diff --git a/docs/my-website/docs/adding_provider/adding_guardrail_support.md b/docs/my-website/docs/adding_provider/adding_guardrail_support.md
index 2646b626ab5..ad76785a33a 100644
--- a/docs/my-website/docs/adding_provider/adding_guardrail_support.md
+++ b/docs/my-website/docs/adding_provider/adding_guardrail_support.md
@@ -321,7 +321,7 @@ curl -X POST 'http://localhost:4000/{my_endpoint}' \
 -H 'Content-Type: application/json' \
 -H 'Authorization: Bearer your-api-key' \
 -d '{
-    "model": "gpt-3.5-turbo",
+    "model": "gpt-4o",
     "messages": [{"role": "user", "content": "Hello"}],
     "guardrails": ["test"]
 }'
diff --git a/docs/my-website/docs/adding_provider/generic_prompt_management_api.md b/docs/my-website/docs/adding_provider/generic_prompt_management_api.md
index d1b119d94c5..c6896ac1243 100644
--- a/docs/my-website/docs/adding_provider/generic_prompt_management_api.md
+++ b/docs/my-website/docs/adding_provider/generic_prompt_management_api.md
@@ -131,9 +131,9 @@ Add to `config.yaml`:
 
 ```yaml
 model_list:
-  - model_name: gpt-3.5-turbo
+  - model_name: gpt-4o
     litellm_params:
-      model: openai/gpt-3.5-turbo
+      model: openai/gpt-4o
       api_key: os.environ/OPENAI_API_KEY
 
 prompts:
diff --git a/docs/my-website/docs/caching/all_caches.md b/docs/my-website/docs/caching/all_caches.md
index 6f81da9105a..02dda99f7a3 100644
--- a/docs/my-website/docs/caching/all_caches.md
+++ b/docs/my-website/docs/caching/all_caches.md
@@ -39,11 +39,11 @@ litellm.cache = Cache(type="redis", host=<host>, port=<port>, password=<password
 
 # Make completion calls
 response1 = completion(
-    model="gpt-3.5-turbo",
+    model="gpt-4o",
     messages=[{"role": "user", "content": "Tell me a joke."}]
 )
 response2 = completion(
-    model="gpt-3.5-turbo",
+    model="gpt-4o",
     messages=[{"role": "user", "content": "Tell me a joke."}]
 )
 
@@ -77,11 +77,11 @@ litellm.cache = RedisClusterCache(
 
 # Make completion calls
 response1 = completion(
-    model="gpt-3.5-turbo",
+    model="gpt-4o",
     messages=[{"role": "user", "content": "Tell me a joke."}]
 )
 response2 = completion(
-    model="gpt-3.5-turbo",
+    model="gpt-4o",
     messages=[{"role": "user", "content": "Tell me a joke."}]
 )
 
@@ -132,11 +132,11 @@ from litellm.caching.caching import Cache
 litellm.cache = Cache(type="gcs", gcs_bucket_name="my-cache-bucket", gcs_path_service_account="/path/to/service_account.json")
 
 response1 = completion(
-    model="gpt-3.5-turbo",
+    model="gpt-4o",
     messages=[{"role": "user", "content": "Tell me a joke."}]
 )
 response2 = completion(
-    model="gpt-3.5-turbo",
+    model="gpt-4o",
     messages=[{"role": "user", "content": "Tell me a joke."}]
 )
 
@@ -170,11 +170,11 @@ litellm.cache = Cache(type="s3", s3_bucket_name="cache-bucket-litellm", s3_regio
 
 # Make completion calls
 response1 = completion(
-    model="gpt-3.5-turbo", 
+    model="gpt-4o", 
     messages=[{"role": "user", "content": "Tell me a joke."}]
 )
 response2 = completion(
-    model="gpt-3.5-turbo", 
+    model="gpt-4o", 
     messages=[{"role": "user", "content": "Tell me a joke."}]
 )
 
@@ -201,11 +201,11 @@ litellm.cache = Cache(type="azure-blob", azure_account_url="https://example.blob
 
 # Make completion calls
 response1 = completion(
-    model="gpt-3.5-turbo",
+    model="gpt-4o",
     messages=[{"role": "user", "content": "Tell me a joke."}]
 )
 response2 = completion(
-    model="gpt-3.5-turbo",
+    model="gpt-4o",
     messages=[{"role": "user", "content": "Tell me a joke."}]
 )
 
@@ -244,7 +244,7 @@ litellm.cache = Cache(
     redis_semantic_cache_embedding_model="text-embedding-ada-002", # this model is passed to litellm.embedding(), any litellm.embedding() model is supported here
 )
 response1 = completion(
-    model="gpt-3.5-turbo",
+    model="gpt-4o",
     messages=[
         {
             "role": "user",
@@ -258,7 +258,7 @@ print(f"response1: {response1}")
 random_number = random.randint(1, 100000)
 
 response2 = completion(
-    model="gpt-3.5-turbo",
+    model="gpt-4o",
     messages=[
         {
             "role": "user",
@@ -301,7 +301,7 @@ litellm.cache = Cache(
 )
 
 response1 = completion(
-    model="gpt-3.5-turbo",
+    model="gpt-4o",
     messages=[
         {
             "role": "user",
@@ -315,7 +315,7 @@ print(f"response1: {response1}")
 random_number = random.randint(1, 100000)
 
 response2 = completion(
-    model="gpt-3.5-turbo",
+    model="gpt-4o",
     messages=[
         {
             "role": "user",
@@ -343,12 +343,12 @@ litellm.cache = Cache()
 
 # Make completion calls
 response1 = completion(
-    model="gpt-3.5-turbo", 
+    model="gpt-4o", 
     messages=[{"role": "user", "content": "Tell me a joke."}],
     caching=True
 )
 response2 = completion(
-    model="gpt-3.5-turbo", 
+    model="gpt-4o", 
     messages=[{"role": "user", "content": "Tell me a joke."}],
     caching=True
 )
@@ -379,12 +379,12 @@ litellm.cache = Cache(type="disk")
 
 # Make completion calls
 response1 = completion(
-    model="gpt-3.5-turbo", 
+    model="gpt-4o", 
     messages=[{"role": "user", "content": "Tell me a joke."}],
     caching=True
 )
 response2 = completion(
-    model="gpt-3.5-turbo", 
+    model="gpt-4o", 
     messages=[{"role": "user", "content": "Tell me a joke."}],
     caching=True
 )
@@ -416,7 +416,7 @@ Example usage `no-cache` - When `True`, Will not return a cached response
 
