Cline
Use Cline in VS Code with your Divyam API key.
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 Cline and open its provider settings
Install the VS Code extension using the official Cline installation instructions.
Open Cline’s sidebar. Choose Bring my own API key → OpenAI Compatible. If Cline is already configured, open its settings to change the provider.
2. Enter the Divyam connection
These settings replace the URL and key in Cline's saved OpenAI Compatible connection with Divyam's values. This guide selects it for Act mode. Plan and Act can keep separate model selections.
Set these values in the provider settings:
Model ID: divyam-as/gpt-6-sol. Context window: 1,050,000 tokens. Models and pricing
| Setting | Value |
|---|---|
| Base URL | https://api.preview.divyam.ai/v1 |
| API Key | divyam-sw-v1-... (replace with your key) |
| Model ID | divyam-as/gpt-6-sol |
| Max Output Tokens | 8192 |
You can use this provider without a Cline account.
3. Open an interactive chat
Open Cline and choose Act. Review changes and approve requested commands in Cline.
Hello, what are your capabilities?
You can ask Cline to read a local image file with an image-capable model. Run /compact to condense earlier messages.
Other editors, web tools, MCP and other modes 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.