Kilo Code
Use the Kilo Code extension 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 Kilo Code and add a custom provider
Install the VS Code extension using the official Kilo Code installation instructions.
Open Kilo's Settings → Providers → Custom provider. Enter these connection settings, then select Submit:
| Setting | Value |
|---|---|
| Provider ID | divyam |
| Display name | Divyam |
| Provider API | OpenAI Compatible |
| 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: 1,050,000 tokens. Models and pricing
| Setting | Value |
|---|---|
| Models | divyam-as/gpt-6-sol from the fetched list |
You can connect this provider without a Kilo account.
2. Select the model
Choose the Divyam model for Default Model and Small Model, then save. In your global ~/.config/kilo/kilo.jsonc, merge these provider options to allow time for replies:
{
"provider": {
"divyam": {
"options": {
"timeout": 180000
}
}
}
}
Keep the connection fields Kilo saved. Reload the extension after changing the file.
For an image-capable model, add "modalities": { "input": ["text", "image"], "output": ["text"] } to the existing provider.divyam.models["divyam-as/gpt-6-sol"] object in the same file. Reload the extension, then ask Kilo to read your image file.
3. Open an interactive chat
Open Kilo and choose Code mode. Review proposed edits and requested commands in the extension.
Hello, what are your capabilities?
Other editors, direct image attachments, reasoning controls, MCP, compaction and background 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.