 ```python
 response = litellm.completion(
-        model="gpt-3.5-turbo",
+        model="gpt-4o",
         messages=[
             {
                 "role": "user",
@@ -435,7 +435,7 @@ Example usage `no-store` - When `True`, Will not cache the response.
 
 ```python
 response = litellm.completion(
-        model="gpt-3.5-turbo",
+        model="gpt-4o",
         messages=[
             {
                 "role": "user",
@@ -453,7 +453,7 @@ Example usage `ttl` - cache the response for 10 seconds
 
 ```python
 response = litellm.completion(
-        model="gpt-3.5-turbo",
+        model="gpt-4o",
         messages=[
             {
                 "role": "user",
@@ -471,7 +471,7 @@ Example usage `s-maxage` - Will only accept cached responses for 60 seconds
 
 ```python
 response = litellm.completion(
-        model="gpt-3.5-turbo",
+        model="gpt-4o",
         messages=[
             {
                 "role": "user",
diff --git a/docs/my-website/docs/caching/caching_api.md b/docs/my-website/docs/caching/caching_api.md
index 15ae7be0fb7..e425aa8a5eb 100644
--- a/docs/my-website/docs/caching/caching_api.md
+++ b/docs/my-website/docs/caching/caching_api.md
@@ -11,13 +11,13 @@ litellm.cache = Cache(type="hosted") # init cache to use api.litellm.ai
 
 # Make completion calls
 response1 = completion(
-    model="gpt-3.5-turbo", 
+    model="gpt-4o", 
     messages=[{"role": "user", "content": "Tell me a joke."}]
     caching=True
 )
 
 response2 = completion(
-    model="gpt-3.5-turbo", 
+    model="gpt-4o", 
     messages=[{"role": "user", "content": "Tell me a joke."}],
     caching=True
 )
@@ -59,7 +59,7 @@ litellm.cache = Cache(type="hosted")
 
 # Make completion calls
 response1 = completion(
-    model="gpt-3.5-turbo", 
+    model="gpt-4o", 
     messages=[{"role": "user", "content": "Tell me a joke."}], 
     stream=True,
     caching=True)
@@ -69,7 +69,7 @@ for chunk in response1:
 time.sleep(1) # cache is updated asynchronously
 
 response2 = completion(
-    model="gpt-3.5-turbo", 
+    model="gpt-4o", 
     messages=[{"role": "user", "content": "Tell me a joke."}], 
     stream=True,
     caching=True)
diff --git a/docs/my-website/docs/caching/local_caching.md b/docs/my-website/docs/caching/local_caching.md
index 8b81438df9d..784e06fe1a0 100644
--- a/docs/my-website/docs/caching/local_caching.md
+++ b/docs/my-website/docs/caching/local_caching.md
@@ -18,12 +18,12 @@ litellm.cache = Cache()
 
 # Make completion calls
 response1 = completion(
-    model="gpt-3.5-turbo", 
+    model="gpt-4o", 
     messages=[{"role": "user", "content": "Tell me a joke."}]
     caching=True
 )
 response2 = completion(
-    model="gpt-3.5-turbo", 
+    model="gpt-4o", 
     messages=[{"role": "user", "content": "Tell me a joke."}],
     caching=True
 )
@@ -55,14 +55,14 @@ litellm.cache = Cache()
 
 # Make completion calls
 response1 = completion(
-    model="gpt-3.5-turbo", 
+    model="gpt-4o", 
     messages=[{"role": "user", "content": "Tell me a joke."}], 
     stream=True,
     caching=True)
 for chunk in response1:
     print(chunk)
 response2 = completion(
-    model="gpt-3.5-turbo", 
+    model="gpt-4o", 
     messages=[{"role": "user", "content": "Tell me a joke."}], 
     stream=True,
     caching=True)
diff --git a/docs/my-website/docs/contribute_integration/custom_webhook_api.md b/docs/my-website/docs/contribute_integration/custom_webhook_api.md
index 158937d2a43..0e365cb439f 100644
--- a/docs/my-website/docs/contribute_integration/custom_webhook_api.md
+++ b/docs/my-website/docs/contribute_integration/custom_webhook_api.md
@@ -50,9 +50,9 @@ a. Setup config.yaml
 
 ```yaml
 model_list:
-  - model_name: gpt-3.5-turbo
+  - model_name: gpt-4o
     litellm_params:
-      model: openai/gpt-3.5-turbo
+      model: openai/gpt-4o
       api_key: os.environ/OPENAI_API_KEY
   - model_name: anthropic-claude
     litellm_params:
@@ -80,7 +80,7 @@ curl -L -X POST 'http://0.0.0.0:4000/chat/completions' \
 -H 'Content-Type: application/json' \
 -H 'Authorization: Bearer sk-1234' \
 -d '{
-  "model": "gpt-3.5-turbo",
+  "model": "gpt-4o",
   "messages": [
     {
       "role": "system",
diff --git a/docs/my-website/docs/debugging/local_debugging.md b/docs/my-website/docs/debugging/local_debugging.md
index 8a56d6c34a0..1f436290e16 100644
--- a/docs/my-website/docs/debugging/local_debugging.md
+++ b/docs/my-website/docs/debugging/local_debugging.md
@@ -17,7 +17,7 @@ os.environ["COHERE_API_KEY"] = "cohere key"
 messages = [{ "content": "Hello, how are you?","role": "user"}]
 
 # openai call
-response = completion(model="gpt-3.5-turbo", messages=messages)
+response = completion(model="gpt-4o", messages=messages)
 
 # cohere call
 response = completion("command-nightly", messages)
@@ -59,7 +59,7 @@ os.environ["COHERE_API_KEY"] = "cohere key"
 messages = [{ "content": "Hello, how are you?","role": "user"}]
 
 # openai call
-response = completion(model="gpt-3.5-turbo", messages=messages, logger_fn=my_custom_logging_fn)
+response = completion(model="gpt-4o", messages=messages, logger_fn=my_custom_logging_fn)
 
