? | OceanLab","description":"An LLM is an AI model trained on large amounts of text to read and write language. What it can and cannot do, how apps use one, and the mistakes to avoid.","canonical":"https://oceanlab.in/glossary/llm"},"crumbs":[{"name":"Home","path":"/"},{"name":"Glossary","path":"/glossary"},{"name":"LLM","path":"/glossary/llm"}],"slug":"llm","term":"LLM (large language model)","aka":["large language model","foundation model"],"category":"AI building blocks","short":"An AI model trained on very large amounts of text that predicts the next piece of text, which lets it read, write and reason in language.","body":[["An LLM is trained to predict the next ",{"href":"/glossary/token","text":"token"}," in a sequence. Done at very large scale, that simple goal produces a model that can answer questions, summarise, translate, write code and follow instructions. Many current models also accept images, audio or files."],["Apps use an LLM through an API or a self-hosted model. The model knows only what was in its training data and what you send in the ",{"href":"/glossary/context-window","text":"context window"},", so most products add their own data with ",{"href":"/glossary/rag","text":"RAG"}," and their own actions with ",{"href":"/glossary/tool-calling","text":"tool calling"},"."]],"why":["LLMs make it practical to automate work that involves reading and writing: support, document handling, search, drafting and data extraction. They are also probabilistic, so the same input can give different outputs and they can be confidently wrong. Building with them means designing for checks, not just prompts."],"example":["A claims team uses an LLM to read incoming emails, pull out the policy number and claim type as structured fields, and draft a first reply. A person reviews the draft before it is sent."],"inBuild":null,"mistakes":[["Treating the model as a database of facts. Ground answers in your own data."],["Shipping without ",{"href":"/glossary/llm-evals","text":"evals"},". Without them you cannot tell if a prompt or model change made things better or worse."],["Picking the biggest model by default. A smaller model is often good enough and cheaper per call."]],"related":[{"href":"/glossary/token","label":"Token (LLM)","detail":"The unit an AI language model reads and writes, and the unit most LLM APIs bill by."},{"href":"/glossary/rag","label":"RAG (retrieval-augmented generation)","detail":"A pattern that finds relevant passages from your own data and gives them to a language model along with the question, so it answers from your content."},{"href":"/glossary/hallucination","label":"Hallucination (AI)","detail":"When an AI model produces information that is false or made up, presented as if it were true."},{"href":"/glossary/fine-tuning","label":"Fine-tuning","detail":"Training an existing model further on your own examples so it behaves the way you want, such as following a format, tone or task more reliably."}],"tools":[{"href":"/tools/llm-model-picker","label":"LLM model picker","detail":"Free tool"},{"href":"/tools/llm-api-cost-calculator","label":"LLM API cost calculator","detail":"Free tool"}],"links":[{"href":"/ai","label":"AI by industry","detail":"AI use cases, costs and risks per industry."},{"href":"/ai-automation","label":"AI automation","detail":"How OceanLab automates company workflows with AI."},{"href":"/pricing/categories/llm-api","label":"LLM API pricing","detail":"Model prices side by side, with sources."}],"sources":[],"legal":false,"updatedAt":"2026-10-25"}