Skip to main content

Kilo 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 Kilo CLI​

Follow the official installation instructions.

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

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

2. Configure Divyam​

divyam-as/

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

Saved compatible connection

This configuration directs the global openai-compatible connection to Divyam. Other models on that provider entry inherit these connection defaults. The divyam key creates a model entry within that connection.

Merge these fields into your global ~/.config/kilo/kilo.jsonc:

{
  "model": "openai-compatible/divyam",
  "small_model": "openai-compatible/divyam",
  "provider": {
    "openai-compatible": {
      "options": {
        "baseURL": "https://api.preview.divyam.ai/v1",
        "apiKey": "{env:DIVYAM_API_KEY}"
      },
      "models": {
        "divyam": {
          "id": "divyam-as/gpt-6-sol",
          "tool_call": true,
          "limit": {
            "context": 128000,
            "output": 16384
          }
        }
      }
    }
  }
}

Keep the environment-key reference in this trusted global configuration. Kilo's /connect flow saves credentials. The configuration above also supplies the wire ID, utility-model route, limits and tool support.

3. Open Kilo's terminal UI​

From your project folder, start the interactive CLI:

kilo --agent code

small_model keeps utility requests on the same model.

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

MCP, remote tools and background delegation are outside this guide. For the VS Code extension, use Kilo Code.

Images

For an image-capable model, add "modalities": { "input": ["text", "image"], "output": ["text"] } to provider.openai-compatible.models.divyam. This model capability setting enables image input.

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.