Install Chatbox or open its web version. In Settings, open Model Provider and add an OpenAI-compatible provider. Set API Host to https://infistar.ai, enter your Infistar key, and keep the Chat Completions path /v1/chat/completions. Check the resulting request URL rather than adding /v1 twice. Add a model using its exact ID, save the provider, then select it in a new conversation. Enable image or tool capabilities only for models that support them.

​
Check the connection

Use an exact model ID available to your key, and begin with a short text request. For coding agents, first ask for a reply without reading or changing files or running commands. A successful text reply does not verify every tool or multimodal feature. For 401, check the key and its status. For 404, check the address and protocol. For model errors, recheck the model ID and selected group. See HTTP troubleshooting. Upstream documentation.