> ## Documentation Index
> Fetch the complete documentation index at: https://docs.llm.kiwi/llms.txt
> Use this file to discover all available pages before exploring further.

# Glossary

> Glossary of LLM and API terms used in the LLM.kiwi docs, including tokens, prompts, completions, context windows, streaming, roles, and rate limits.

Use this plain-language glossary whenever a term in the documentation is unfamiliar.

## API and web terms

<AccordionGroup>
  <Accordion title="API">
    An Application Programming Interface is a defined way for software systems to communicate. Your application sends a request; the API returns a response.
  </Accordion>

  <Accordion title="Base URL">
    The shared beginning of API addresses. LLM.kiwi uses `https://api.llm.kiwi/v1`.
  </Accordion>

  <Accordion title="Endpoint">
    A specific API function and path. For example, `POST /v1/chat/completions` creates a chat completion, while `GET /v1/models` lists models.
  </Accordion>

  <Accordion title="HTTP method">
    The action associated with a request. `GET` retrieves information. `POST` sends data for processing.
  </Accordion>

  <Accordion title="Header">
    Metadata sent with a request. The `Authorization` header carries the API key, and `Content-Type` tells the API that the request body is JSON.
  </Accordion>

  <Accordion title="Request body">
    Data sent with a request. For a chat completion, the JSON body contains fields such as `model` and `messages`.
  </Accordion>

  <Accordion title="JSON">
    JavaScript Object Notation is a text format for structured data. JSON uses double-quoted keys and values, objects in braces, and arrays in brackets.

    ```json theme={null}
    {"model": "auto", "messages": []}
    ```
  </Accordion>

  <Accordion title="HTTP status code">
    A number describing the result. `200` means success, `400` means the request is invalid, `401` means authentication failed, and `429` means a rate limit was reached.
  </Accordion>

  <Accordion title="Timeout">
    The maximum time a client waits for a request. A timeout prevents an application from waiting forever when a network or service problem occurs.
  </Accordion>
</AccordionGroup>

## Authentication terms

<AccordionGroup>
  <Accordion title="API key">
    A secret value identifying authorized API access. LLM.kiwi keys begin with `sk_kiwi_`. Treat a key like a password and keep it on a trusted server.
  </Accordion>

  <Accordion title="Bearer token">
    The authentication format used in the request header: `Authorization: Bearer YOUR_API_KEY`. The space after `Bearer` is required.
  </Accordion>

  <Accordion title="Environment variable">
    A value supplied to a program by its operating environment instead of being written directly in source code. It is the normal place to load an API key, though deployment access controls still matter.
  </Accordion>

  <Accordion title="Revoke">
    Disable an API key so it can no longer be used. Revoke a key immediately if it was exposed.
  </Accordion>
</AccordionGroup>

## AI terms

<AccordionGroup>
  <Accordion title="LLM">
    A large language model is an AI model trained to process and generate language. It predicts output based on the instructions and context in a request.
  </Accordion>

  <Accordion title="Model">
    The AI system selected for a request. LLM.kiwi documents `auto` for automatic selection and `hrllm` for Croatian-focused generation.
  </Accordion>

  <Accordion title="Prompt">
    The input and instructions given to a model. In chat completions, this usually means the complete `messages` array, not only the newest user message.
  </Accordion>

  <Accordion title="System message">
    A message with role `system` that describes the assistant's behavior or task. It guides output but does not replace application-level security or validation.
  </Accordion>

  <Accordion title="Token">
    A unit a model uses to process text. A token may be a whole word, part of a word, punctuation, or whitespace. The count varies by language, text, and tokenizer.
  </Accordion>

  <Accordion title="Context window">
    The maximum token capacity available for input and output in a request. When a request is too large, your application must shorten, remove, split, or summarize content.
  </Accordion>

  <Accordion title="Temperature">
    A sampling setting that can affect output variation when supported by the selected model. Exact behavior and allowed values can differ between models.
  </Accordion>

  <Accordion title="Completion">
    Text generated by the model in response to the request. In a chat completion, the main result is usually at `choices[0].message.content`.
  </Accordion>

  <Accordion title="Finish reason">
    A response field describing why generation ended. `stop` commonly indicates a normal end; `length` commonly means an output or context limit was reached.
  </Accordion>

  <Accordion title="Streaming">
    Receiving a response incrementally as it is generated instead of waiting for one complete response.
  </Accordion>

  <Accordion title="Hallucination">
    A confident-looking but incorrect or unsupported model output. Verify important facts and validate outputs before acting on them.
  </Accordion>
</AccordionGroup>

## Application terms

<AccordionGroup>
  <Accordion title="SDK">
    A software package that wraps HTTP requests in language-specific functions and types. LLM.kiwi can be used with compatible OpenAI clients by setting a custom base URL.
  </Accordion>

  <Accordion title="Rate limit">
    A restriction on request frequency or capacity. When reached, an API commonly responds with status `429`.
  </Accordion>

  <Accordion title="Exponential backoff">
    A retry strategy that increases the wait after each temporary failure, for example one second, then two, then four. A small random delay helps prevent many clients from retrying together.
  </Accordion>

  <Accordion title="Stateless API">
    An API that does not remember prior requests automatically. For a continuing conversation, your application sends the relevant message history each time.
  </Accordion>

  <Accordion title="Server-side code">
    Code that runs in infrastructure you control and can safely access secrets. Browser JavaScript is client-side and must not contain private API keys.
  </Accordion>
</AccordionGroup>

<Card title="Learn these concepts in context" icon="lightbulb" href="/concepts">
  The core concepts guide connects these terms into one complete request flow.
</Card>