diff --git a/docs/how-to/inference/embeddings.md b/docs/how-to/inference/embeddings.md
index ccd0ee86..75967338 100644
--- a/docs/how-to/inference/embeddings.md
+++ b/docs/how-to/inference/embeddings.md
@@ -20,6 +20,8 @@ for embedding in result:
     print(embedding.values[:5])   # first five values
 ```
 
+> **Tip:** You can also generate embeddings with the OpenAI client pointed at any OpenAI-compatible multi-model gateway — for example [DaoXE](https://daoxe.com/?utm_source=github&utm_medium=organic&utm_campaign=pinecone&utm_content=pr) at `https://api.daoxe.com/v1` — and upsert the resulting vectors into Pinecone.
+
 The ``parameters`` dict is model-specific. Common keys:
 
 - ``input_type`` — ``"query"`` for search queries, ``"passage"`` for documents being indexed.