diff --git a/docs/my-website/docs/proxy/caching.md b/docs/my-website/docs/proxy/caching.md
index 3357dcb28b2..74512e6fd60 100644
--- a/docs/my-website/docs/proxy/caching.md
+++ b/docs/my-website/docs/proxy/caching.md
@@ -34,9 +34,9 @@ Caching can be enabled by adding the `cache` key in the `config.yaml`
 
 ```yaml
 model_list:
-  - model_name: gpt-3.5-turbo
+  - model_name: gpt-4o
     litellm_params:
-      model: gpt-3.5-turbo
+      model: gpt-4o
   - model_name: text-embedding-ada-002
     litellm_params:
       model: text-embedding-ada-002
@@ -382,9 +382,9 @@ one**
 
 ```yaml
 model_list:
-  - model_name: gpt-3.5-turbo
+  - model_name: gpt-4o
     litellm_params:
-      model: gpt-3.5-turbo
+      model: gpt-4o
   - model_name: text-embedding-ada-002
     litellm_params:
       model: text-embedding-ada-002
@@ -415,9 +415,9 @@ $ litellm --config /path/to/config.yaml
 
 ```yaml
 model_list:
-  - model_name: gpt-3.5-turbo
+  - model_name: gpt-4o
     litellm_params:
-      model: gpt-3.5-turbo
+      model: gpt-4o
   - model_name: text-embedding-ada-002
     litellm_params:
       model: text-embedding-ada-002
@@ -457,9 +457,9 @@ Caching can be enabled by adding the `cache` key in the `config.yaml`
 
 ```yaml
 model_list:
-  - model_name: gpt-3.5-turbo
+  - model_name: gpt-4o
     litellm_params:
-      model: gpt-3.5-turbo
+      model: gpt-4o
   - model_name: azure-embedding-model
     litellm_params:
       model: azure/azure-embedding-model
@@ -558,7 +558,7 @@ Send the same request twice:
 curl http://0.0.0.0:4000/v1/chat/completions \
   -H "Content-Type: application/json" \
   -d '{
-     "model": "gpt-3.5-turbo",
+     "model": "gpt-4o",
      "messages": [{"role": "user", "content": "write a poem about litellm!"}],
      "temperature": 0.7
    }'
@@ -566,7 +566,7 @@ curl http://0.0.0.0:4000/v1/chat/completions \
 curl http://0.0.0.0:4000/v1/chat/completions \
   -H "Content-Type: application/json" \
   -d '{
-     "model": "gpt-3.5-turbo",
+     "model": "gpt-4o",
      "messages": [{"role": "user", "content": "write a poem about litellm!"}],
      "temperature": 0.7
    }'
@@ -625,7 +625,7 @@ client = OpenAI(
 
 chat_completion = client.chat.completions.create(
     messages=[{"role": "user", "content": "Hello"}],
-    model="gpt-3.5-turbo",
+    model="gpt-4o",
     extra_body={
         "cache": {
             "ttl": 300  # Cache response for 5 minutes
@@ -643,7 +643,7 @@ curl http://localhost:4000/v1/chat/completions \
   -H "Content-Type: application/json" \
   -H "Authorization: Bearer sk-1234" \
   -d '{
-    "model": "gpt-3.5-turbo",
+    "model": "gpt-4o",
     "cache": {"ttl": 300},
     "messages": [
       {"role": "user", "content": "Hello"}
@@ -671,7 +671,7 @@ client = OpenAI(
 
 chat_completion = client.chat.completions.create(
     messages=[{"role": "user", "content": "Hello"}],
-    model="gpt-3.5-turbo",
+    model="gpt-4o",
     extra_body={
         "cache": {
             "s-maxage": 600  # Only use cache if less than 10 minutes old
@@ -689,7 +689,7 @@ curl http://localhost:4000/v1/chat/completions \
   -H "Content-Type: application/json" \
   -H "Authorization: Bearer sk-1234" \
   -d '{
-    "model": "gpt-3.5-turbo",
+    "model": "gpt-4o",
     "cache": {"s-maxage": 600},
     "messages": [
       {"role": "user", "content": "Hello"}
@@ -717,7 +717,7 @@ client = OpenAI(
 
