Use the NextChat release appropriate to your system. In Settings, select OpenAI and enable the custom endpoint. Set the endpoint host to https://infistar.ai and enter your Infistar key. This client appends the API path, so check that the final address contains /v1 once. In Custom Models, enter exact model IDs; separate multiple IDs with commas. Save and start a new conversation with the model. A web installation may impose its own provider or network restrictions. If the browser reports Failed to fetch, check that installation’s configuration or use the desktop client.

​
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.