Skip to main content

Before you begin

Install OpenClaw CLI, create a key on the API Keys page, and choose a model on the Models page.
1

Set your API key

Set your key in the Gateway’s environment:
For a managed service, set the variable in its service configuration.
2

Configure LithosAI

The configuration uses deepseek-ai/DeepSeek-V4.1-Flash as an example.Merge into ~/.openclaw/openclaw.json, keeping existing settings. Set the token limits to match your model.
~/.openclaw/openclaw.json
To add another model or tier, copy the entry in models.providers.lithosai.models. Set id and name to the ID from the model catalog, and adjust contextWindow and maxTokens to match the model. Also add lithosai/<model-id> to agents.defaults.models.
3

Restart the Gateway

Restart your Gateway to load the provider and key:

Model and reasoning effort

  • Model and tier: Use /model lithosai/<model-id>; in the TUI, use /models.
  • Reasoning effort: Use /think low, /think high, or /think max.
With the same configuration and your key exported:
Use /models and /think. Omit the startup --thinking flag, which overrides the session’s effort selection.
Issues common to every agent are listed under Common issues.

Resources