DEDUPED Hot AI repos, turned into use cases Get 5 a day

How to switch Copilot Chat models without reloading VSCode with Route VSCODE

Route Copilot Chat through a local proxy and change the active AI model in one click.

Credentials. The 9Router API Key is entered into VSCode settings and forwarded through the local proxy, so keep it out of shared screens, logs and committed files.

Who it is forA developer who uses Copilot Chat daily and wants to try Claude, GPT, Gemini or DeepSeek models without editing config files or restarting VSCode.

The problemChanging the model in Copilot Chat normally means editing JSON configuration and reloading the window, which breaks flow.

The outcomeCopilot Chat sends requests through the local proxy on port 20129, and the active model can be changed from the dashboard or the status bar while the chat session stays open.

What you need first

  • Visual Studio Code with GitHub Copilot Chat
  • Node.js and npm, needed for `npm install -g 9router` and `npm start`
  • A 9Router account or local setup that gives you an API Key from the 9Router dashboard at http://localhost:20128/dashboard
  • Ports 20128, 20129 and 5500 free on your machine

Steps

  1. Install the gateway with npm install -g 9router, then start it in a separate terminal with 9router.
  2. Clone the repo with git clone https://github.com/yudaprasetya007/routeVSCODE.git and open the folder with cd routeVSCODE.
  3. Install the extension with code --install-extension releases/routevscode.model-connector-2.5.0.vsix --force.
  4. Start the dashboard with npm start and open http://localhost:5500.
  5. In VSCode press Ctrl+Shift+P, run 9Router: Set API Key & Base URL, enter http://localhost:20128/v1 and your 9Router API Key.
  6. Open Copilot Chat with Ctrl+Alt+I, choose 9Router via Proxy in the Model Picker, then switch models from the dashboard or the status bar.

Prompt for your agent

Using the repo yudaprasetya007/routeVSCODE, install the VSCode extension from releases/routevscode.model-connector-2.5.0.vsix and start the dashboard with npm start, then confirm that http://localhost:5500 loads. Set the model to <target model name> from the dashboard and report the active model shown in the status bar; verify that port 20129 is listening before reporting success.

Caveat. The README says a Model Picker reload may be needed after first install, so expect to run Developer: Reload Window once.

Share: X LinkedIn Hacker News Email Copy link

Disclaimer

Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page