 chat_completion = client.chat.completions.create(
     messages=[{"role": "user", "content": "Hello"}],
-    model="gpt-3.5-turbo",
+    model="gpt-4o",
     extra_body={
         "cache": {
             "no-cache": True  # Skip cache check, get fresh response
@@ -735,7 +735,7 @@ curl http://localhost:4000/v1/chat/completions \
   -H "Content-Type: application/json" \
   -H "Authorization: Bearer sk-1234" \
   -d '{
-    "model": "gpt-3.5-turbo",
+    "model": "gpt-4o",
     "cache": {"no-cache": true},
     "messages": [
       {"role": "user", "content": "Hello"}
@@ -763,7 +763,7 @@ client = OpenAI(
 
 chat_completion = client.chat.completions.create(
     messages=[{"role": "user", "content": "Hello"}],
-    model="gpt-3.5-turbo",
+    model="gpt-4o",
     extra_body={
         "cache": {
             "no-store": True  # Don't cache this response
@@ -781,7 +781,7 @@ curl http://localhost:4000/v1/chat/completions \
   -H "Content-Type: application/json" \
   -H "Authorization: Bearer sk-1234" \
   -d '{
-    "model": "gpt-3.5-turbo",
+    "model": "gpt-4o",
     "cache": {"no-store": true},
     "messages": [
       {"role": "user", "content": "Hello"}
@@ -809,7 +809,7 @@ client = OpenAI(
 
 chat_completion = client.chat.completions.create(
     messages=[{"role": "user", "content": "Hello"}],
-    model="gpt-3.5-turbo",
+    model="gpt-4o",
     extra_body={
         "cache": {
             "namespace": "my-custom-namespace"  # Store in custom namespace
@@ -827,7 +827,7 @@ curl http://localhost:4000/v1/chat/completions \
   -H "Content-Type: application/json" \
   -H "Authorization: Bearer sk-1234" \
   -d '{
-    "model": "gpt-3.5-turbo",
+    "model": "gpt-4o",
     "cache": {"namespace": "my-custom-namespace"},
     "messages": [
       {"role": "user", "content": "Hello"}
@@ -908,9 +908,9 @@ litellm_settings:
 
 ```yaml
 model_list:
-  - model_name: gpt-3.5-turbo
+  - model_name: gpt-4o
     litellm_params:
-      model: gpt-3.5-turbo
+      model: gpt-4o
   - model_name: text-embedding-ada-002
     litellm_params:
       model: text-embedding-ada-002
@@ -956,7 +956,7 @@ curl -i --location 'http://0.0.0.0:4000/chat/completions' \
     --header 'Authorization: Bearer sk-1234' \
     --header 'Content-Type: application/json' \
     --data '{
-    "model": "gpt-3.5-turbo",
+    "model": "gpt-4o",
     "user": "ishan",
     "messages": [
         {
@@ -1029,7 +1029,7 @@ chat_completion = client.chat.completions.create(
             "content": "Say this is a test",
         }
     ],
-    model="gpt-3.5-turbo",
+    model="gpt-4o",
     extra_body = {        # OpenAI python accepts extra args in extra_body
         "cache": {"use-cache": True}
     }
@@ -1045,7 +1045,7 @@ curl http://localhost:4000/v1/chat/completions \
   -H "Content-Type: application/json" \
   -H "Authorization: Bearer sk-1234" \
   -d '{
-    "model": "gpt-3.5-turbo",
+    "model": "gpt-4o",
     "cache": {"use-cache": True}
     "messages": [
       {"role": "user", "content": "Say this is a test"}
diff --git a/docs/my-website/docs/proxy/call_hooks.md b/docs/my-website/docs/proxy/call_hooks.md
index 5935a29c50b..850978e00b1 100644
--- a/docs/my-website/docs/proxy/call_hooks.md
+++ b/docs/my-website/docs/proxy/call_hooks.md
@@ -135,9 +135,9 @@ proxy_handler_instance = MyCustomHandler()
 
