Continue

What you need

• Base URLhttps://api.opencheap.si/v1
• API keyA kl_live_… key from the console, kept in OPENCHEAP_API_KEY.
• ModelAn id from Models, for example claude-sonnet-5.

The model

Add the model to ~/.continue/config.yaml (%USERPROFILE%\.continue\config.yaml on Windows). In the extension, the cog beside Local Config in the chat's configs menu opens it.

name: OpenCheap
version: 0.0.1
schema: v1

models:
  - name: Claude Sonnet 5
    provider: openai
    model: claude-sonnet-5
    apiBase: https://api.opencheap.si/v1
    apiKey: ${{ secrets.OPENCHEAP_API_KEY }}
    roles:
      - chat
      - edit
      - apply

${{ secrets.OPENCHEAP_API_KEY }} is read when the config loads, from the first of these that has it: ~/.continue/.env, .continue/.env in the workspace, .env in the workspace, then the environment Continue was started from. Put the key in ~/.continue/.env:

OPENCHEAP_API_KEY=<your key>

Writing the key straight into apiKey also works, but then the file holds a secret. Use any chat model id from the Models page for model; the picker in the extension lists the model by its name.

In the terminal

The Continue CLI reads the same file, and the key from the environment:

npm install -g @continuedev/cli
export OPENCHEAP_API_KEY=<your key>
cn -p --config config.yaml "Reply with one word: ready"

What was checked

Run on October 28, 2026 with Continue CLI 1.5.47 and the config above on claude-sonnet-5: the key resolved from the environment and again from ~/.continue/.env with the variable unset, and the answer came back. The extension's key lookup order is from the source of its final release (v2.0.0-vscode, LocalPlatformClient); the extension itself was not run.