diff --git a/docs/my-website/docs/completion/input.md b/docs/my-website/docs/completion/input.md
index 892cc17c6..96c6a936f 100644
--- a/docs/my-website/docs/completion/input.md
+++ b/docs/my-website/docs/completion/input.md
@@ -53,6 +53,9 @@ By default, LiteLLM raises an exception if the openai param being passed in isn'
 
 To drop the param instead, set `litellm.drop_params = True`.
 
+**For function calling:**
+
+Add to prompt for non-openai models, set: `litellm.add_function_to_prompt = True`. 
 ::: 
 
 ## Provider-specific Params
diff --git a/docs/my-website/docs/providers/vllm.md b/docs/my-website/docs/providers/vllm.md
index 90f945b42..df9e07ef7 100644
--- a/docs/my-website/docs/providers/vllm.md
+++ b/docs/my-website/docs/providers/vllm.md
@@ -30,10 +30,9 @@ In order to use litellm to call a hosted vllm server add the following to your c
 import litellm 
 
 response = completion(
-            model="facebook/opt-125m", # pass the vllm model name
+            model="openai/facebook/opt-125m", # pass the vllm model name
             messages=messages,
             api_base="https://hosted-vllm-api.co",
-            custom_llm_provider="openai",
             temperature=0.2,
             max_tokens=80)