Open your LobeChat installation and go to Settings → AI Providers. Select the OpenAI provider, enter your Infistar key and set its custom endpoint to https://infistar.ai/v1. Save the provider, then select an available model in a new conversation. Add its exact ID as a custom model if the list does not include it. Image input requires an image-capable model. LobeChat installations and versions can expose different settings; the administrator must permit custom provider configuration.

​
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.