Using Ads for Credits in Open WebUI

Last updated 2026-08-31

Open WebUI is a self-hosted chat interface, usually run in Docker. It accepts any number of OpenAI-compatible endpoints side by side, so this can be added without disturbing what you already use.

The three values

Every client needs the same three. Sign in and take them from the console.

• Base URL — https://onomeo.com/v1
• API key — the key shown in your console, starting ac-
• Model — one of the names on the models page

Step by step

1. Open Settings, then Connections.
2. Add an OpenAI API connection.
3. URL: paste ours. Key: paste yours.
4. Save. Open WebUI will query the endpoint for its model list.
5. Start a new chat and pick the model from the selector at the top.

If the model list comes back empty

Open WebUI reads the model list from the endpoint itself. An empty list almost always means the key was rejected, not that there are no models — check the key first.

Because connections sit side by side, an unreachable one can slow down the model selector for every provider. Remove connections you are not using.

Checking it worked

If the model appears in the selector at all, the key and endpoint are already accepted — Open WebUI could not have fetched that list otherwise. Send a message to confirm the call reaches the console.

If it does not connect

A 401 usually means the key was copied with a trailing space. A 404 means the base URL has /v1 twice or not at all — try it the other way. A 400 saying the model is not allowed means the tool sent its own default name instead of one of ours. The full table is on the clients page.

---

在 Open WebUI 中使用

最后更新 2026-08-31

Open WebUI 是一款自托管的对话界面，通常以 Docker 方式运行。它支持同时配置多个 OpenAI 兼容接口，因此可以在不影响现有配置的情况下添加本服务。

需要填的三个值

所有客户端要的都是这三个。登录后在控制台获取。

• 接口地址 — https://onomeo.com/v1
• 密钥 — 控制台中显示的密钥，以 ac- 开头
• 模型名称 — 模型页面所列名称之一

操作步骤

1. 打开 Settings，进入 Connections。
2. 添加一个 OpenAI API 连接。
3. URL 填入本站接口地址，Key 填入您的密钥。
4. 保存。Open WebUI 会自动向该接口查询可用模型列表。
5. 新建对话，在顶部的模型选择器中选择模型。

若模型列表为空

Open WebUI 通过接口自动读取模型列表。列表为空几乎都意味着密钥未通过验证，而非确实没有可用模型，请先检查密钥。

由于多个连接并列存在，某个无法访问的连接会拖慢所有服务商的模型选择器。建议移除不再使用的连接。

如何确认配置成功

只要模型出现在选择器中，即说明密钥与接口均已通过验证——否则 Open WebUI 无法取得该列表。发送一条消息即可确认调用已到达控制台。

连接失败时

返回 401 通常是密钥复制时末尾带了空格；返回 404 是接口地址中 /v1 重复或缺失，改成另一种写法即可；返回 400 且提示模型不被允许，说明客户端发送的是它自带的默认模型名，需手动填写本站的名称。完整对照表见客户端总览。