diff --git a/docs/my-website/docs/completion/audio.md b/docs/my-website/docs/completion/audio.md
index 96b5e4f41c6..bfdd3d90a13 100644
--- a/docs/my-website/docs/completion/audio.md
+++ b/docs/my-website/docs/completion/audio.md
@@ -216,8 +216,8 @@ Use `litellm.supports_audio_input(model="")` -> returns `True` if model can acce
 assert litellm.supports_audio_output(model="gpt-4o-audio-preview") == True
 assert litellm.supports_audio_input(model="gpt-4o-audio-preview") == True
 
-assert litellm.supports_audio_output(model="gpt-3.5-turbo") == False
-assert litellm.supports_audio_input(model="gpt-3.5-turbo") == False
+assert litellm.supports_audio_output(model="gpt-4o") == False
+assert litellm.supports_audio_input(model="gpt-4o") == False
 ```
 </TabItem>
 
diff --git a/docs/my-website/docs/completion/batching.md b/docs/my-website/docs/completion/batching.md
index 5854f4db800..d588d7570fc 100644
--- a/docs/my-website/docs/completion/batching.md
+++ b/docs/my-website/docs/completion/batching.md
@@ -68,7 +68,7 @@ os.environ['OPENAI_API_KEY'] = ""
 os.environ['COHERE_API_KEY'] = ""
 
 response = batch_completion_models(
-    models=["gpt-3.5-turbo", "claude-instant-1.2", "command-nightly"], 
+    models=["gpt-4o", "claude-instant-1.2", "command-nightly"], 
     messages=[{"role": "user", "content": "Hey, how's it going"}]
 )
 print(result)
@@ -203,7 +203,7 @@ os.environ['OPENAI_API_KEY'] = ""
 os.environ['COHERE_API_KEY'] = ""
 
 responses = batch_completion_models_all_responses(
-    models=["gpt-3.5-turbo", "claude-instant-1.2", "command-nightly"], 
+    models=["gpt-4o", "claude-instant-1.2", "command-nightly"], 
     messages=[{"role": "user", "content": "Hey, how's it going"}]
 )
 print(responses)
@@ -259,7 +259,7 @@ print(responses)
   "id": "chatcmpl-80szFnKHzCxObW0RqCMw1hWW1Icrq",
   "object": "chat.completion",
   "created": 1695222061,
-  "model": "gpt-3.5-turbo-0613",
+  "model": "gpt-4o-0613",
   "choices": [
     {
       "index": 0,
diff --git a/docs/my-website/docs/completion/drop_params.md b/docs/my-website/docs/completion/drop_params.md
index cc32d3bbd32..b22315d3f00 100644
--- a/docs/my-website/docs/completion/drop_params.md
+++ b/docs/my-website/docs/completion/drop_params.md
@@ -210,7 +210,7 @@ client = openai.OpenAI(
 )
 
 response = client.chat.completions.create(
-    model="gpt-3.5-turbo",
+    model="gpt-4o",
     messages = [
         {
             "role": "user",
diff --git a/docs/my-website/docs/completion/function_call.md b/docs/my-website/docs/completion/function_call.md
index f10df68bf6f..bd4864d4405 100644
--- a/docs/my-website/docs/completion/function_call.md
+++ b/docs/my-website/docs/completion/function_call.md
@@ -5,7 +5,7 @@
 Use `litellm.supports_function_calling(model="")` -> returns `True` if model supports Function calling, `False` if not
 
 ```python
-assert litellm.supports_function_calling(model="gpt-3.5-turbo") == True
+assert litellm.supports_function_calling(model="gpt-4o") == True
 assert litellm.supports_function_calling(model="azure/gpt-4-1106-preview") == True
 assert litellm.supports_function_calling(model="palm/chat-bison") == False
 assert litellm.supports_function_calling(model="xai/grok-2-latest") == True
@@ -24,7 +24,7 @@ assert litellm.supports_parallel_function_calling(model="gpt-4") == False
 ## Parallel Function calling
 Parallel function calling is the model's ability to perform multiple function calls together, allowing the effects and results of these function calls to be resolved in parallel
 