 ```yaml
 model_list:
-  - model_name: gpt-3.5-turbo
+  - model_name: gpt-4o
     litellm_params:
-      model: gpt-3.5-turbo
+      model: gpt-4o
 
 litellm_settings:
   callbacks: custom_callbacks.proxy_handler_instance # sets litellm.callbacks = [proxy_handler_instance]
@@ -151,7 +151,7 @@ $ litellm /path/to/config.yaml
 ```shell
 curl --location 'http://0.0.0.0:4000/chat/completions' \
     --data ' {
-    "model": "gpt-3.5-turbo",
+    "model": "gpt-4o",
     "messages": [
         {
         "role": "user",
@@ -231,9 +231,9 @@ proxy_handler_instance = MyCustomHandler()
 
 ```yaml
 model_list:
-  - model_name: gpt-3.5-turbo
+  - model_name: gpt-4o
     litellm_params:
-      model: gpt-3.5-turbo
+      model: gpt-4o
 
 litellm_settings:
   callbacks: custom_callbacks.proxy_handler_instance # sets litellm.callbacks = [proxy_handler_instance]
@@ -247,7 +247,7 @@ $ litellm /path/to/config.yaml
 ```shell
 curl --location 'http://0.0.0.0:4000/chat/completions' \
     --data ' {
-    "model": "gpt-3.5-turbo",
+    "model": "gpt-4o",
     "messages": [
         {
         "role": "user",
@@ -318,9 +318,9 @@ proxy_handler_instance = MyCustomHandler()
 
 ```yaml
 model_list:
-  - model_name: gpt-3.5-turbo
+  - model_name: gpt-4o
     litellm_params:
-      model: gpt-3.5-turbo
+      model: gpt-4o
 