 # cohere call
 response = completion("command-nightly", messages, logger_fn=my_custom_logging_fn)
diff --git a/docs/my-website/docs/guides/finetuned_models.md b/docs/my-website/docs/guides/finetuned_models.md
index cb0d49b4433..ecc919062a2 100644
--- a/docs/my-website/docs/guides/finetuned_models.md
+++ b/docs/my-website/docs/guides/finetuned_models.md
@@ -11,9 +11,9 @@ import TabItem from '@theme/TabItem';
 |---------------------------|-----------------------------------------------------------------|
 | fine tuned `gpt-4-0613`    | `response = completion(model="ft:gpt-4-0613", messages=messages)`     |
 | fine tuned `gpt-4o-2024-05-13` | `response = completion(model="ft:gpt-4o-2024-05-13", messages=messages)` |
-| fine tuned `gpt-3.5-turbo-0125` | `response = completion(model="ft:gpt-3.5-turbo-0125", messages=messages)` |
-| fine tuned `gpt-3.5-turbo-1106` | `response = completion(model="ft:gpt-3.5-turbo-1106", messages=messages)` |
-| fine tuned `gpt-3.5-turbo-0613` | `response = completion(model="ft:gpt-3.5-turbo-0613", messages=messages)` |
+| fine tuned `gpt-4o-0125` | `response = completion(model="ft:gpt-4o-0125", messages=messages)` |
+| fine tuned `gpt-4o-1106` | `response = completion(model="ft:gpt-4o-1106", messages=messages)` |
+| fine tuned `gpt-4o-0613` | `response = completion(model="ft:gpt-4o-0613", messages=messages)` |
 
 
 ## Vertex AI
diff --git a/docs/my-website/docs/integrations/letta.md b/docs/my-website/docs/integrations/letta.md
index 9711999df5e..f8395bffccb 100644
--- a/docs/my-website/docs/integrations/letta.md
+++ b/docs/my-website/docs/integrations/letta.md
@@ -41,7 +41,7 @@ model_list:
       model: anthropic/claude-3-sonnet-20240229
       api_key: os.environ/ANTHROPIC_API_KEY
 
-  - model_name: gpt-3.5-turbo
+  - model_name: gpt-4o
     litellm_params:
       model: azure/gpt-35-turbo
       api_key: os.environ/AZURE_API_KEY
@@ -726,7 +726,7 @@ agents['reviewer'] = client.create_agent(
     name="reviewer",
     system="You are an editor. Review and improve content quality.",
     llm_config=LLMConfig(
-        model="openai/gpt-3.5-turbo",
+        model="openai/gpt-4o",
         model_endpoint_type="openai"
     )
 )
@@ -795,7 +795,7 @@ print(article)
 1. **Model Selection**: Choose models based on task requirements:
    - Use `openai/gpt-4` for complex reasoning
    - Use `anthropic/claude-3-sonnet-20240229` for analysis
-   - Use `openai/gpt-3.5-turbo` for cost-effective simple tasks
+   - Use `openai/gpt-4o` for cost-effective simple tasks
 
 2. **Error Handling**: Implement robust error handling with retries:
    ```python
@@ -813,7 +813,7 @@ print(article)
        except Exception as e:
            print(f"LLM call failed: {e}")
            # Implement fallback logic
-           return completion(model="openai/gpt-3.5-turbo", **kwargs)
+           return completion(model="openai/gpt-4o", **kwargs)
    ```
 
 3. **Cost Management**:
@@ -882,7 +882,7 @@ print("Anthropic Key:", os.environ.get("ANTHROPIC_API_KEY", "Not set"))
 # Test direct LiteLLM call
 try:
     response = litellm.completion(
-        model="openai/gpt-3.5-turbo",
+        model="openai/gpt-4o",
         messages=[{"role": "user", "content": "Hello"}]
     )
     print("LiteLLM working:", response.choices[0].message.content)
diff --git a/docs/my-website/docs/langchain/langchain.md b/docs/my-website/docs/langchain/langchain.md
index c67375ce1be..5ce18b47adc 100644
--- a/docs/my-website/docs/langchain/langchain.md
+++ b/docs/my-website/docs/langchain/langchain.md
@@ -24,7 +24,7 @@ from langchain_core.prompts import (
 from langchain_core.messages import AIMessage, HumanMessage, SystemMessage
 
 os.environ['OPENAI_API_KEY'] = ""
-chat = ChatLiteLLM(model="gpt-3.5-turbo")
+chat = ChatLiteLLM(model="gpt-4o")
 messages = [
     HumanMessage(
         content="what model are you"
@@ -455,7 +455,7 @@ tag_routing:
   - tags: ["premium", "high-priority"]
     models: ["gpt-4o", "claude-3-opus"]
   - tags: ["standard"]
-    models: ["gpt-3.5-turbo", "claude-3-haiku"]
+    models: ["gpt-4o", "claude-3-haiku"]
 ```
 
 ### Monitoring and Analytics
diff --git a/docs/my-website/docs/providers/azure/azure.md b/docs/my-website/docs/providers/azure/azure.md
index 682f263c108..b67307df9b7 100644
--- a/docs/my-website/docs/providers/azure/azure.md
+++ b/docs/my-website/docs/providers/azure/azure.md
@@ -100,7 +100,7 @@ export AZURE_API_KEY=""
 
