Title: Frequently asked questions %E2%80%94 LLM EU
Canonical: https://llmeu.com/en/learn/
Markdown mirror: https://llmeu.com/en/learn.md
Machine-readable: https://llmeu.com/llms.txt (index) - https://llmeu.com/llms-full.txt (full catalogue) - https://llmeu.com/llms-catalogue.json

# Frequently asked questions

## Basics

### [What is a context window, and what is a token?](/en/learn/context-window-and-tokens/)

A token is a small piece of text, roughly a word fragment. A context window is the maximum number of tokens one call may hold: instructions, the conversation so far, retrieved passages and the reply.

### [LLM vs AI: what is a large language model, what is an llm base, and what is Nemotron 3 Super?](/en/learn/llm-vs-ai/)

AI is the field; a large language model is one kind of model inside it, a base LLM continues text instead of following instructions, and Nemotron 3 Super is a 123.6B mixture of experts.

### [What is an LLM?](/en/learn/what-is-an-llm/)

An LLM is a program trained on large amounts of text to predict the next token, a small piece of text. It answers from its weights and the prompt you send, not from a database it searches.

## Retrieval

### [What is an LLM retriever, and which multilingual embedding model should I use?](/en/learn/embeddings-and-vector-search/)

A retriever pairs an embedding model that turns text into vectors with a reranker that scores passages. multilingual-e5-large is MIT with 512-token chunks; embeddinggemma-300m takes 2048.

### [What is RAG?](/en/learn/what-is-rag/)

RAG is a pipeline, not a model: your application retrieves passages and the model answers from those. Only the last stage is a chat completion; embedding and reranking are separate calls.

## Hosting

### [How do LLMs run in the EU?](/en/learn/how-llms-run-in-the-eu/)

A model runs where an endpoint runs, and the row records its region and class. Residency is a filter applied before scoring: if nothing satisfies it, the request returns 409 no_endpoint_for_policy.

### [Open weights or an API: which should I use?](/en/learn/open-weights-vs-api/)

Open weights mean the files are downloadable; an endpoint means someone runs them for you. Many European deployments use both: an API for variable load, a self-hosted checkpoint for sensitive work.

## Cost

### [What does an LLM API call cost, and what do the benchmark numbers mean?](/en/learn/llm-cost-and-pricing/)

A price is read from the rate an endpoint row records, per million tokens in and out, plus one visible fee per request. A row with no recorded rate is shown without a price.

## Licences

### [How do open model licences work?](/en/learn/llm-licences-explained/)

A licence is a recorded field on every model card: an SPDX identifier and a link to the text. Open weights means the weights are downloadable, not that commercial use is allowed.

## API

### [What are LLM API rate limits?](/en/learn/llm-rate-limits-explained/)

A rate limit here is a ceiling per bucket in a fixed window: 600 calls per key and 1800 per organization each minute, with at most 8 requests in flight on one key.

## Routing

### [How does an LLM router work?](/en/learn/llm-routing-explained/)

A router turns a request naming no machine into one endpoint response. A pure function filters candidates by policy and residency, scores what survives and takes the highest score.