Unquant

Opening your workspace…

Unquant

Use Unquant in VS Code: Copilot Chat, Cline, Roo Code, Kilo Code and Continue

Every major VS Code AI tool accepts an OpenAI-compatible endpoint. Here is where the setting lives in each.

Setup guide2 min readUpdated 1 October 2026

GitHub Copilot Chat

Copilot Chat can use your own models in chat (inline completions still use Copilot's). Open the Command Palette, run Chat: Manage Language Models, add an OpenAI Compatible provider and enter:

OpenAI Compatible
URLhttps://api.unquant.io/v1
API keyYour Unquant API key
Modelglm-5.3-flash

Cline

Open Cline's settings and set the API Provider to OpenAI Compatible:

Cline
Base URLhttps://api.unquant.io/v1
API KeyYour Unquant API key
Model IDglm-5.3-flash
Context window262144

Roo Code

The same as Cline: API Provider → OpenAI Compatible, then the base URL, key and model ID above.

Kilo Code

In Settings → Providers, add a custom provider with the base URL https://api.unquant.io/v1 and your key. Kilo reads the model list from /v1/models.

Continue

Add a model to ~/.continue/config.yaml:

models:
  - name: GLM-5.3-Flash
    provider: openai
    model: glm-5.3-flash
    apiBase: https://api.unquant.io/v1
    apiKey: ${{ secrets.UNQUANT_API_KEY }}
    roles: [chat, edit, apply]

Keep reading