-## Quick Start - gpt-3.5-turbo-1106
+## Quick Start - gpt-4o-1106
 <a target="_blank" href="https://colab.research.google.com/github/BerriAI/litellm/blob/main/cookbook/Parallel_function_calling.ipynb">
   <img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/>
 </a>
@@ -36,7 +36,7 @@ In this example we define a single function `get_current_weather`.
 - Step 3: Send the model the output from running the `get_current_weather` function
 
 
-### Full Code - Parallel function calling with `gpt-3.5-turbo-1106`
+### Full Code - Parallel function calling with `gpt-4o-1106`
 
 ```python
 import litellm
@@ -84,7 +84,7 @@ def test_parallel_function_call():
             }
         ]
         response = litellm.completion(
-            model="gpt-3.5-turbo-1106",
+            model="gpt-4o-1106",
             messages=messages,
             tools=tools,
             tool_choice="auto",  # auto is default, but we'll be explicit
@@ -122,7 +122,7 @@ def test_parallel_function_call():
                     }
                 )  # extend conversation with function response
             second_response = litellm.completion(
-                model="gpt-3.5-turbo-1106",
+                model="gpt-4o-1106",
                 messages=messages,
             )  # get a new response from the model where it can see the function response
             print("\nSecond LLM response:\n", second_response)
@@ -134,7 +134,7 @@ test_parallel_function_call()
 ```
 
 ### Explanation - Parallel function calling
-Below is an explanation of what is happening in the code snippet above for Parallel function calling with `gpt-3.5-turbo-1106`
+Below is an explanation of what is happening in the code snippet above for Parallel function calling with `gpt-4o-1106`
 ### Step1: litellm.completion() with `tools` set to `get_current_weather`
 ```python
 import litellm
@@ -178,7 +178,7 @@ tools = [
 ]
 
 response = litellm.completion(
-    model="gpt-3.5-turbo-1106",
+    model="gpt-4o-1106",
     messages=messages,
     tools=tools,
     tool_choice="auto",  # auto is default, but we'll be explicit
@@ -206,7 +206,7 @@ ModelResponse(
         ]))
     ], 
     created=1700319953, 
-    model='gpt-3.5-turbo-1106', 
+    model='gpt-4o-1106', 
     object='chat.completion', 
     system_fingerprint='fp_eeff13170a',
     usage={'completion_tokens': 77, 'prompt_tokens': 88, 'total_tokens': 165}, 
@@ -255,7 +255,7 @@ if tool_calls:
 Once the functions are executed, send the model the information for each function call and its response. This allows the model to generate a new response considering the effects of the function calls.
 ```python
 second_response = litellm.completion(
-    model="gpt-3.5-turbo-1106",
+    model="gpt-4o-1106",
     messages=messages,
 )
 print("Second Response\n", second_response)
@@ -270,7 +270,7 @@ ModelResponse(
     message=Message(content="The current weather in San Francisco is 72°F, in Tokyo it's 10°C, and in Paris it's 22°C.", role='assistant'))
   ], 
   created=1700319955, 
-  model='gpt-3.5-turbo-1106', 
+  model='gpt-4o-1106', 
   object='chat.completion', 
   system_fingerprint='fp_eeff13170a', 
   usage={'completion_tokens': 28, 'prompt_tokens': 169, 'total_tokens': 197}, 
@@ -415,7 +415,7 @@ functions = [
     }
   ]
 
-response = completion(model="gpt-3.5-turbo-0613", messages=messages, functions=functions)
+response = completion(model="gpt-4o-0613", messages=messages, functions=functions)
 print(response)
 ```
 
@@ -499,7 +499,7 @@ def get_current_weather(location: str, unit: str):
 
 functions = [litellm.utils.function_to_dict(get_current_weather)]
 
-response = completion(model="gpt-3.5-turbo-0613", messages=messages, functions=functions)
+response = completion(model="gpt-4o-0613", messages=messages, functions=functions)
 print(response)
 ```
 
diff --git a/docs/my-website/docs/completion/http_handler_config.md b/docs/my-website/docs/completion/http_handler_config.md
index d4a25ce2043..bae5995d4a3 100644
--- a/docs/my-website/docs/completion/http_handler_config.md
+++ b/docs/my-website/docs/completion/http_handler_config.md
@@ -18,7 +18,7 @@ import litellm
 
