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

# Continue on Sideren.

> One models entry per catalog id in ~/.continue/config.yaml points Continue at the gateway — chat, edit, and autocomplete can each use a different model.

Continue speaks the OpenAI [Chat Completions](/api/chat-completions) dialect, so it runs
on Sideren through the `openai` provider type pointed at the gateway.

<Note>
  Continue's repository is no longer actively maintained; its last release is 2.0.0. The
  setup below keeps working with that release.
</Note>

## One command

```sh theme={null}
npx sideren setup --tool continue --key sdn_your_key
```

The setup helper adds one `openai`-provider entry per selected model to
`~/.continue/config.yaml`, or prints the entries to merge when a config already exists.
See [setup helper](/setup).

## By hand

Add a `models` entry to `~/.continue/config.yaml` using the OpenAI provider type pointed
at the gateway (a new file also needs the `name`, `version` and `schema` lines):

```yaml title="~/.continue/config.yaml" theme={null}
name: Sideren
version: 0.0.1
schema: v1
models:
  - name: Sideren
    provider: openai
    model: "@sdn/gpt-oss-120b"
    apiBase: https://api.sideren.io/v1
    apiKey: sdn_your_key
```

Add one entry per model you want in the picker — chat, edit, and autocomplete roles can
each point at a different [catalog id](/models).

## Verify

Open a file, trigger the chat panel, and send a trivial prompt. To confirm the key works
against the gateway without Continue in the loop:

```sh theme={null}
npx sideren test --key sdn_your_key
```


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.