From 99b92c4b23e61cf2fe65d937bd9e091188e6500e Mon Sep 17 00:00:00 2001
From: Krish Dholakia <krrishdholakia@gmail.com>
Date: Mon, 26 Feb 2024 15:22:50 -0800
Subject: [PATCH] Update README.md

---
 README.md | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/README.md b/README.md
index 6a4c738c5..deef7ddf2 100644
--- a/README.md
+++ b/README.md
@@ -68,6 +68,8 @@ response = completion(model="command-nightly", messages=messages)
 print(response)
 ```
 
+To call any model supported by a provider, just use `model=<provider_name>/<model_name>`. This way, LiteLLM will know which provider to route it to. There might be provider-specific details here (e.g. for vertex ai, any unmapped model is assumed to be a model garden endpoint). So refer to [provider docs for more information](https://docs.litellm.ai/docs/providers)
+
 ## Async ([Docs](https://docs.litellm.ai/docs/completion/stream#async-completion))
 
 ```python