Stop burning expensive tokens on simple autocomplete tasks. SuiteThrottle governs your local AI usage by intelligently routing tasks to the most cost-effective models.
Key Features
Pre-Flight Cost Estimation
Predict your GitHub Copilot token usage and expenses before execution to prevent billing surprises.
Zero-Friction Context Routing (Haiku vs Opus/Sonnet)
Automatically route simple autocomplete tasks to lightning-fast, affordable models (like Claude 3.5 Haiku) while reserving premium models (like Claude 3 Opus or Sonnet) for complex Chat and Agent interactions.
Local Telemetry Dashboards
Gain full visibility into your FinOps. Track token consumption, model utilization, and cost savings with rich, built-in observability dashboards right inside VS Code.
Installation
You can install the SuiteThrottle extension manually using the VSIX file:
Open Visual Studio Code.
Go to the Extensions view (Ctrl+Shift+X or Cmd+Shift+X).
Click the Views and More Actions (...) button at the top right of the Extensions view.
Select Install from VSIX... from the dropdown menu.
Browse to the downloaded suitethrottle-1.0.0.vsix file and select it.
Reload VS Code if prompted to activate the extension.
