OpenClaw

Prepare API Access

Have the three items below ready before you configure anything:

API Key

The key string you generated when creating your API Key.

Base URL

https://api.watt-cloud.com/v1

The trailing /v1 is required - do not drop it.

Model Name

Take the complete model identifier from the Model Marketplace, for example DeepSeek-V4-Pro.

On Linux or macOS, pipe the OpenClaw install script into bash:

curl -fsSL https://openclaw.ai/install.sh | bash

Windows instead gets a PowerShell one-liner:

iwr -useb https://openclaw.ai/install.ps1 | iex

Launch the OpenClaw terminal and enter:

openclaw configure

Then walk through the prompts in this order:

Choose local (this machine gets configured)
Choose model
Pick custom provider
When the platform address is requested, type https://api.watt-cloud.com/v1
Paste in your API Key
Take the first option: OpenAI-compatible endpoint
Supply a model name (GLM-5.1 / DeepSeek-V4-Pro / MiniMax-M2.7)
Let the verification run to completion
Change the provider name to one you set yourself ("watt" or "mx" is recommended for easier handling)
Optionally rename the model as well (short forms such as "glm", "deepseek" work well)

Restart the gateway so the new settings take effect:

openclaw gateway restart

List what is available:

/models [your-provider-name]

For instance: /models watt

Then make the switch:

/model [provider-name]/[your-model-name]

For instance: /model watt/GLM-5.1