# Connect Continue

https://modelportal.ai/docs/integrations/continue

> Open-source coding assistant for VS Code and JetBrains, configured from one file.

## Use cases

Good for an open-source coding assistant in VS Code or JetBrains, with all model settings in one config file that is easy to share across a team.

## Tips

Coding prompts tend to be long, so pick a long-context model and set a daily spend limit on the key to keep long tasks in check.

## If it cannot connect

1. Use `https://modelportal.ai/v1` as the API host, without `/chat/completions`.
2. The key starts with `mp-` (older keys: `key_`) and is not paused or revoked; `invalid_api_key` means the key cannot be used.
3. The model ID matches the [catalog](/catalog) and is in the key's allowed models.
4. `insufficient_balance` means the balance is too low; see [common errors](/docs/errors?lang=en) for more.

## Setup

1. Run Continue: Open Config from the command palette.
2. Add the block below to the models array.
3. Save, then switch to the model from the chat box.

## Settings

- API host：`https://modelportal.ai/v1`
- API key：`YOUR_API_KEY`
- Model：`MODEL_ID`

```json
{
  "models": [
    {
      "title": "ModelPortal.AI",
      "provider": "openai",
      "model": "MODEL_ID",
      "apiBase": "https://modelportal.ai/v1",
      "apiKey": "YOUR_API_KEY"
    }
  ]
}
```

## FAQ

### How do we share config without sharing keys?

Share the config file, but each member should use their own key; never commit keys to the repository.

### What should apiBase be?

https://modelportal.ai/v1, without an endpoint path at the end.