 # Works exactly as before
 response = await litellm.acompletion(
-    model="gpt-3.5-turbo",
+    model="gpt-4o",
     messages=[{"role": "user", "content": "Hello!"}]
 )
 ```
@@ -39,7 +39,7 @@ session = aiohttp.ClientSession(
 litellm.base_llm_aiohttp_handler = BaseLLMAIOHTTPHandler(client_session=session)
 
 # All completions now use your session
-response = await litellm.acompletion(model="gpt-3.5-turbo", messages=[...])
+response = await litellm.acompletion(model="gpt-4o", messages=[...])
 ```
 
 ## Common Patterns
@@ -69,7 +69,7 @@ app = FastAPI(lifespan=lifespan)
 
 @app.post("/chat")
 async def chat(messages: list[dict]):
-    return await litellm.acompletion(model="gpt-3.5-turbo", messages=messages)
+    return await litellm.acompletion(model="gpt-4o", messages=messages)
 ```
 
 ### Corporate Proxy
diff --git a/docs/my-website/docs/completion/input.md b/docs/my-website/docs/completion/input.md
index cc058935221..7e836078d5c 100644
--- a/docs/my-website/docs/completion/input.md
+++ b/docs/my-website/docs/completion/input.md
@@ -15,7 +15,7 @@ os.environ["OPENAI_API_KEY"] = "your-openai-key"
 
 ## SET MAX TOKENS - via completion() 
 response = litellm.completion(
-            model="gpt-3.5-turbo",
+            model="gpt-4o",
             messages=[{ "content": "Hello, how are you?","role": "user"}],
             max_tokens=10
         )
diff --git a/docs/my-website/docs/completion/mock_requests.md b/docs/my-website/docs/completion/mock_requests.md
index fc357b0d7d7..de2643dd4a8 100644
--- a/docs/my-website/docs/completion/mock_requests.md
+++ b/docs/my-website/docs/completion/mock_requests.md
@@ -8,7 +8,7 @@ This will return a response object with a default response (works for streaming
 ```python
 from litellm import completion 
 
-model = "gpt-3.5-turbo"
+model = "gpt-4o"
 messages = [{"role":"user", "content":"This is a test request"}]
 
 completion(model=model, messages=messages, mock_response="It's simple to use and easy to get started")
@@ -18,7 +18,7 @@ completion(model=model, messages=messages, mock_response="It's simple to use and
 
 ```python
 from litellm import completion 
-model = "gpt-3.5-turbo"
+model = "gpt-4o"
 messages = [{"role": "user", "content": "Hey, I'm a mock request"}]
 response = completion(model=model, messages=messages, stream=True, mock_response="It's simple to use and easy to get started")
 for chunk in response: 
@@ -60,7 +60,7 @@ import pytest
 def test_completion_openai():
     try:
         response = completion(
-            model="gpt-3.5-turbo",
+            model="gpt-4o",
             messages=[{"role":"user", "content":"Why is LiteLLM amazing?"}],
             mock_response="LiteLLM is awesome"
         )
diff --git a/docs/my-website/docs/completion/model_alias.md b/docs/my-website/docs/completion/model_alias.md
index 5fa83264993..d5620e510ef 100644
--- a/docs/my-website/docs/completion/model_alias.md
+++ b/docs/my-website/docs/completion/model_alias.md
@@ -1,6 +1,6 @@
 # Model Alias
 
-The model name you show an end-user might be different from the one you pass to LiteLLM - e.g. Displaying `GPT-3.5` while calling `gpt-3.5-turbo-16k` on the backend. 
+The model name you show an end-user might be different from the one you pass to LiteLLM - e.g. Displaying `GPT-3.5` while calling `gpt-4o-16k` on the backend. 
 
 LiteLLM simplifies this by letting you pass in a model alias mapping. 
 
@@ -18,7 +18,7 @@ litellm.model_alias_map = {
 ### Relevant Code
 ```python
 model_alias_map = {
-    "GPT-3.5": "gpt-3.5-turbo-16k",
+    "GPT-3.5": "gpt-4o-16k",
     "llama2": "replicate/llama-2-70b-chat:2796ee9483c3fd7aa2e171d38f4ca12251a30609463dcfd4cd76703f22e96cdf"
 }
 