 ```yaml
 model_list:
-  - model_name: gpt-3.5-turbo
+  - model_name: gpt-4o
     litellm_params:
       model: azure/chatgpt-v-2
       api_base: https://openai-gpt-4-test-v-1.openai.azure.com/
@@ -117,7 +117,7 @@ model_list:
 curl --location 'http://0.0.0.0:4000/chat/completions' \
 --header 'Content-Type: application/json' \
 --data ' {
-      "model": "gpt-3.5-turbo",
+      "model": "gpt-4o",
       "messages": [
         {
           "role": "user",
@@ -137,7 +137,7 @@ client = openai.OpenAI(
     base_url="http://0.0.0.0:4000"
 )
 
-response = client.chat.completions.create(model="gpt-3.5-turbo", messages = [
+response = client.chat.completions.create(model="gpt-4o", messages = [
     {
         "role": "user",
         "content": "this is a test request, write a short poem"
@@ -161,7 +161,7 @@ from langchain.schema import HumanMessage, SystemMessage
 
 chat = ChatOpenAI(
     openai_api_base="http://0.0.0.0:4000", # set openai_api_base to the LiteLLM Proxy
-    model = "gpt-3.5-turbo",
+    model = "gpt-4o",
     temperature=0.1
 )
 
@@ -224,11 +224,11 @@ model_list:
 | gpt-4-32k-0613            | `completion('azure/<your deployment name>', messages)`         | 
 | gpt-4-1106-preview            | `completion('azure/<your deployment name>', messages)`         | 
 | gpt-4-0125-preview            | `completion('azure/<your deployment name>', messages)`         | 
-| gpt-3.5-turbo    | `completion('azure/<your deployment name>', messages)` |
-| gpt-3.5-turbo-0301    | `completion('azure/<your deployment name>', messages)` |
-| gpt-3.5-turbo-0613    | `completion('azure/<your deployment name>', messages)` |
-| gpt-3.5-turbo-16k    | `completion('azure/<your deployment name>', messages)` |
-| gpt-3.5-turbo-16k-0613    | `completion('azure/<your deployment name>', messages)`
+| gpt-4o    | `completion('azure/<your deployment name>', messages)` |
+| gpt-4o-0301    | `completion('azure/<your deployment name>', messages)` |
+| gpt-4o-0613    | `completion('azure/<your deployment name>', messages)` |
+| gpt-4o-16k    | `completion('azure/<your deployment name>', messages)` |
+| gpt-4o-16k-0613    | `completion('azure/<your deployment name>', messages)`
 
 ## Azure OpenAI Vision Models 
 | Model Name            | Function Call                                                   |
@@ -524,8 +524,8 @@ Use `model="azure_text/<your-deployment>"`
 
 | Model Name          | Function Call                                      |
 |---------------------|----------------------------------------------------|
-| gpt-3.5-turbo-instruct | `response = completion(model="azure_text/<your deployment name>", messages=messages)` |
-| gpt-3.5-turbo-instruct-0914 | `response = completion(model="azure_text/<your deployment name>", messages=messages)` |
+| gpt-4o-instruct | `response = completion(model="azure_text/<your deployment name>", messages=messages)` |
+| gpt-4o-instruct-0914 | `response = completion(model="azure_text/<your deployment name>", messages=messages)` |
 
