Skip to main content

VS Code

Use Divyam with VS Code's native chat and coding tools through a Custom Endpoint.

Before you start

You need a Divyam account and an API key. If you don't have them yet, follow Getting Started first.

Replace the shortened divyam-sw-v1-... shown in examples with your complete API key.

The examples use divyam-as/gpt-6-sol. For another model, select its current ID in your harness or copy it from Models and pricing, and check its context limit and supported features.

1. Install VS Code and add a Custom Endpoint​

Install VS Code from its official installation page and open your project folder.

Open the Command Palette and run Chat: Manage Language Models. Select Add Models → Custom Endpoint, name the group Divyam, enter your Divyam API key (divyam-sw-v1-...), and choose Chat Completions. This chat route does not require GitHub sign-in or a Copilot plan.

2. Configure the model​

divyam-as/

Model ID: divyam-as/gpt-6-sol. Context window: 1,050,000 tokens. Models and pricing

VS Code opens chatLanguageModels.json. Keep the API-key value VS Code created and set the Divyam entry's models array to:

[
  {
    "id": "divyam-as/gpt-6-sol",
    "name": "GPT-6 Sol",
    "url": "https://api.preview.divyam.ai/v1/chat/completions",
    "toolCalling": true,
    "vision": false,
    "maxInputTokens": 120000,
    "maxOutputTokens": 16384,
    "modelOptions": { "temperature": 1 }
  }
]

In Preferences: Open User Settings (JSON), add these settings so chat helpers use your selected Divyam model:

{
  "chat.byokUtilityModelDefault": "mainAgent"
}

Merge these fields with your existing settings.

3. Open an interactive chat​

Open the Chat view. Choose Agent, the Local harness and GPT-6 Sol.

In VS Code's composer
Hello, what are your capabilities?
Paste this message, then send it.
Feature limits

Temporary Divyam provider errors may require a retry. VS Code’s inline suggestions and other Copilot services have separate account requirements. Images, browser tools, MCP and subagents are outside this guide.

Check your requests​

Open the Divyam console and select Logs. Your requests appear there within a few seconds, newest first, with their status, token counts and latency. Usage and Credits & Billing catch up within a few minutes.

Local cost estimates

Some clients display zero when model prices are missing. Check Credits & Billing for Divyam charges. Local dollar limits depend on the client's price and usage data.

For filters, cached-token counts and the requested-versus-routed view, see Logs and usage.