Continue.dev

Continue.dev Setup Guide

Drop a UnoRouter model entry into Continue’s config.yaml and it hot-reloads across VSCode and JetBrains.

Overview

Continue uses a yaml config you can version-control. Drop a UnoRouter model entry and Continue hot-reloads it.

Drop these values into the client. Your key auto-fills when you are signed in.

text

Base URL: https://api.unorouter.ai/v1
API Key: YOUR_API_KEY

Chat CompletionsStreamingTool calling

1
Open the Continue config
Edit ~/.continue/config.yaml (macOS/Linux) or %USERPROFILE%\.continue\config.yaml (Windows). Create the file if it does not exist.

Add a model entry

Use provider openai with apiBase. You can add multiple models as separate entries.

yaml

models:
  - name: UnoRouter model
    provider: openai
    model: YOUR_MODEL_ID
    apiBase: https://api.unorouter.ai/v1
    apiKey: YOUR_API_KEY

3
Save and reload
Continue hot-reloads the config. Pick UnoRouter from the model selector at the bottom of the panel.

Free models that work well here. Paste any model id into the client.

compound-miniglm-4.5-flashglm-4.5-airmistral-nemo-instruct-2407mistral-large-2512

Use config.yaml, not the legacy config.json.
If a model rejects extra params, set requestOptions.dropParams: ['frequency_penalty','presence_penalty'] on that model entry.