Skip to main content

OpenClaw Setup on Windows with Custom Provider

1. Install OpenClaw

You can install OpenClaw using the official installer or via npm.

Windows (PowerShell)

macOS / Linux

This installs OpenClaw and performs the initial setup automatically.

Option 2: Install via npm

Requires Node.js to be installed.

Verify Installation

You should see the installed OpenClaw version displayed.

2. Locate the Configuration File

Open:
or
Replace the entire contents of openclaw.json with:
If you need to add additional models, ensure you add them to both the agents.defaults.models object and the models.providers.znapai.models array in the JSON file using the same format as gpt-5.3-codex.

3. Configure API Key

Set the API key as an environment variable:

For Current PowerShell Session

Verify:

Permanent Configuration

Open a new PowerShell window and verify:

4. Validate Configuration

No output means the JSON is valid.

5. Start OpenClaw Gateway

Expected output:

6. Verify Gateway Health

Open another terminal:
Expected:
Check status:
Expected:

7. Launch OpenClaw

OpenClaw Terminal
Initially, OpenClaw launches into Crestodian, the setup and troubleshooting assistant. Example:
Crestodian is not the main conversational agent. To switch to the actual chat agent, type:
Expected output:
After switching, you can chat normally with the configured model.

Troubleshooting

JSON Syntax Error

Example:
Missing comma. Correct:

Unknown Model Error

Ensure:
  • Provider name is znapai
  • Default model is znapai/gpt-5.3-codex
  • Model exists under models.providers.znapai.models[]

Gateway Start Blocked

Ensure:
exists in the configuration.