---
title: 'Which models can I use?'
description: 'Anything your model provider resolves. The default provider is OpenRouter, and any OpenAI-compatible endpoint works instead.'
position: 4
---

# Which models can I use?

> Whatever your **model provider** resolves. A model provider is any
> OpenAI-compatible endpoint. The container running your agent sends every model
> call to it, and the default is [OpenRouter](https://openrouter.ai/docs).

Your code names a model as a bare id in the `creator/model-name` form, such as
`openai/gpt-4o-mini` or `anthropic/claude-haiku-4.5`. The container resolves
that id through its provider, so swapping providers changes nothing in your
project.

The provider is operator configuration. You set it on the **Model provider**
screen, or with `MODEL_PROVIDER_BASE_URL` and `MODEL_PROVIDER_API_KEY` on the
container. Point the base URL at a local gateway (Ollama, LM Studio, LiteLLM,
vLLM) and the key becomes optional.

To read the live catalogue, call `stackbone.ai.models.list()`. Every entry carries the model `id`. Whether it
also carries `context_length` and `pricing` is up to the provider: OpenRouter
reports both, a local gateway usually reports neither.

## Read more

- **[Gateway](/docs/home/features/gateway)**: the Model provider screen, and
  every caller in the workspace that resolves through it.
- **[`stackbone.ai`](/docs/sdk/platform/ai)**: chat, embeddings, images and the
  model catalogue.
- **[Choosing a model](/docs/faqs/building/choosing-a-model)**: where each model
  id is set and how to compare two of them.
- **[Getting started](/docs/cli/guides/getting-started)**: the first run stops
  until a provider is configured.