MiniMax Code CLI
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 MiniMax Code CLI
Follow the official installation instructions.
Set your key in the shell you will use to start MiniMax Code:
export MCODE_PROVIDER_API_KEY="divyam-sw-v1-..."
2. Connect Divyam and choose a model
Model ID: divyam-as/gpt-6-sol. Context window: 1,050,000 tokens. Models and pricing
Add Divyam with MiniMax's custom-provider command:
mcode provider add \
--name Divyam \
--base-url https://api.preview.divyam.ai/v1 \
--api-format openai-completions \
--model divyam-as/gpt-6-sol
Replace the shortened key with your complete key before running the command. For an image-capable model, include --support-image when adding the provider.
Open ~/.minimax/config.yaml and add or update this root-level setting:
defaultModel: custom_provider:divyam/divyam-as/gpt-6-sol
Use the provider ID from the file's custom_provider section. Replace divyam in this setting if that ID differs.
3. Send your first prompt
From your project folder, run:
mcode
Hello, what are your capabilities?
Review proposed changes and tool approvals in the terminal.
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.