 litellm_settings:
   callbacks: custom_callbacks.proxy_handler_instance # sets litellm.callbacks = [proxy_handler_instance]
@@ -335,7 +335,7 @@ $ litellm /path/to/config.yaml
 ```shell
 curl --location 'http://0.0.0.0:4000/chat/completions' \
     --data ' {
-    "model": "gpt-3.5-turbo",
+    "model": "gpt-4o",
     "messages": [
         {
         "role": "user",
diff --git a/docs/my-website/docs/proxy/clientside_auth.md b/docs/my-website/docs/proxy/clientside_auth.md
index c696737adc0..8b258f3c967 100644
--- a/docs/my-website/docs/proxy/clientside_auth.md
+++ b/docs/my-website/docs/proxy/clientside_auth.md
@@ -41,7 +41,7 @@ user_config = {
         {
             'model_name': 'user-openai-instance',
             'litellm_params': {
-                'model': 'gpt-3.5-turbo',
+                'model': 'gpt-4o',
                 'api_key': os.getenv('OPENAI_API_KEY'),
                 'timeout': 10,
             },
@@ -109,7 +109,7 @@ const userConfig = {
         {
             model_name: 'user-openai-instance',
             litellm_params: {
-                model: 'gpt-3.5-turbo',
+                model: 'gpt-4o',
                 api_key: process.env.OPENAI_API_KEY,
                 timeout: 10,
             },
@@ -140,7 +140,7 @@ const openai = new OpenAI({
 async function main() {
   const chatCompletion = await openai.chat.completions.create({
     messages: [{ role: 'user', content: 'Say this is a test' }],
-    model: 'gpt-3.5-turbo',
+    model: 'gpt-4o',
     user_config: userConfig // # 👈 User config
   });
 }
@@ -188,7 +188,7 @@ client = openai.OpenAI(
 )
 
 # request sent to model set on litellm proxy, `litellm --model`
-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"
@@ -213,7 +213,7 @@ client = openai.OpenAI(
 )
 
 # request sent to model set on litellm proxy, `litellm --model`
-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"
@@ -245,7 +245,7 @@ const openai = new OpenAI({
 async function main() {
   const chatCompletion = await openai.chat.completions.create({
     messages: [{ role: 'user', content: 'Say this is a test' }],
-    model: 'gpt-3.5-turbo',
+    model: 'gpt-4o',
     api_key: "my-bad-key" // 👈 User Key
   });
 }
@@ -272,7 +272,7 @@ client = openai.OpenAI(
 
 # request sent to model set on litellm proxy, `litellm --model`
 response = client.chat.completions.create(
-    model="gpt-3.5-turbo",
+    model="gpt-4o",
     messages = [
         {
             "role": "user",
diff --git a/docs/my-website/docs/proxy/config_settings.md b/docs/my-website/docs/proxy/config_settings.md
index d7542fc2c3d..c59575a0d1d 100644
--- a/docs/my-website/docs/proxy/config_settings.md
+++ b/docs/my-website/docs/proxy/config_settings.md
@@ -34,8 +34,8 @@ litellm_settings:
 
   # Fallbacks, reliability
   default_fallbacks: ["claude-opus"] # set default_fallbacks, in case a specific model group is misconfigured / bad.
-  content_policy_fallbacks: [{ "gpt-3.5-turbo-small": ["claude-opus"] }] # fallbacks for ContentPolicyErrors
-  context_window_fallbacks: [{ "gpt-3.5-turbo-small": ["gpt-3.5-turbo-large", "claude-opus"] }] # fallbacks for ContextWindowExceededErrors
+  content_policy_fallbacks: [{ "gpt-4o-small": ["claude-opus"] }] # fallbacks for ContentPolicyErrors
+  context_window_fallbacks: [{ "gpt-4o-small": ["gpt-4o-large", "claude-opus"] }] # fallbacks for ContextWindowExceededErrors
 
   # MCP Aliases - Map aliases to MCP server names for easier tool access
   mcp_aliases: {
@@ -349,7 +349,7 @@ router_settings:
 | model_group_alias | dict | Model group alias mapping. E.g. `{"claude-3-haiku": "claude-3-haiku-20240229"}` |
 | num_retries | int | Number of retries for a request. Defaults to 3. |
 | default_fallbacks | Optional[List[str]] | Fallbacks to try if no model group-specific fallbacks are defined. |
-| caching_groups | Optional[List[tuple]] | List of model groups for caching across model groups. Defaults to None. - e.g. caching_groups=[("openai-gpt-3.5-turbo", "azure-gpt-3.5-turbo")]|
+| caching_groups | Optional[List[tuple]] | List of model groups for caching across model groups. Defaults to None. - e.g. caching_groups=[("openai-gpt-4o", "azure-gpt-4o")]|
 | alerting_config | AlertingConfig | [SDK-only arg] Slack alerting configuration. Defaults to None. [Further Docs](../routing.md#alerting-) |
 | assistants_config | AssistantsConfig | Set on proxy via `assistant_settings`. [Further docs](../assistants.md) |
 | set_verbose | boolean | [DEPRECATED PARAM - see debug docs](./debugging) If true, sets the logging level to verbose. |
diff --git a/docs/my-website/docs/proxy/configs.md b/docs/my-website/docs/proxy/configs.md
index 84a6fac1210..cc054c2beb2 100644
--- a/docs/my-website/docs/proxy/configs.md
+++ b/docs/my-website/docs/proxy/configs.md
@@ -400,9 +400,9 @@ model_list:
         model: gpt-4o
         api_key: <my-openai-key>
         rpm: 200      
-  - model_name: gpt-3.5-turbo-16k
+  - model_name: gpt-4o-16k
     litellm_params:
-        model: gpt-3.5-turbo-16k
+        model: gpt-4o-16k
         api_key: <my-openai-key>
         rpm: 100      
 
@@ -410,7 +410,7 @@ litellm_settings:
   num_retries: 3 # retry call 3 times on each model_name (e.g. zephyr-beta)
   request_timeout: 10 # raise Timeout error if call takes longer than 10s. Sets litellm.request_timeout 
   fallbacks: [{"zephyr-beta": ["gpt-4o"]}] # fallback to gpt-4o if call fails num_retries 
-  context_window_fallbacks: [{"zephyr-beta": ["gpt-3.5-turbo-16k"]}, {"gpt-4o": ["gpt-3.5-turbo-16k"]}] # fallback to gpt-3.5-turbo-16k if context window error
+  context_window_fallbacks: [{"zephyr-beta": ["gpt-4o-16k"]}, {"gpt-4o": ["gpt-4o-16k"]}] # fallback to gpt-4o-16k if context window error
   allowed_fails: 3 # cooldown model if it fails > 1 call in a minute. 
 
 router_settings: # router_settings are optional
@@ -497,9 +497,9 @@ Supported Environments:
 2. For each model set the list of supported environments in `model_info.supported_environments`
 ```yaml
 model_list:
- - model_name: gpt-3.5-turbo-16k
+ - model_name: gpt-4o-16k
    litellm_params:
-     model: openai/gpt-3.5-turbo-16k
+     model: openai/gpt-4o-16k
      api_key: os.environ/OPENAI_API_KEY
    model_info:
      supported_environments: ["development", "production", "staging"]
diff --git a/docs/my-website/docs/proxy/cost_tracking.md b/docs/my-website/docs/proxy/cost_tracking.md
index f28eec287d4..d60af663fa8 100644
--- a/docs/my-website/docs/proxy/cost_tracking.md
+++ b/docs/my-website/docs/proxy/cost_tracking.md
@@ -388,7 +388,7 @@ client = openai.OpenAI(
 
