Connect External Tools
Use your platform AI models with external tools and editors. Any tool that supports an OpenAI-compatible provider can send requests to ACTIVATE's OpenAI-compatible API, authenticated with an API key and subject to the same access checks as Chat.
To open the page, navigate to AI > Providers and click Connect tools. The AI keys page has the same button.
pw code
The page starts with pw code, the Parallel Works coding agent for your terminal. It signs in with your account, so it needs no key or base URL: install the pw CLI, sign in, and run pw code in your project.
Base URL and API Key
External tools need two values, both shown at the top of the page:
- Base URL: your platform's endpoint,
https://<your-activate-domain>/api/openai/v1. Click the URL on the page to copy it with your domain filled in. - API Key: click Create Key to create a key without leaving the page. The new key is shown once.
The dialog offers two kinds of key for external tools. Which one to use depends on the providers you need:
| Key | Reaches | Allocation |
|---|---|---|
| AI Gateway API key | Your personal providers, providers shared with you, session models, and organization providers | Bound to the key when you create it, so organization provider usage is tracked against it |
| API key (platform API key) | Your personal providers, providers shared with you, and session models. Organization providers too, if the tool sends an X-Allocation header. | None, unless the tool sends X-Allocation |
As the page puts it: "Use an AI Gateway API key when you have an allocation so usage is tracked and organization providers are available. A platform API key works with your own providers and session models." If you have no allocations, the page notes that organization providers are unavailable to external tools. See AI Keys for the differences in full.
Available Models
The Your models list shows every model you can use across your providers. Click a model to copy its ID. IDs take one of three forms:
owner:provider/modelfor a personal providerorg:provider/modelfor an organization providersession:owner:session/modelfor a model served from a session
If the list is empty, add a provider or ask for access to one; see AI Providers.
Setup Guides
The page includes step-by-step guides for popular tools. Each guide inserts your Base URL, API key, and model IDs in place.
Open WebUI
A self-hosted, feature-rich web interface for AI chat.
- Open your Open WebUI instance, click your avatar in the bottom-left corner, and select "Admin Panel".
- Go to the Settings tab, then navigate to Connections > OpenAI.
- Click the "+" button to add a new connection.
- Enter your Base URL.
- Paste your API key into the Auth field (leave the type set to "Bearer").
- Click "Save" to add the connection.
OpenCode
An AI coding assistant with OpenAI-compatible provider support.
Desktop
- Open OpenCode and go to Settings > Providers.
- Scroll down to "Custom provider" and click "+ Connect".
- Enter a Provider ID (e.g. "pw") and a Display name (e.g. "Parallel Works").
- Set the Base URL to your gateway Base URL.
- Paste your API key into the API key field.
- Under Models, enter one of your model IDs and a display name, then click "Submit". Repeat to add more.
CLI
-
Launch OpenCode in your terminal and run the
/connectcommand to register a new provider credential. -
Enter a Provider ID (e.g. "pw") and select "Other" when prompted for a provider.
-
Paste your API key when OpenCode prompts for it.
-
Open (or create)
opencode.jsonin your project root or at~/.config/opencode/opencode.json, then add this provider entry:{ "$schema": "https://opencode.ai/config.json", "provider": { "pw": { "npm": "@ai-sdk/openai-compatible", "name": "Parallel Works", "options": { "baseURL": "https://<your-activate-domain>/api/openai/v1" }, "models": { "model-id-here": { "name": "Model Display Name" } } } } } -
Replace
model-id-herewith one of your model IDs. Add more entries undermodelsfor every model you want available. -
Restart OpenCode. Your custom provider and models will appear in the model picker.
Tip
OpenCode Desktop and CLI share the same opencode.json. If you already set up the desktop variant above, the CLI will pick up the same provider. The quickest path is often to configure in the desktop and then just run opencode in your terminal.
Kilo Code
An open-source AI coding assistant for VS Code with OpenAI-compatible provider support.
- Open VS Code and install the Kilo Code extension.
- Open the Kilo Code panel, open Settings, and choose Providers.
- Click "Connect" next to "Custom provider".
- Enter a Provider ID (e.g. "pw") and a Display name (e.g. "Parallel Works").
- Set the Base URL to your gateway Base URL.
- Paste your API key into the API key field.
- Kilo Code fetches your available models automatically. Select the ones you want and click "Add N model(s)".
Cursor
An AI-powered code editor built on VS Code with integrated chat and code generation.
- Open Cursor and go to Settings > Models.
- Expand the "API Keys" section and enable the "OpenAI API Key" toggle.
- Paste your API key into the OpenAI API Key field.
- Enable the "Override OpenAI Base URL" toggle and set it to your gateway Base URL.
- Scroll down and click "+ Add Custom Model", enter one of your model IDs, and click "Add". Repeat for every model you want available.
- Turn off "Auto" mode in the model picker. Otherwise Cursor ignores your custom models and routes to its own.
Related Documentation
- AI Keys: Creating and managing keys
- AI Providers: Connecting model backends
- AI Usage: Tracking spend on organization providers