> For the complete documentation index, see [llms.txt](https://docs.kontinent.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.kontinent.ai/reference/glossary.md).

# Glossary

Plain-language definitions of terms used across Kontinent. Click any entry to expand it.

***

## A to F

<details>

<summary><strong>API key</strong></summary>

A 49-character bearer token (`sk-kt-` plus 43 base62 characters) that authenticates data-plane requests. Shown exactly once at creation; only a SHA-256 hash is stored. Scoped to one organization. See [Authentication](/overview/authentication.md).

</details>

<details>

<summary><strong>Chat completion</strong></summary>

A request to `POST /v1/chat/completions`, the OpenAI-compatible endpoint for conversational models. Supports streaming via `stream: true`.

</details>

<details>

<summary><strong>Cost-quality threshold</strong></summary>

A single optional dial from 1 to 10, used when the smart router's pool mixes cheaper open-weight models with stronger ones. Low lets smaller models win more often; high sends more traffic to your strongest models. See [Price & performance](/models-and-routing/price-performance.md).

</details>

<details>

<summary><strong>Credits</strong></summary>

The prepaid balance an organization holds, denominated in micro-EUR. Each request debits the exact cost of the tokens it used. An exhausted balance returns `402 insufficient_credits`. See [Rate limits & credits](/features/rate-limits.md).

</details>

<details>

<summary><strong>Custom router</strong></summary>

A routing method you configure on the smart router that selects among your models on live metrics, such as latency, throughput, or error rate, rather than (or on top of) prompt classification.

</details>

<details>

<summary><strong>Data plane</strong></summary>

The OpenAI-compatible request path: chat completions, embeddings, and model listing at `https://api.kontinent.ai`. Distinct from the dashboard, where keys and credits are managed.

</details>

<details>

<summary><strong>Embedding</strong></summary>

A vector representation of text, returned by `POST /v1/embeddings`. Models declare `kind: "embedding"`; sending one to the chat endpoint is rejected.

</details>

<details>

<summary><strong>Fail-open</strong></summary>

The rate limiter's behavior when its backing store has trouble: requests pass rather than being blocked. You are never rate-limited by an infrastructure hiccup on our side.

</details>

<details>

<summary><strong>Failover</strong></summary>

Automatically retrying a request on the next provider in a model's route chain after an upstream `429`, `5xx`, or connection error. For streams it happens only before the first byte. See [Maximum availability](/models-and-routing/availability.md).

</details>

***

## G to P

<details>

<summary><strong>Metadata</strong></summary>

The only data a request leaves behind: token counts, latency, HTTP status, model id, and computed cost. Never the prompt or the completion. See [Privacy & retention](/privacy/privacy.md).

</details>

<details>

<summary><strong>micro-EUR (µEUR)</strong></summary>

The integer money unit used everywhere in Kontinent: 1 EUR = 1,000,000 µEUR. Prices are quoted per million tokens. Integers avoid floating-point rounding in billing.

</details>

<details>

<summary><strong>Model id</strong></summary>

A logical model address in `provider/model` form, e.g. `mistral/mistral-large-latest`. One id can resolve to several upstream routes. Unknown or disabled ids return `404 model_not_found`.

</details>

<details>

<summary><strong>Organization</strong></summary>

The account boundary a key belongs to. It owns the credit balance, the rate limit, and usage attribution for every request made with its keys.

</details>

<details>

<summary><strong>Passthrough error</strong></summary>

An upstream 4xx body that is already OpenAI-shaped and is returned with its original status rather than rewrapped by the gateway. See [Handling errors](/features/errors.md).

</details>

<details>

<summary><strong>Pragmatic</strong></summary>

The sovereignty tier for a model served from an **EU region** of a provider whose parent company sits outside the EU.

</details>

<details>

<summary><strong>Primary</strong></summary>

The default route for a model: the provider that serves the request whenever it is healthy.

</details>

***

## R to Z

<details>

<summary><strong>Route</strong></summary>

One upstream provider path behind a logical model id. A model declares a primary route and, optionally, standby routes used for failover.

</details>

<details>

<summary><strong>RPM</strong></summary>

Requests per minute: the per-key rate limit, enforced over a sliding window of two 1-minute buckets. Exceeding it returns `429 rate_limit_exceeded`.

</details>

<details>

<summary><strong>Smart router</strong></summary>

A configurable router that classifies each incoming request and sends it to one of the models you picked for its pool. Kontinent does not pick models you didn't allow. See [Price & performance](/models-and-routing/price-performance.md).

</details>

<details>

<summary><strong>Sovereignty tier</strong></summary>

A per-model declaration of how strict its data residency is: `strict` for an EU-owned provider, `pragmatic` for an EU region of a non-EU parent. Returned on every model from `GET /v1/models`. See [Models & sovereignty](/models-and-routing/models.md).

</details>

<details>

<summary><strong>Standby</strong></summary>

A fallback route for the same logical model, on a different provider, that takes over when the primary can't serve a request.

</details>

<details>

<summary><strong>Streaming</strong></summary>

Receiving tokens as they are generated over Server-Sent Events, enabled with `stream: true`. The final chunk before `data: [DONE]` carries `usage`. See [Streaming](/features/streaming.md).

</details>

<details>

<summary><strong>Strict</strong></summary>

The sovereignty tier for a model served by an **EU-owned** provider.

</details>

<details>

<summary><strong>Zero prompt retention</strong></summary>

The design contract that request and response bodies are never persisted or logged anywhere in the pipeline, enforced by an end-to-end test that fails CI if a prompt reaches the logs. See [Privacy & retention](/privacy/privacy.md).

</details>

***

{% hint style="info" %}
A term missing? Let us know from the [dashboard](https://app.kontinent.ai). We update this glossary regularly.
{% endhint %}


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://docs.kontinent.ai/reference/glossary.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.