 
 ```python
@@ -604,7 +604,7 @@ response = litellm.completion(
 
 ```yaml
 model_list:
-  - model_name: gpt-3.5-turbo
+  - model_name: gpt-4o
     litellm_params:
       model: azure/chatgpt-v-2
       api_base: https://openai-gpt-4-test-v-1.openai.azure.com/
@@ -620,7 +620,7 @@ model_list:
 Here is an example of setting up `tenant_id`, `client_id`, `client_secret` in your litellm proxy `config.yaml`
 ```yaml
 model_list:
-  - model_name: gpt-3.5-turbo
+  - model_name: gpt-4o
     litellm_params:
       model: azure/chatgpt-v-2
       api_base: https://openai-gpt-4-test-v-1.openai.azure.com/
@@ -637,7 +637,7 @@ Test it
 curl --location 'http://0.0.0.0:4000/chat/completions' \
 --header 'Content-Type: application/json' \
 --data ' {
-      "model": "gpt-3.5-turbo",
+      "model": "gpt-4o",
       "messages": [
         {
           "role": "user",
@@ -657,7 +657,7 @@ Example video of using `tenant_id`, `client_id`, `client_secret` with LiteLLM Pr
 Here is an example of setting up `client_id`, `azure_username`, `azure_password` in your litellm proxy `config.yaml`
 ```yaml
 model_list:
-  - model_name: gpt-3.5-turbo
+  - model_name: gpt-4o
     litellm_params:
       model: azure/chatgpt-v-2
       api_base: https://openai-gpt-4-test-v-1.openai.azure.com/
@@ -674,7 +674,7 @@ Test it
 curl --location 'http://0.0.0.0:4000/chat/completions' \
 --header 'Content-Type: application/json' \
 --data ' {
-      "model": "gpt-3.5-turbo",
+      "model": "gpt-4o",
       "messages": [
         {
           "role": "user",
@@ -746,7 +746,7 @@ export AZURE_CLIENT_SECRET=""
 
 ```yaml
 model_list:
-  - model_name: gpt-3.5-turbo
+  - model_name: gpt-4o
     litellm_params:
       model: azure/your-deployment-name
       api_base: https://openai-gpt-4-test-v-1.openai.azure.com/
@@ -761,7 +761,7 @@ Perfect for AKS clusters, Azure VMs, or other managed environments where Azure a
 