@@ -37,7 +37,7 @@ os.environ["REPLICATE_API_KEY"] = "cohere key"
 
 ## set model alias map
 model_alias_map = {
-    "GPT-3.5": "gpt-3.5-turbo-16k",
+    "GPT-3.5": "gpt-4o-16k",
     "llama2": "replicate/llama-2-70b-chat:2796ee9483c3fd7aa2e171d38f4ca12251a30609463dcfd4cd76703f22e96cdf"
 }
 
@@ -45,7 +45,7 @@ litellm.model_alias_map = model_alias_map
 
 messages = [{ "content": "Hello, how are you?","role": "user"}]
 
-# call "gpt-3.5-turbo-16k"
+# call "gpt-4o-16k"
 response = completion(model="GPT-3.5", messages=messages)
 
 # call replicate/llama-2-70b-chat:2796ee9483c3fd7aa2e171d38f4ca1...
diff --git a/docs/my-website/docs/completion/prompt_caching.md b/docs/my-website/docs/completion/prompt_caching.md
index 402c7b9f4c7..0d2ef499c08 100644
--- a/docs/my-website/docs/completion/prompt_caching.md
+++ b/docs/my-website/docs/completion/prompt_caching.md
@@ -700,7 +700,7 @@ response = client.chat.completions.with_raw_response.create(
         "role": "user",
         "content": "Say this is a test",
     }],
-    model="gpt-3.5-turbo",
+    model="gpt-4o",
 )
 print(response.headers.get('x-litellm-response-cost'))
 
diff --git a/docs/my-website/docs/completion/provider_specific_params.md b/docs/my-website/docs/completion/provider_specific_params.md
index 250b410c9c4..92610984974 100644
--- a/docs/my-website/docs/completion/provider_specific_params.md
+++ b/docs/my-website/docs/completion/provider_specific_params.md
@@ -22,7 +22,7 @@ os.environ["OPENAI_API_KEY"] = "your-openai-key"
 
 ## SET MAX TOKENS - via completion() 
 response_1 = litellm.completion(
-            model="gpt-3.5-turbo",
+            model="gpt-4o",
             messages=[{ "content": "Hello, how are you?","role": "user"}],
             max_tokens=10
         )
@@ -33,7 +33,7 @@ response_1_text = response_1.choices[0].message.content
 litellm.OpenAIConfig(max_tokens=10)
 
 response_2 = litellm.completion(
-            model="gpt-3.5-turbo",
+            model="gpt-4o",
             messages=[{ "content": "Hello, how are you?","role": "user"}],
         )
 
diff --git a/docs/my-website/docs/completion/reliable_completions.md b/docs/my-website/docs/completion/reliable_completions.md
index f38917fe53d..32b280e5886 100644
--- a/docs/my-website/docs/completion/reliable_completions.md
+++ b/docs/my-website/docs/completion/reliable_completions.md
@@ -25,7 +25,7 @@ messages = [{"content": user_message, "role": "user"}]
 
 # normal call 
 response = completion(
-            model="gpt-3.5-turbo",
+            model="gpt-4o",
             messages=messages,
             num_retries=2
         )
@@ -43,10 +43,10 @@ response = completion(
 ```python 
 from litellm import completion
 
-fallback_dict = {"gpt-3.5-turbo": "gpt-3.5-turbo-16k"}
+fallback_dict = {"gpt-4o": "gpt-4o-16k"}
 messages = [{"content": "how does a court case get to the Supreme Court?" * 500, "role": "user"}]
 
-completion(model="gpt-3.5-turbo", messages=messages, context_window_fallback_dict=fallback_dict)
+completion(model="gpt-4o", messages=messages, context_window_fallback_dict=fallback_dict)
 ```
 
 ### Fallbacks - Switch Models/API Keys/API Bases (SDK)
@@ -61,7 +61,7 @@ The `fallbacks` list should include the primary model you want to use, followed
 #### switch models 
 ```python
 response = completion(model="bad-model", messages=messages, 
-    fallbacks=["gpt-3.5-turbo" "command-nightly"])
+    fallbacks=["gpt-4o" "command-nightly"])
 ```
 
 #### switch api keys/bases (E.g. azure deployment)
@@ -84,12 +84,12 @@ Completion with 'bad-model': got exception Unable to map your input to a model.
 
