diff --git a/docs/getting-started/quick-start/connect-a-provider/starting-with-openai-compatible.mdx b/docs/getting-started/quick-start/connect-a-provider/starting-with-openai-compatible.mdx
index ac677794c..da38a4234 100644
--- a/docs/getting-started/quick-start/connect-a-provider/starting-with-openai-compatible.mdx
+++ b/docs/getting-started/quick-start/connect-a-provider/starting-with-openai-compatible.mdx
@@ -251,6 +251,21 @@ Each connection has a **toggle switch** that lets you enable or disable it witho
   Vercel AI Gateway implements the OpenAI Chat Completions API, including `/models` and `/chat/completions`, so you can add it as a normal OpenAI-compatible connection in Open WebUI. Use the model IDs shown in the [AI Gateway model catalog](https://vercel.com/ai-gateway/models).
   :::
 
+  </TabItem>
+  <TabItem value="synthorai" label="Synthorai">
+
+  **Synthorai** provides a single OpenAI-compatible endpoint for models from multiple upstream providers, with per-key model permissions and spend limits.
+
+  | Setting | Value |
+  |---|---|
+  | **URL** | `https://synthorai.io/v1` |
+  | **API Key** | Your API key from the [Synthorai console](https://synthorai.io/docs/quickstart/) |
+  | **Model IDs** | Auto-detected, leave empty or filter to specific models |
+
+  :::tip
+  `/models` returns the models **your key is permitted to use**, not the whole catalog, so the list you see depends on the key. If a model you expect is missing, check that key's model permissions rather than adding the ID by hand. The [model catalog](https://synthorai.io/models/) lists what is available overall.
+  :::
+
   </TabItem>
   <TabItem value="openrouter" label="OpenRouter">