This guide shows you how to integrate SambaCloud’s high-performance LLMs with the VS Code AI Toolkit. The AI Toolkit is a lightweight extension that helps you develop and optimize AI agents directly within your code editor.
Getting started with SambaNova’s LLM in VS Code is quick and easy. Follow the steps below to connect your model and start building generative AI applications.
Open the AI toolkit panelIn VS Code, open the AI Toolkit panel (usually located in the sidebar).
Add a custom model
Select the + icon at the top of the AI Toolkit panel
Select “Add a custom model” from the dropdown
Enter the Model Endpoint
Paste the SambaNova inference endpoint URL:
Copy
https://api.sambanova.ai/v1/chat/completions
The URL may vary if you’re using a dedicated SambaCloud node.
Enter the Model ID
Copy the Model ID (from the Supported models page) for the model you would like to use.
Paste and select Enter.
Setup a display name
Use the same Model ID or create a custom display name.
Select Enter.
Provide your API key.
Generate an API key on the SambaCloud portal if you don’e have one already.
Enter the key in Authorization: Bearer <your-api-key> and select Enter.
Test the connection
In the AI Toolkit panel, go to the Tools section and open the Playground
After a few moments, you should see your SambaNova model name appear in the Model dropdown (top-right of the Playground)
Select your model and:
Edit the Context (e.g., “You are a helpful coding assistant”)
Adjust inference parameters (optional)
Try a test prompt
Your SambaNova model is now live in the AI Toolkit — and you’re ready to experience inference that’s up to 5x faster than typical GPU providers. If you need help or run into any issues, reach out to your SambaNova support team.