Click the model picker and click "Manage Models...".
Select "LiteLLM" provider.
Provide your LiteLLM base URL (e.g., http://localhost:4000 for self-hosted or your LiteLLM proxy URL).
Provide your LiteLLM API key (if required).
Choose the models you want to add to the model picker.
Each model entry also offers cheapest and fastest mode for each model. fastest selects the provider with highest throughput and cheapest selects the provider with lowest price per output token.
✨ Why use the LiteLLM provider in Copilot
Access 100+ LLMs from OpenAI, Azure, Anthropic, Google, AWS, and more through a single unified API.
Single API to switch between multiple providers.
Built for high availability and low latency.
Self-hosted or cloud-based options.
Support for streaming, function calling, and vision models.
Requirements
VS Code 1.104.0 or higher.
LiteLLM proxy running (self-hosted or cloud).
Optional: LiteLLM API key depending on your setup.
🛠️ Development
git clone https://github.com/Vivswan/litellm-vscode-chat
cd litellm-vscode-chat
npm install
npm run compile
