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.
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:
Cline
Open Cline's settings and set the API Provider to OpenAI Compatible:
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
- How to use Claude Code with an uncensored, unlimited modelRun Claude Code on GLM-5.3-Flash or Qwen 3.8 Flash Next through Unquant's Anthropic-compatible endpoint: two environment variables, no proxy, unlimited tokens and 262K context.
- Use Unquant with Crush, Goose, Zed and AiderExact OpenAI-compatible settings to run Crush, Goose, the Zed editor and Aider on Unquant's uncensored GLM-5.3-Flash and Qwen 3.8 Flash Next.
- Uncensored AI for coding and agentsWhy developers use an uncensored model for coding and agents: no refusals on security work, reverse engineering or edgy content pipelines, plus 262K context and unlimited tokens for long agent loops.