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
To add another model or tier, copy the entry in
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 configuration
OpenClaw configuration
~/.openclaw/openclaw.json
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.
Use a local TUI without a Gateway
Use a local TUI without a Gateway
With the same configuration and your key exported:Use
/models and /think. Omit the startup --thinking flag, which overrides
the session’s effort selection.