diff --git a/docs/my-website/docs/completion/input.md b/docs/my-website/docs/completion/input.md
index c1ae22c82f..53826c9d0f 100644
--- a/docs/my-website/docs/completion/input.md
+++ b/docs/my-website/docs/completion/input.md
@@ -1,4 +1,4 @@
-# Input Format - completion()
+# Input Format
 The Input params are **exactly the same** as the 
 <a href="https://platform.openai.com/docs/api-reference/chat/create" target="_blank" rel="noopener noreferrer">OpenAI Create chat completion</a>, and let you call Azure OpenAI, Anthropic, Cohere, Replicate, OpenRouter models in the same format. 
 
diff --git a/docs/my-website/docs/completion/model_alias.md b/docs/my-website/docs/completion/model_alias.md
new file mode 100644
index 0000000000..0e6e897099
--- /dev/null
+++ b/docs/my-website/docs/completion/model_alias.md
@@ -0,0 +1,49 @@
+# Model Alias
+
+Model names can be long, and you might want to use more user-friendly names for your end-users - e.g. Calling it `GPT-3.5` when the model name is `gpt-3.5-turbo-16k`. 
+
+LiteLLM supports this by letting you pass in a model alias mapping. 
+
+# usage 
+
+### Relevant Code
+```
+model_alias_map = {
+    "GPT-3.5": "gpt-3.5-turbo-16k",
+    "llama2": "replicate/llama-2-70b-chat:2796ee9483c3fd7aa2e171d38f4ca12251a30609463dcfd4cd76703f22e96cdf"
+}
+
+litellm.model_alias_map = model_alias_map
+```
+
+### Complete Code
+```
+import litellm 
+from litellm import completion 
+
+
+## set ENV variables
+os.environ["OPENAI_API_KEY"] = "openai key"
+os.environ["REPLICATE_API_KEY"] = "cohere key"
+
+## set model alias map
+model_alias_map = {
+    "GPT-3.5": "gpt-3.5-turbo-16k",
+    "llama2": "replicate/llama-2-70b-chat:2796ee9483c3fd7aa2e171d38f4ca12251a30609463dcfd4cd76703f22e96cdf"
+}
+
+litellm.model_alias_map = model_alias_map
+
+messages = [{ "content": "Hello, how are you?","role": "user"}]
+
+# openai call
+response = completion(model="GPT-3.5", messages=messages)
+
+# replicate call
+response = completion("llama2", messages)
+```
+
+
+# no-code
+
+If you use litellm client, you can also do this without going into code. [Learn more]("https://docs.litellm.ai/docs/debugging/hosted_debugging")
\ No newline at end of file
diff --git a/docs/my-website/docs/completion/output.md b/docs/my-website/docs/completion/output.md
index 4fb12c91d0..6f7f503ff3 100644
--- a/docs/my-website/docs/completion/output.md
+++ b/docs/my-website/docs/completion/output.md
@@ -1,4 +1,4 @@
-# Output Format - completion()
+# Output Format
 Here's the exact json output and type you can expect from all litellm `completion` calls for all models
 
 ```python 
diff --git a/docs/my-website/docs/completion/reliable_completions.md b/docs/my-website/docs/completion/reliable_completions.md
index 97d93e2147..eb37c3941e 100644
--- a/docs/my-website/docs/completion/reliable_completions.md
+++ b/docs/my-website/docs/completion/reliable_completions.md
@@ -1,4 +1,4 @@
-# Reliability for completion()
+# Reliability
 
 LiteLLM supports the following functions for reliability:
 * `completion_with_retries`: use tenacity retries
diff --git a/docs/my-website/sidebars.js b/docs/my-website/sidebars.js
index 1a28783566..e9bf50e3c8 100644
--- a/docs/my-website/sidebars.js
+++ b/docs/my-website/sidebars.js
@@ -22,7 +22,7 @@ const sidebars = {
     {
       type: "category",
       label: "Completion()",
-      items: ["completion/input", "completion/output", "completion/reliable_completions", "completion/stream"],
+      items: ["completion/input", "completion/output", "completion/model_alias", "completion/reliable_completions", "completion/stream"],
     },
     {
       type: "category",