---
title: "Glossary"
description: "Terms and concepts used across Token Factory docs, defined in one place."
section: reference
order: 3
layout: guide
updated: "2026-06-12"
---

Short definitions for the terms that recur across these docs. If a term you saw on a page isn't covered here, file an issue.

## API key

A secret credential of the form `sk-oais-...` that authenticates requests to the public `/v1` API. Keys are scoped to a single [workspace](#workspace); quotas, billing, and Observability all attribute to the owning workspace.

## Bearer token

The HTTP authorization scheme used by `/v1`. Pass your [API key](#api-key) as `Authorization: Bearer sk-oais-...` — there is no separate token-exchange step.

## Cold start

The gap between an autoscaled [Dedicated Endpoint](#dedicated-endpoint) sitting at zero replicas and being able to serve again. What brings it back, and what happens to a call that arrives in the meantime, is covered under [Scale-to-zero vs a warm floor](/docs/dedicated-endpoints/autoscaling#scale-to-zero-vs-a-warm-floor). How long the gap lasts is not something the platform reports. Keeping a [warm floor](#warm-floor) means the endpoint never sits at zero.

## Dedicated Endpoint

Reserved GPU capacity serving a single model, called through the same `/v1` API using a `dedicated/<endpoint-name>` [Model ID](#model-id). Distinct from a REST endpoint such as `/v1/chat/completions`.

See [What are Dedicated Endpoints?](/docs/dedicated-endpoints/what-are-dedicated-endpoints).

## Endpoint flavor

A pre-defined hardware shape — GPU count, type, and precision — offered for a model on a [Dedicated Endpoint](#dedicated-endpoint). Which flavors are offered depends on the model you're deploying. Your [GPU allotment](#gpu-allotment) doesn't change that list — a shape that won't fit your remaining headroom is shown and marked as not fitting, rather than hidden.

## GPU allotment

The per-organization, per-GPU-type cap on GPU capacity committed across your [Dedicated Endpoints](#dedicated-endpoint). Checked on create, resume, and scaling changes; never on suspend, delete, or a read. See [GPU allotment](/docs/dedicated-endpoints/gpu-allotment).

## GPU-hour

The unit dedicated-endpoint GPU usage is measured in — how many GPUs an endpoint holds, and for how long. The [GPU cost](/docs/dedicated-endpoints/cost#reading-the-cost-kpis) view states the arithmetic in full and reports it per window. Distinct from [GPU allotment](#gpu-allotment), which caps what you may reserve rather than recording what you used.

## Model ID

The string identifier for a model in API requests, formatted as `provider/model-name`. The prefix carries meaning: an `Omniva/…` id (for example `Omniva/glm-5.2`) is an Omniva-optimized build of an open model — tuned and quantized for low-latency serving — while the raw upstream open weights are offered under the author prefix (for example `zai-org/GLM-5.2`). Echoed back in the `model` field of responses.

## Model Library

The browseable catalog of available models in the Token Factory app — filterable by provider, modality, and status. The same set is exposed programmatically through [`GET /v1/models`](/docs/api-reference/models).

## Playground

The in-app chat and completion UI for trying a model interactively without writing code. The Playground calls the same `/v1` gateway as your API key, but authenticates with your signed-in session instead of a key — not a substitute for an API key in production.

## Production gateway

The deployed `/v1` endpoint at `https://api.tokenfactory.omniva.com/v1`. The contract documented across these pages.

## Replica

One running instance of a [Dedicated Endpoint](#dedicated-endpoint)'s model server. `minReplicas` and `maxReplicas` bound how many can run at once; a fixed endpoint runs an exact count instead.

## Scale-to-zero

`minReplicas: 0` on an autoscaled [Dedicated Endpoint](#dedicated-endpoint): once the endpoint is idle past its scale-to-zero window, the last [replica](#replica) is removed. See [cold start](#cold-start) for what a call that arrives while it sits at zero runs into. Contrast with [warm floor](#warm-floor).

## Token-based pricing

The pay-as-you-go pricing mode: billed per 1M tokens, with input and output priced separately per model. Best fit for variable traffic and prototyping. GA today via `/v1/chat/completions` and `/v1/embeddings`.

## Token Factory

Omniva's managed inference product with a console and an OpenAI-compatible `/v1` API. The production gateway is live for chat and embeddings.

## Utilization

Three different figures wear this name, and they measure different things:

- On the [GPU cost](/docs/dedicated-endpoints/cost) view — how busy the GPUs were, averaged evenly across
  collection windows rather than weighted by GPU count, so a one-GPU hour counts the same as a thirty-GPU one.
  A true 0% and a missing measurement render identically there.
- On the [GPU allotment](/docs/dedicated-endpoints/gpu-allotment) ledger — how much of your organization's
  per-type cap is committed. Capacity accounting; says nothing about how busy anything is.
- As `kv-cache-utilization` in [Autoscaling](/docs/dedicated-endpoints/autoscaling) — the fraction of the
  serving engine's KV-cache memory in use, the alternative scaling metric.

## Warm floor

`minReplicas` ≥ 1 on an autoscaled [Dedicated Endpoint](#dedicated-endpoint): at least one [replica](#replica) always stays resident, so the endpoint never sits at zero. That floor is held around the clock and accrues [GPU-hours](#gpu-hour) the whole time. Contrast with [scale-to-zero](#scale-to-zero).

## Workspace

The scope unit for everything that costs money or carries quota: [API keys](#api-key), monthly token caps, billing, and Observability dashboards. Users belong to one or more workspaces; each request attributes to exactly one.

## What next

  - [Quickstart](/docs/getting-started/quickstart) — Make your first API call in minutes.
  - [Models overview](/docs/getting-started/models-overview) — Browse the catalog and pick a model.
  - [Errors & status codes](/docs/reference/errors) — What 401, 403, and 429 mean and how to recover.