 
 
-completion call gpt-3.5-turbo
+completion call gpt-4o
 {
   "id": "chatcmpl-7qTmVRuO3m3gIBg4aTmAumV1TmQhB",
   "object": "chat.completion",
   "created": 1692741891,
-  "model": "gpt-3.5-turbo-0613",
+  "model": "gpt-4o-0613",
   "choices": [
     {
       "index": 0,
diff --git a/docs/my-website/docs/completion/stream.md b/docs/my-website/docs/completion/stream.md
index 088437a76d9..370f92e9c50 100644
--- a/docs/my-website/docs/completion/stream.md
+++ b/docs/my-website/docs/completion/stream.md
@@ -15,7 +15,7 @@ LiteLLM supports streaming the model response back by passing `stream=True` as a
 ```python
 from litellm import completion
 messages = [{"role": "user", "content": "Hey, how's it going?"}]
-response = completion(model="gpt-3.5-turbo", messages=messages, stream=True)
+response = completion(model="gpt-4o", messages=messages, stream=True)
 for part in response:
     print(part.choices[0].delta.content or "")
 ```
@@ -27,7 +27,7 @@ LiteLLM also exposes a helper function to rebuild the complete streaming respons
 ```python
 from litellm import completion
 messages = [{"role": "user", "content": "Hey, how's it going?"}]
-response = completion(model="gpt-3.5-turbo", messages=messages, stream=True)
+response = completion(model="gpt-4o", messages=messages, stream=True)
 
 for chunk in response: 
     chunks.append(chunk)
@@ -45,7 +45,7 @@ import asyncio
 async def test_get_response():
     user_message = "Hello, how are you?"
     messages = [{"content": user_message, "role": "user"}]
-    response = await acompletion(model="gpt-3.5-turbo", messages=messages)
+    response = await acompletion(model="gpt-4o", messages=messages)
     return response
 
 response = asyncio.run(test_get_response())
@@ -66,7 +66,7 @@ async def completion_call():
     try:
         print("test acompletion + streaming")
         response = await acompletion(
-            model="gpt-3.5-turbo", 
+            model="gpt-4o", 
             messages=[{"content": "Hello, how are you?", "role": "user"}], 
             stream=True
         )
@@ -106,7 +106,7 @@ chunks = [
     "id": "chatcmpl-123",
     "object": "chat.completion.chunk",
     "created": 1694268190,
-    "model": "gpt-3.5-turbo-0125",
+    "model": "gpt-4o-0125",
     "system_fingerprint": "fp_44709d6fcb",
     "choices": [
         {"index": 0, "delta": {"content": "How are you?"}, "finish_reason": "stop"}
@@ -117,10 +117,10 @@ completion_stream = litellm.ModelResponseListIterator(model_responses=chunks)
 
 response = litellm.CustomStreamWrapper(
     completion_stream=completion_stream,
-    model="gpt-3.5-turbo",
+    model="gpt-4o",
     custom_llm_provider="cached_response",
     logging_obj=litellm.Logging(
-        model="gpt-3.5-turbo",
+        model="gpt-4o",
         messages=[{"role": "user", "content": "Hey"}],
         stream=True,
         call_type="completion",
diff --git a/docs/my-website/docs/completion/token_usage.md b/docs/my-website/docs/completion/token_usage.md
index d99564765a1..b5c617dd09f 100644
--- a/docs/my-website/docs/completion/token_usage.md
+++ b/docs/my-website/docs/completion/token_usage.md
@@ -7,7 +7,7 @@ LiteLLM returns `response_cost` in all calls.
 from litellm import completion 
 
 response = litellm.completion(
-            model="gpt-3.5-turbo",
+            model="gpt-4o",
             messages=[{"role": "user", "content": "Hey, how's it going?"}],
             mock_response="Hello world",
         )
@@ -49,7 +49,7 @@ from litellm import encode, decode
 
 sample_text = "Hellö World, this is my input string!"
 # openai encoding + decoding
-openai_tokens = encode(model="gpt-3.5-turbo", text=sample_text)
+openai_tokens = encode(model="gpt-4o", text=sample_text)
 print(openai_tokens)
 ```
 
