Continue Configuration

Continue is an AI coding assistant for VS Code and JetBrains, supporting model configuration via config.yaml. This guide covers configuring Continue to use ShopAIKey for both OpenAI-compatible and Anthropic-compatible providers.

Endpoint

OpenAI-compatible:

code

https://api.shopaikey.com/v1

Claude in Continue also uses:

code

https://api.shopaikey.com/v1

1. Install Continue

VS Code

Open VS Code.
Go to Extensions.
Search for Continue.
Install the official extension.

JetBrains

Open your JetBrains IDE.
Go to Settings → Plugins.
Search for Continue.
Install the plugin and restart the IDE if prompted.

2. Open the configuration directory

Continue reads global configuration from:

macOS / Linux

code

~/.continue

Windows

code

%USERPROFILE%\.continue

Create or open the file:

code

config.yaml

If config.yaml exists, Continue will prioritize this file over config.json.

3. Basic configuration

Paste the following into config.yaml:

code

name: ShopAIKey
version: 1.0.0
schema: v1

models:
  - name: GPT-5.2
    provider: openai
    model: gpt-5.2
    apiKey: sk-your-api-key
    apiBase: https://api.shopaikey.com/v1
    roles:
      - chat
      - edit
      - apply
    capabilities:
      - tool_use
      - image_input

  - name: Claude Sonnet 4.5
    provider: anthropic
    model: claude-sonnet-4-5
    apiKey: sk-your-api-key
    apiBase: https://api.shopaikey.com/v1
    roles:
      - chat
      - edit
      - apply
    capabilities:
      - tool_use
      - image_input

Replace sk-your-api-key with your ShopAIKey API key.

4. Minimal `config.yaml` sample for Claude

If you only want to use Claude via Continue, start with this minimal configuration:

code

name: Local Config
version: 1.0.0
schema: v1

models:
  - name: Claude Opus 4.6
    provider: anthropic
    model: claude-opus-4-6
    apiKey: sk-your-api-key
    apiBase: https://api.shopaikey.com/v1

With Continue, keep apiBase: https://api.shopaikey.com/v1 for both provider: openai and provider: anthropic.

5. Recommended: use environment variables

Avoid storing API keys directly in configuration files if you share your machine or sync dotfiles.

macOS / Linux

code

export SHOPAIKEY_API_KEY="sk-your-api-key"

Windows PowerShell

code

$env:SHOPAIKEY_API_KEY = "sk-your-api-key"

Then use the following configuration:

code

name: ShopAIKey
version: 1.0.0
schema: v1

models:
  - name: GPT-5.2
    provider: openai
    model: gpt-5.2
    apiKey: ${{ env.SHOPAIKEY_API_KEY }}
    apiBase: https://api.shopaikey.com/v1
    roles:
      - chat
      - edit
      - apply
    capabilities:
      - tool_use
      - image_input

  - name: GPT-5.3 Codex
    provider: openai
    model: gpt-5.3-codex
    apiKey: ${{ env.SHOPAIKEY_API_KEY }}
    apiBase: https://api.shopaikey.com/v1
    roles:
      - chat
      - edit
      - apply
    capabilities:
      - tool_use

  - name: Claude Sonnet 4.5
    provider: anthropic
    model: claude-sonnet-4-5
    apiKey: ${{ env.SHOPAIKEY_API_KEY }}
    apiBase: https://api.shopaikey.com/v1
    roles:
      - chat
      - edit
      - apply
    capabilities:
      - tool_use
      - image_input

6. Autocomplete

If you want tab autocomplete, add a lighter model with the autocomplete role:

code

  - name: Qwen Coder Autocomplete
    provider: openai
    model: qwen3-coder-plus
    apiKey: ${{ env.SHOPAIKEY_API_KEY }}
    apiBase: https://api.shopaikey.com/v1
    roles:
      - autocomplete
    autocompleteOptions:
      debounceDelay: 350
      maxPromptTokens: 1024
      onlyMyCode: true

7. Restart Continue

After editing config.yaml:

Reload VS Code or your IDE.
Open Continue.
Select the ShopAIKey model from the list.
Send a test request.

Example:

code

Explain the current file and suggest the smallest refactor.

8. Notes

GPT/Qwen/OpenAI-compatible models should use provider: openai with apiBase: https://api.shopaikey.com/v1.
Claude models should use provider: anthropic with apiBase: https://api.shopaikey.com/v1.
Model IDs must match the models currently supported by ShopAIKey.
If Continue doesn't see the new model, reload the IDE.
Do not commit config.yaml with a real API key to Git.

9. Troubleshooting

Continue doesn't pick up the new config

Check that the file is in the correct directory ~/.continue/config.yaml.
Check that YAML indentation is correct.
Reload the IDE.

Authentication error

Check your API key.
Check that the environment variable is exported in the shell/IDE session.
Check that the key still has credit.

Model not responding

Try switching to gpt-5.2.
Check that apiBase is https://api.shopaikey.com/v1.
Check that the model is still supported on the Models page.

In this section · Tools & IDE

Claude Code Configuration

Codex CLI Configuration

Gemini CLI Configuration

OpenClaw Configuration

OpenCode Configuration

Cline Configuration

DeepSeek Harness Configuration

PreviousCline Configuration Next DeepSeek Harness Configuration