 ```yaml
 model_list:
-  - model_name: gpt-3.5-turbo
+  - model_name: gpt-4o
     litellm_params:
       model: azure/your-deployment-name
       api_base: https://openai-gpt-4-test-v-1.openai.azure.com/
@@ -776,7 +776,7 @@ If you're authenticated via `az login`, no additional configuration needed:
 
 ```yaml
 model_list:
-  - model_name: gpt-3.5-turbo
+  - model_name: gpt-4o
     litellm_params:
       model: azure/your-deployment-name
       api_base: https://openai-gpt-4-test-v-1.openai.azure.com/
@@ -1150,7 +1150,7 @@ pip install litellm
 from litellm import Router
 
 model_list = [{ # list of model deployments 
-	"model_name": "gpt-3.5-turbo", # openai model name 
+	"model_name": "gpt-4o", # openai model name 
 	"litellm_params": { # params for litellm completion/embedding call 
 		"model": "azure/chatgpt-v-2", 
 		"api_key": os.getenv("AZURE_API_KEY"),
@@ -1160,7 +1160,7 @@ model_list = [{ # list of model deployments
 	"tpm": 240000,
 	"rpm": 1800
 }, {
-    "model_name": "gpt-3.5-turbo", # openai model name 
+    "model_name": "gpt-4o", # openai model name 
 	"litellm_params": { # params for litellm completion/embedding call 
 		"model": "azure/chatgpt-functioncalling", 
 		"api_key": os.getenv("AZURE_API_KEY"),
@@ -1170,9 +1170,9 @@ model_list = [{ # list of model deployments
 	"tpm": 240000,
 	"rpm": 1800
 }, {
-    "model_name": "gpt-3.5-turbo", # openai model name 
+    "model_name": "gpt-4o", # openai model name 
 	"litellm_params": { # params for litellm completion/embedding call 
-		"model": "gpt-3.5-turbo", 
+		"model": "gpt-4o", 
 		"api_key": os.getenv("OPENAI_API_KEY"),
 	},
 	"tpm": 1000000,
@@ -1182,7 +1182,7 @@ model_list = [{ # list of model deployments
 router = Router(model_list=model_list)
 
 # openai.chat.completions.create replacement
-response = router.completion(model="gpt-3.5-turbo", 
+response = router.completion(model="gpt-4o", 
 				messages=[{"role": "user", "content": "Hey, how's it going?"}]
 
 print(response)
diff --git a/docs/my-website/docs/providers/custom_llm_server.md b/docs/my-website/docs/providers/custom_llm_server.md
index 4fcbf8942ce..ac350af7446 100644
--- a/docs/my-website/docs/providers/custom_llm_server.md
+++ b/docs/my-website/docs/providers/custom_llm_server.md
@@ -31,7 +31,7 @@ from litellm import CustomLLM, completion, get_llm_provider
 class MyCustomLLM(CustomLLM):
     def completion(self, *args, **kwargs) -> litellm.ModelResponse:
         return litellm.completion(
-            model="gpt-3.5-turbo",
+            model="gpt-4o",
             messages=[{"role": "user", "content": "Hello world"}],
             mock_response="Hi!",
         )  # type: ignore
@@ -62,14 +62,14 @@ from litellm import CustomLLM, completion, get_llm_provider
 class MyCustomLLM(CustomLLM):
     def completion(self, *args, **kwargs) -> litellm.ModelResponse:
         return litellm.completion(
-            model="gpt-3.5-turbo",
+            model="gpt-4o",
             messages=[{"role": "user", "content": "Hello world"}],
             mock_response="Hi!",
         )  # type: ignore
 
     async def acompletion(self, *args, **kwargs) -> litellm.ModelResponse:
         return litellm.completion(
-            model="gpt-3.5-turbo",
+            model="gpt-4o",
             messages=[{"role": "user", "content": "Hello world"}],
             mock_response="Hi!",
         )  # type: ignore
@@ -135,7 +135,7 @@ Expected Response
         }
     ],
     "created": 1721955063,
-    "model": "gpt-3.5-turbo",
+    "model": "gpt-4o",
     "object": "chat.completion",
     "system_fingerprint": null,
     "usage": {
@@ -356,7 +356,7 @@ from litellm import CustomLLM, completion, get_llm_provider
 class MyCustomLLM(CustomLLM):
     async def acompletion(self, *args, **kwargs) -> litellm.ModelResponse:
         return litellm.completion(
-            model="gpt-3.5-turbo",
+            model="gpt-4o",
             messages=[{"role": "user", "content": "Hello world"}],
             mock_response="Hi!",
         )  # type: ignore
