Qoder CLI
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 and authorize Qoder CLI
Follow the official installation instructions. Create a Qoder Personal Access Token, then set it in your terminal using the documented authentication method:
export QODER_PERSONAL_ACCESS_TOKEN="YOUR_QODER_PERSONAL_ACCESS_TOKEN"
The Qoder token authorizes the CLI account. Your Divyam API key connects the model provider below.
2. Add and select the Divyam model
Start Qoder CLI from your project folder:
qodercli
Enter /model, open Custom, and choose Add custom model → OpenAI-compatible → Chat Completions.
Choose your Divyam model:
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.
| Setting | Value |
|---|---|
| Base URL | https://api.preview.divyam.ai/v1 |
| Model ID | divyam-as/gpt-6-sol |
| API Key | divyam-sw-v1-... |
Keep the other fields at their defaults. Choose Review and save, follow the save confirmation, then select the new model in the Custom tab.
See Qoder's custom model documentation for account availability and the model picker.
The wizard saves the provider and selected model for later CLI launches. Local custom-provider settings store the API key as plaintext in ~/.qoder/settings.json. Keep that file private.
3. Start a coding task
Hello, what are your capabilities?
Review Qoder's file and command approvals as you work.
Check your requests
Qoder's structured custom-provider output can report zero token and cost totals even when upstream usage is nonzero. Those totals do not establish free Divyam usage.
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.
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.