Use LithosAI with OpenClaw

Before you begin

Install OpenClaw, create a key on the API Keys page, and confirm the model ID you want to use on the Models page.

Export your LithosAI key

Export the key in the environment that runs the OpenClaw Gateway.

export LITHOSAI_API_KEY="your-key"

The Gateway process itself must see LITHOSAI_API_KEY. Exporting it in another shell does not update a running service; restart the Gateway after changing it.

Add LithosAI as a custom provider

Merge the following settings into ~/.openclaw/openclaw.json.

~/.openclaw/openclaw.json

{
  agents: {
    defaults: {
      model: { primary: "lithosai/moonshotai/Kimi-K3" }
    }
  },
  models: {
    mode: "merge",
    providers: {
      lithosai: {
        baseUrl: "https://api.lithosai.cloud/v1",
        apiKey: "${LITHOSAI_API_KEY}",
        api: "openai-completions",
        models: [
          {
            id: "moonshotai/Kimi-K3",
            name: "Kimi K3 on LithosAI",
            input: ["text"]
          }
        ]
      }
    }
  }
}

Replace the model ID if you selected a different model in the LithosAI console.

Check and restart OpenClaw

Validate the configuration, then restart the Gateway so it reads the new provider.

openclaw doctor
openclaw gateway restart

Troubleshooting

Symptom	Cause
The model does not appear	The provider was not merged into `models.providers`, or the Gateway has not restarted.
Authentication fails	`LITHOSAI_API_KEY` is unavailable to the Gateway process.
OpenClaw uses a different model	`agents.defaults.model.primary` does not use the `lithosai/` provider prefix.

Issues common to every agent are listed under Common issues.

Getting Started

Inference APIs

Account

Use LithosAI with OpenClaw

Before you begin

Verify the connection

Troubleshooting

Resources

​Before you begin

​Verify the connection

​Troubleshooting

​Resources

Before you begin

Verify the connection

Troubleshooting

Resources