Autohand
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.
Connect Autohand to Divyam for reading files, editing code and running project commands.
1. Install and sign in to Autohand
Install Autohand using the official instructions, then sign in:
autohand --login
Autohand requires its own account login for this route, even when Divyam supplies the model.
2. Add Divyam in the provider wizard
From your project folder, start Autohand:
autohand --temperature 1 --set network.timeout=180000
Run /model → New provider... and enter:
Model ID: divyam-as/gpt-6-sol. Context window: 1,050,000 tokens. Models and pricing
| Setting | Value |
|---|---|
| Provider name | Divyam |
| Base URL | https://api.preview.divyam.ai/v1 |
| API key | divyam-sw-v1-... (replace with your key) |
| Model ID | divyam-as/gpt-6-sol |
| Context window | 200000 |
Keep the other wizard defaults. Autohand saves the custom provider and selects it. Keep --temperature 1 for this model. The timeout is in milliseconds and applies to this session.
3. Send your first prompt
Use the same Autohand session. Review file changes and command approvals in the terminal.
Hello, what are your capabilities?
Use the launch command above for later sessions so the temperature and timeout settings apply. Images, web tools and subagents are outside this guide.
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.
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.