Skip to main content

Pochi 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 Pochi CLI​

Follow the official installation instructions.

Pochi also requires rg on your PATH. If it is missing, follow the ripgrep installation instructions.

2. Add the Divyam provider​

divyam-as/

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

Merge this provider into ~/.pochi/config.jsonc, creating the file if needed:

{
  "providers": {
    "divyam": {
      "baseURL": "https://api.preview.divyam.ai/v1",
      "apiKey": "divyam-sw-v1-...",
      "models": {
        "divyam-as/gpt-6-sol": {}
      }
    }
  }
}

Replace the shortened key with your complete Divyam key. If the file already contains providers, add divyam to its existing providers object.

3. Send your first task​

Pochi CLI runs one task per invocation. From your project folder, run:

In your terminal
pochi --model divyam/divyam-as/gpt-6-sol --prompt 'Hello, what are your capabilities?'
Run this command to send the message.

For image input, add --attach path/to/image.png to the command when your selected model accepts images.

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.