@@ -420,7 +420,7 @@ Expected Response
     "id": "chatcmpl-Bm4qEp4h4vCe7Zi4Gud1MAxTWgibO",
     "type": "message",
     "role": "assistant",
-    "model": "gpt-3.5-turbo-0125",
+    "model": "gpt-4o-0125",
     "stop_sequence": null,
     "usage": {
         "input_tokens": 18,
@@ -455,7 +455,7 @@ class MyCustomLLM(CustomLLM):
     def completion(self, *args, **kwargs) -> litellm.ModelResponse:
         assert kwargs["optional_params"] == {"my_custom_param": "my-custom-param"} # 👈 CHECK HERE
         return litellm.completion(
-            model="gpt-3.5-turbo",
+            model="gpt-4o",
             messages=[{"role": "user", "content": "Hello world"}],
             mock_response="Hi!",
         )  # type: ignore
diff --git a/docs/my-website/docs/providers/openrouter.md b/docs/my-website/docs/providers/openrouter.md
index 4c79c41cfd5..ee7189f0540 100644
--- a/docs/my-website/docs/providers/openrouter.md
+++ b/docs/my-website/docs/providers/openrouter.md
@@ -51,8 +51,8 @@ This approach provides better flexibility for managing configurations across dif
 
 | Model Name                | Function Call                                       |
 |---------------------------|-----------------------------------------------------|
-| openrouter/openai/gpt-3.5-turbo | `completion('openrouter/openai/gpt-3.5-turbo', messages)` | `os.environ['OR_SITE_URL']`,`os.environ['OR_APP_NAME']`,`os.environ['OPENROUTER_API_KEY']` |
-| openrouter/openai/gpt-3.5-turbo-16k | `completion('openrouter/openai/gpt-3.5-turbo-16k', messages)` | `os.environ['OR_SITE_URL']`,`os.environ['OR_APP_NAME']`,`os.environ['OPENROUTER_API_KEY']` |
+| openrouter/openai/gpt-4o | `completion('openrouter/openai/gpt-4o', messages)` | `os.environ['OR_SITE_URL']`,`os.environ['OR_APP_NAME']`,`os.environ['OPENROUTER_API_KEY']` |
+| openrouter/openai/gpt-4o-16k | `completion('openrouter/openai/gpt-4o-16k', messages)` | `os.environ['OR_SITE_URL']`,`os.environ['OR_APP_NAME']`,`os.environ['OPENROUTER_API_KEY']` |
 | openrouter/openai/gpt-4    | `completion('openrouter/openai/gpt-4', messages)`       | `os.environ['OR_SITE_URL']`,`os.environ['OR_APP_NAME']`,`os.environ['OPENROUTER_API_KEY']` |
 | openrouter/openai/gpt-4-32k | `completion('openrouter/openai/gpt-4-32k', messages)` | `os.environ['OR_SITE_URL']`,`os.environ['OR_APP_NAME']`,`os.environ['OPENROUTER_API_KEY']` |
 | openrouter/anthropic/claude-2 | `completion('openrouter/anthropic/claude-2', messages)` | `os.environ['OR_SITE_URL']`,`os.environ['OR_APP_NAME']`,`os.environ['OPENROUTER_API_KEY']` |
diff --git a/docs/my-website/docs/providers/text_completion_openai.md b/docs/my-website/docs/providers/text_completion_openai.md
index d790c01fe0b..ab150f3908f 100644
--- a/docs/my-website/docs/providers/text_completion_openai.md
+++ b/docs/my-website/docs/providers/text_completion_openai.md
@@ -21,7 +21,7 @@ os.environ["OPENAI_API_KEY"] = "your-api-key"
 
 # openai call
 response = completion(
-    model = "gpt-3.5-turbo-instruct", 
+    model = "gpt-4o-instruct", 
     messages=[{ "content": "Hello, how are you?","role": "user"}]
 )
 ```
@@ -43,20 +43,20 @@ export OPENAI_API_KEY=""
 
 ```yaml
 model_list:
-  - model_name: gpt-3.5-turbo
+  - model_name: gpt-4o
     litellm_params:
-      model: openai/gpt-3.5-turbo                          # The `openai/` prefix will call openai.chat.completions.create
+      model: openai/gpt-4o                          # The `openai/` prefix will call openai.chat.completions.create
       api_key: os.environ/OPENAI_API_KEY
-  - model_name: gpt-3.5-turbo-instruct
+  - model_name: gpt-4o-instruct
     litellm_params:
-      model: text-completion-openai/gpt-3.5-turbo-instruct # The `text-completion-openai/` prefix will call openai.completions.create
+      model: text-completion-openai/gpt-4o-instruct # The `text-completion-openai/` prefix will call openai.completions.create
       api_key: os.environ/OPENAI_API_KEY
 ```
 </TabItem>
 <TabItem value="config-*" label="config.yaml - proxy all OpenAI models">
 
