# Models overview

Ethen gives you three ways to discover and use models: the **Model Library**
catalog, **local model runtimes**, and the **Gateway model list**. Which one you
reach for depends on whether you are browsing, running locally, or integrating
via API.

## Model Library

The **[Model Library](/model-intelligence)** is the central catalog of models
available through Ethen. Use it to browse models by provider, compare context
windows, modalities, and pricing signals, and open a model profile for deeper
detail.

See the [Model Library overview](/docs/models/model-library) for a full guide.

## Local models

Local runtimes let you run open-weight models on your own machine through
Ollama or LM Studio. Models loaded locally are available in the Console for
chat and in the Code workspace.

See [Local versus hosted models](/docs/models/local-vs-hosted) for the trade-offs
and setup guide.

## Gateway model list

The Gateway exposes a `/api/gateway/v1/models` endpoint that returns the subset
of models available for API routing. This is a different surface from the full
Model Library — only models with active provider routes appear here.

See the [Gateway overview](/docs/gateway/overview) for how routing and model
availability work in the API.

## Choosing a model

Start from the task, not the model. Match the workload to the smallest model
that reliably meets quality and latency needs, then route with fallback for
resilience.

See [Choosing a model](/docs/models/choosing-a-model) for detailed guidance.