Skip to main content

Amp

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. To choose another model, use this guide’s model selector when one is shown, or copy its current ID from Models and pricing. Check its context limit and supported features.

1. Install Amp and authorize the CLI​

Follow the official Amp installation instructions. Sign in to your Amp account, then create an access token in Personal Settings → Security.

Set the Amp access token in your terminal:

export AMP_API_KEY="YOUR_AMP_ACCESS_TOKEN"
Two separate credentials

The Amp access token authorizes the CLI to use your Amp account. Your Divyam API key connects the model provider in the next step.

2. Connect Divyam in Model Routing​

Open Personal Settings → Model Routing, then choose Add → Custom URL. Keep the default OpenAI Chat Completions API format.

Choose your Divyam model:

divyam-as/

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

Enter these values. Replace divyam-sw-v1-... with your complete Divyam API key.

SettingValue
Base URLhttps://api.preview.divyam.ai/v1
API Keydivyam-sw-v1-...

Turn on Advanced beside Models and replace the default mapping with:

openai/gpt-6.1-sol -> divyam-as/gpt-6-sol

Choose Create, then place this connection before any other connection serving the same Amp model. Confirm the routing graph shows this connection for GPT-6.1 Sol.

Saved connection

This account-level mapping sends the selected Amp model to Divyam across Amp clients. The example maps Medium's GPT-6.1 Sol model. Other Amp models keep their existing routing.

3. Start a coding task​

From your project folder, start the mapped Medium mode:

amp --mode medium
In Amp's composer
Hello, what are your capabilities?
Paste this message, then send it.

Review Amp's file and command approvals as you work.

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.