@@ -62,8 +62,8 @@ from litellm import encode, decode
 
 sample_text = "Hellö World, this is my input string!"
 # openai encoding + decoding
-openai_tokens = encode(model="gpt-3.5-turbo", text=sample_text)
-openai_text = decode(model="gpt-3.5-turbo", tokens=openai_tokens)
+openai_tokens = encode(model="gpt-4o", text=sample_text)
+openai_text = decode(model="gpt-4o", tokens=openai_tokens)
 print(openai_text)
 ```
 
@@ -73,7 +73,7 @@ print(openai_text)
 from litellm import token_counter
 
 messages = [{"user": "role", "content": "Hey, how's it going"}]
-print(token_counter(model="gpt-3.5-turbo", messages=messages))
+print(token_counter(model="gpt-4o", messages=messages))
 ```
 
 ### 4. `create_pretrained_tokenizer` and `create_tokenizer`
@@ -100,7 +100,7 @@ from litellm import cost_per_token
 
 prompt_tokens =  5
 completion_tokens = 10
-prompt_tokens_cost_usd_dollar, completion_tokens_cost_usd_dollar = cost_per_token(model="gpt-3.5-turbo", prompt_tokens=prompt_tokens, completion_tokens=completion_tokens)
+prompt_tokens_cost_usd_dollar, completion_tokens_cost_usd_dollar = cost_per_token(model="gpt-4o", prompt_tokens=prompt_tokens, completion_tokens=completion_tokens)
 
 print(prompt_tokens_cost_usd_dollar, completion_tokens_cost_usd_dollar)
 ```
@@ -134,13 +134,13 @@ print(formatted_string)
 ```
 ### 7. `get_max_tokens`
 
-Input: Accepts a model name - e.g., gpt-3.5-turbo (to get a complete list, call litellm.model_list).
+Input: Accepts a model name - e.g., gpt-4o (to get a complete list, call litellm.model_list).
 Output: Returns the maximum number of tokens allowed for the given model
 
 ```python 
 from litellm import get_max_tokens 
 
-model = "gpt-3.5-turbo"
+model = "gpt-4o"
 
 print(get_max_tokens(model)) # Output: 4097
 ```
@@ -152,7 +152,7 @@ print(get_max_tokens(model)) # Output: 4097
 ```python 
 from litellm import model_cost 
 
-print(model_cost) # {'gpt-3.5-turbo': {'max_tokens': 4000, 'input_cost_per_token': 1.5e-06, 'output_cost_per_token': 2e-06}, ...}
+print(model_cost) # {'gpt-4o': {'max_tokens': 4000, 'input_cost_per_token': 1.5e-06, 'output_cost_per_token': 2e-06}, ...}
 ```
 
 ### 9. `register_model`
diff --git a/docs/my-website/docs/completion/usage.md b/docs/my-website/docs/completion/usage.md
index d610afeae55..fa66ae401ea 100644
--- a/docs/my-website/docs/completion/usage.md
+++ b/docs/my-website/docs/completion/usage.md
@@ -20,7 +20,7 @@ import os
 os.environ["OPENAI_API_KEY"] = "your-api-key"
 
 response = completion(
-  model="gpt-3.5-turbo",
+  model="gpt-4o",
   messages=[{ "content": "Hello, how are you?","role": "user"}]
 )
 
diff --git a/docs/my-website/docs/completion/vision.md b/docs/my-website/docs/completion/vision.md
index 90d6b2393fb..c08aeff8531 100644
--- a/docs/my-website/docs/completion/vision.md
+++ b/docs/my-website/docs/completion/vision.md
@@ -120,7 +120,7 @@ Use `litellm.supports_vision(model="")` -> returns `True` if model supports `vis
 ```python
 assert litellm.supports_vision(model="openai/gpt-4-vision-preview") == True
 assert litellm.supports_vision(model="vertex_ai/gemini-1.0-pro-vision") == True
-assert litellm.supports_vision(model="openai/gpt-3.5-turbo") == False
+assert litellm.supports_vision(model="openai/gpt-4o") == False
 assert litellm.supports_vision(model="xai/grok-2-vision-latest") == True
 assert litellm.supports_vision(model="xai/grok-2-latest") == False
 ```