Dexto
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 Dexto and copy its coding agent
Install Dexto using the official instructions. Open your project folder before configuring the coding agent.
2. Set the Divyam connection
Follow the official agent-installation instructions for the coding-agent preset. Locate it with dexto which coding-agent, then copy its complete directory, including skills, into your project as divyam-coding-agent.
Set your Divyam key in the same terminal:
export DIVYAM_API_KEY="divyam-sw-v1-..."
Model ID: divyam-as/gpt-6-sol. Context window: 1,050,000 tokens. Models and pricing
In divyam-coding-agent/coding-agent.yml, replace only the llm block with these provider settings. Keep the rest of the preset and its skills:
llm:
provider: openai-compatible
model: divyam-as/gpt-6-sol
apiKey: $DIVYAM_API_KEY
baseURL: https://api.preview.divyam.ai/v1
maxInputTokens: 100000
maxOutputTokens: 8192
3. Start an interactive session
From your project folder, run:
dexto --mode cli --agent ./divyam-coding-agent/coding-agent.yml
Review tool requests in the terminal.
Hello, what are your capabilities?
Images, compaction, MCP, search, skills and delegation 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.