Skip to content

VS Code

VS Code does not natively support adding custom models. To use FloTorch, install one of the OpenAI‑compatible extensions below. Each extension allows you to configure the Base URL, API Key, and Model.

Before configuring VS Code, complete these steps in the FloTorch Console:

  1. Register or log in to FloTorch

  2. Create a custom model

    • In the Console, go to GatewayModel RegistryModels and create a model with your preferred configuration.
    • Note the model name (e.g. flotorch/<model-name>).
  3. Create an API key

    • Go to WorkspaceSettingsAPI Keys and create an API key.
    • Copy and store the key securely; you will need it when configuring the extension.

Extension: Kilo

  1. Open Extensions in VS Code.
  2. Search for Kilo in the VS Code Extensions Marketplace and install it, or install directly from the marketplace.
Kilo Extension Installation
  1. Open Kilo (from the sidebar or Command Palette).
  2. Navigate to SettingsProviders.
  3. Under API Provider, select OpenAI Compatible.
  4. Configure:
    • Base URL / Endpoint: https://gateway.flotorch.cloud/openai/v1
    • API Key: Your FloTorch API key (Create API Key)
    • Model: Your FloTorch custom model name (Create Model)
  5. Save and start using the model in Kilo.
Kilo Settings Configuration

Extension: Continue

  1. Install Continue from the VS Code Extensions Marketplace, or install directly from the marketplace.
Continue Extension Installation
  1. Open Continue (from the sidebar or Command Palette).
  2. Navigate to SettingsConfigs.
  3. Open Local Config (this opens configs.yaml).
  4. Add the FloTorch model configuration:
name: Local Config
version: 1.0.0
schema: v1
models:
- name: FloTorch Gateway
provider: openai
model: YOUR_FLOTORCH_MODEL_NAME
apiBase: https://gateway.flotorch.cloud/openai/v1
apiKey: YOUR_FLOTORCH_API_KEY
roles:
- chat
- edit
- apply
  1. Replace YOUR_FLOTORCH_MODEL_NAME (Create Model) and YOUR_FLOTORCH_API_KEY (Create API Key) with your actual values, save, and select this model in Continue.
Continue Configuration

Extension: Roo Code

  1. Open Extensions in VS Code and install Roo Code, or install directly from the marketplace.
Roo Code Extension Installation
  1. Open Roo Code (sidebar or panel).
  2. Create a Roo Code account and redirect to VS Code.
  3. Navigate to SettingsProviders.
  4. Under API Provider, select OpenAI Compatible.
  5. Configure:
    • Base URL: https://gateway.flotorch.cloud/openai/v1
    • API Key: Your FloTorch API key (Create API Key)
    • Model ID: Your FloTorch custom model name (Create Model)
  6. Save the settings and select the model for chat and code actions.
Roo Code Settings Configuration

FloTorch integrates with OpenAI-compatible CLIs and editors. In VS Code, use any of the extensions above (Kilo, Continue.dev, Roo Code) with the same Flotorch gateway URL, API key, and model name. Other OpenAI-compatible tools—such as Cline, vscode-openai, and similar extensions that let you set a custom base URL, API key, and model also work.