ClawBox AI (default)
Works immediately, no keys to manage. The simplest way to get started — and a great default for most people.Bring your own provider
Prefer a specific model? ClawBox treats these as first-class options:Anthropic Claude
Add your Anthropic API key to drive ClawBox with Claude models.
OpenAI GPT
Use your OpenAI API key for GPT models.
Google Gemini
Connect Gemini with a Google AI API key.
OpenRouter
One key, many models — route across providers.
Local models
For fully on-device inference, ClawBox supports local Ollama and llama.cpp models. This is an option for users who want it rather than the default path.Local model performance depends on your hardware. ClawBox Workstation (DGX Spark,
128 GB unified memory) can run models up to ~200B parameters locally; ClawBox
Connect (Jetson Orin Nano) is best paired with cloud providers or smaller local models.
See Hardware.
Reasoning effort
You can control how hard the model thinks before answering, per conversation, from the brain icon in the chat header. More thinking gives better answers on hard problems, and costs more time and tokens. The picker offers the same four levels on every cloud provider — Off, Low, Medium, High — so it works the same way whichever model you choose.- ClawBox AI starts at Off, so everyday prompts stay fast and you turn reasoning on when a task needs it.
- Claude, GPT, Gemini and OpenRouter start at Medium.
- The on-device local model has no reasoning control, so the brain icon does not appear when it is selected.
For the technical detail of how model reasoning capability is configured — and why it is set in code rather than by hand — see AI Providers → Reasoning effort.