---
title: "Open WebUI setup"
description: "Configure Open WebUI for Infistar and check the address, key and model."
lastUpdated: 2026-10-22
---

You need an existing Open WebUI installation and an administrator account. Open Settings → Admin → Connections and add an OpenAI-compatible connection.

Use `https://infistar.ai/v1` as the URL and your Infistar key as the API key. Save and enable the connection. If discovery does not show the required model, add its exact ID to the connection's Model IDs allowlist.

The machine running Open WebUI must be able to reach Infistar. A successful request from your desktop does not prove that a separate server has connectivity. Do not append `/models` or `/chat/completions` to the configured base URL.


## 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](/en/troubleshooting/http-status-troubleshooting).

[Upstream documentation](https://docs.openwebui.com/getting-started/quick-start/connect-a-provider/starting-with-openai-compatible/).