OpenHands
Connect OpenHands to AudioLab Router.
Configure OpenHands
Create an AudioLab workspace key with llm.write and available credits. Use a model enabled for your workspace. Keep existing client permissions and tool approval settings.
Open Settings → LLM → Advanced. Use the OpenAI-compatible base URL, key, and openai/<AudioLab model ID>. Configure the condenser with the same provider if it should also use Router.
export LLM_BASE_URL="https://api.tryaudiolab.ai/v1"
export LLM_API_KEY="$AUDIOLAB_API_KEY"
export LLM_MODEL="openai/openai/gpt-6-astra"For the web app, enter those same values in LLM Settings with Advanced enabled. The extra openai/ prefix selects the LiteLLM adapter. If you use a separate condenser, configure its model and credentials too.
Verify the Connection
Send a short text prompt, then a read-only tool request in a disposable project. Check the model, request record, and usage in Router. Test streaming and a follow-up turn before using a longer workflow. Client-specific tools and permissions remain managed by OpenHands.
The setup command can check authentication and model discovery without generating a response. See the protocol contracts for model and feature limits.