Skip to main content

OpenClaw

Before you start

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 OpenClaw​

Follow the official installation instructions.

2. Add the Divyam model​

divyam-as/

Model ID: divyam-as/gpt-6-sol. Context window: 1,050,000 tokens. Models and pricing

Merge this into ~/.openclaw/openclaw.json, keeping your existing settings. Replace /REPLACE/WITH/YOUR/PROJECT on the workspace line with your project's absolute path. Replace divyam-sw-v1-... with your key:

{
  "agents": {
    "defaults": {
      "model": {
        "primary": "divyam/divyam-as/gpt-6-sol"
      },
      "workspace": "/REPLACE/WITH/YOUR/PROJECT"
    }
  },
  "models": {
    "providers": {
      "divyam": {
        "baseUrl": "https://api.preview.divyam.ai/v1",
        "apiKey": "divyam-sw-v1-...",
        "models": [
          {
            "id": "divyam-as/gpt-6-sol",
            "name": "GPT-6 Sol",
            "contextWindow": 128000,
            "maxTokens": 8192
          }
        ]
      }
    }
  }
}

The leading divyam/ selects this provider, while OpenClaw sends divyam-as/gpt-6-sol as the API model ID.

3. Open the local terminal UI​

Start OpenClaw's local interactive UI without a gateway:

openclaw tui --local --thinking off
In OpenClaw's composer
Hello, what are your capabilities?
Paste this message, then send it.
Images

To inspect images with an image-capable model, add "input": ["text", "image"] to that model's object inside models.providers.divyam.models.

Feature limits

For messaging, personal connectors or remote gateways, follow the OpenClaw documentation.

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.

Local cost estimates

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.