 Use this to add all openai models with one API Key. **WARNING: This will not do any load balancing**
-This means requests to `gpt-4`, `gpt-3.5-turbo` , `gpt-4-turbo-preview` will all go through this route 
+This means requests to `gpt-4`, `gpt-4o` , `gpt-4-turbo-preview` will all go through this route 
 
 ```yaml
 model_list:
@@ -69,7 +69,7 @@ model_list:
 <TabItem value="cli" label="CLI">
 
 ```bash
-$ litellm --model gpt-3.5-turbo-instruct
+$ litellm --model gpt-4o-instruct
 
 # Server running on http://0.0.0.0:4000
 ```
@@ -87,7 +87,7 @@ $ litellm --model gpt-3.5-turbo-instruct
 curl --location 'http://0.0.0.0:4000/chat/completions' \
 --header 'Content-Type: application/json' \
 --data ' {
-      "model": "gpt-3.5-turbo-instruct",
+      "model": "gpt-4o-instruct",
       "messages": [
         {
           "role": "user",
@@ -108,7 +108,7 @@ client = openai.OpenAI(
 )
 
 # request sent to model set on litellm proxy, `litellm --model`
-response = client.chat.completions.create(model="gpt-3.5-turbo-instruct", messages = [
+response = client.chat.completions.create(model="gpt-4o-instruct", messages = [
     {
         "role": "user",
         "content": "this is a test request, write a short poem"
@@ -132,7 +132,7 @@ from langchain.schema import HumanMessage, SystemMessage
 
 chat = ChatOpenAI(
     openai_api_base="http://0.0.0.0:4000", # set openai_api_base to the LiteLLM Proxy
-    model = "gpt-3.5-turbo-instruct",
+    model = "gpt-4o-instruct",
     temperature=0.1
 )
 
@@ -156,8 +156,8 @@ print(response)
 
 | Model Name          | Function Call                                      |
 |---------------------|----------------------------------------------------|
-| gpt-3.5-turbo-instruct | `response = completion(model="gpt-3.5-turbo-instruct", messages=messages)` |
-| gpt-3.5-turbo-instruct-0914 | `response = completion(model="gpt-3.5-turbo-instruct-0914", messages=messages)` |
+| gpt-4o-instruct | `response = completion(model="gpt-4o-instruct", messages=messages)` |
+| gpt-4o-instruct-0914 | `response = completion(model="gpt-4o-instruct-0914", messages=messages)` |
 | text-davinci-003    | `response = completion(model="text-davinci-003", messages=messages)` |
 | ada-001             | `response = completion(model="ada-001", messages=messages)` |
 | curie-001           | `response = completion(model="curie-001", messages=messages)` |