GitHub Copilot CLI
Connect Copilot CLI to Divyam for file edits and shell commands.
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 GitHub Copilot CLI
Follow the official installation instructions.
2. Set the provider and model
Model ID: divyam-as/gpt-6-sol. Context window: 1,050,000 tokens. Models and pricing
Export these settings in the same shell:
export COPILOT_PROVIDER_BASE_URL="https://api.preview.divyam.ai/v1"
export COPILOT_PROVIDER_API_KEY="divyam-sw-v1-..."
export COPILOT_PROVIDER_MODEL_ID="gpt-6-sol"
export COPILOT_PROVIDER_WIRE_MODEL="divyam-as/gpt-6-sol"
export COPILOT_PROVIDER_MAX_PROMPT_TOKENS=200000
export COPILOT_PROVIDER_MAX_OUTPUT_TOKENS=8192
The model profile is gpt-6-sol, while WIRE_MODEL is the ID sent to Divyam.
3. Send your first prompt
Start Copilot from the shell where you set the provider:
copilot --excluded-tools apply_patch
Hello, what are your capabilities?
The command excludes Copilot's grammar-based apply_patch tool. Copilot can edit files through its shell tool. MCP is 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.