Skip to main content

Oh My Pi

Connect Oh My Pi (omp) to Divyam through its native provider settings.

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 Oh My Pi​

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. Add the Divyam provider​

Add this to ~/.omp/agent/models.yml. If providers: already exists, add only the divyam: entry beneath it.

providers:
  divyam:
    baseUrl: https://api.preview.divyam.ai/v1
    api: openai-completions
    apiKey: DIVYAM_API_KEY
    discovery:
      type: openai-models-list

The discovery setting reads Divyam's model list using your exported key. omp keeps its configuration separate from Pi.

3. Send your first prompt​

divyam-as/

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

Start a session:

omp --model divyam/divyam-as/gpt-6-sol
In Oh My Pi's composer
Hello, what are your capabilities?
Paste this message, then send it.
Feature limits

Divyam's model list does not supply context or output limits, so omp uses its defaults. Check charges in the Divyam console rather than omp's local cost estimate.

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.

Troubleshooting​

  • No Divyam models: Check the YAML indentation and that the file is ~/.omp/agent/models.yml.
  • HTTP 401: Export DIVYAM_API_KEY in the shell that starts omp.
  • HTTP 404: Use https://api.preview.divyam.ai/v1 as baseUrl.