Skip to main content

CodeBuddy CLI

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 CodeBuddy CLI​

Follow the official installation instructions.

Set your key in the shell you will use to start CodeBuddy:

export DIVYAM_API_KEY="divyam-sw-v1-..."

2. Add the Divyam model​

divyam-as/

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

Merge this custom model configuration into ~/.codebuddy/models.json. Keep your other models and the full /chat/completions path in url:

{
  "models": [
    {
      "id": "divyam-as/gpt-6-sol",
      "url": "https://api.preview.divyam.ai/v1/chat/completions",
      "apiKey": "${DIVYAM_API_KEY}",
      "maxInputTokens": 200000,
      "maxOutputTokens": 8192,
      "supportsToolCall": true,
      "supportsImages": false
    }
  ]
}

CodeBuddy reads your Divyam key from the environment reference in apiKey.

3. Start CodeBuddy​

From your project folder, run this in the shell where you set the key:

CODEBUDDY_API_KEY=custom-model codebuddy --model divyam-as/gpt-6-sol

custom-model is a startup placeholder. The model configuration supplies your Divyam key. This opens the interactive CLI.

In CodeBuddy CLI's composer
Hello, what are your capabilities?
Paste this message, then send it.
Optional features

For image input, change supportsImages to true when your selected Divyam model accepts images, then ask CodeBuddy to read a local image file. Use /compact to shorten the current conversation. CodeBuddy's local cost total can show zero for custom models. Use the Divyam console for charges.

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.