 
 response = client.chat.completions.create(
-    model="gpt-3.5-turbo",
+    model="gpt-4o",
     messages = [
         {
             "role": "user",
@@ -420,7 +420,7 @@ async function runOpenAI() {
 
   try {
     const response = await client.chat.completions.create({
-      model: "gpt-3.5-turbo",
+      model: "gpt-4o",
       messages: [
         {
           role: "user",
@@ -452,7 +452,7 @@ Pass `metadata` as part of the request body
 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",
@@ -477,7 +477,7 @@ from langchain.schema import HumanMessage, SystemMessage
 
 chat = ChatOpenAI(
     openai_api_base="http://0.0.0.0:4000",
-    model = "gpt-3.5-turbo",
+    model = "gpt-4o",
     temperature=0.1,
     extra_body={
         "metadata": {
@@ -574,7 +574,7 @@ curl -X GET 'http://localhost:4000/global/spend/report?start_date=2024-04-01&end
                         "api_key": "898c28.." # the hashed api key
                     },
                     {
-                        "model": "gpt-3.5-turbo",
+                        "model": "gpt-4o",
                         "spend": 0.0000825,
                         "total_tokens": 85,
                         "api_key": "84dc28.." # the hashed api key
@@ -627,22 +627,22 @@ Output from script
 # Date: 2024-05-11T00:00:00+00:00
 # Team: local_test_team
 # Total Spend: 0.003675099999999999
-# Metadata:  [{'model': 'gpt-3.5-turbo', 'spend': 0.003675099999999999, 'api_key': 'b94d5e0bc3a71a573917fe1335dc0c14728c7016337451af9714924ff3a729db', 'total_tokens': 3105}]
+# Metadata:  [{'model': 'gpt-4o', 'spend': 0.003675099999999999, 'api_key': 'b94d5e0bc3a71a573917fe1335dc0c14728c7016337451af9714924ff3a729db', 'total_tokens': 3105}]
 
 # Date: 2024-05-13T00:00:00+00:00
 # Team: Unassigned Team
 # Total Spend: 3.4e-05
-# Metadata:  [{'model': 'gpt-3.5-turbo', 'spend': 3.4e-05, 'api_key': '9569d13c9777dba68096dea49b0b03e0aaf4d2b65d4030eda9e8a2733c3cd6e0', 'total_tokens': 50}]
+# Metadata:  [{'model': 'gpt-4o', 'spend': 3.4e-05, 'api_key': '9569d13c9777dba68096dea49b0b03e0aaf4d2b65d4030eda9e8a2733c3cd6e0', 'total_tokens': 50}]
 
 # Date: 2024-05-13T00:00:00+00:00
 # Team: central
 # Total Spend: 0.000684
-# Metadata:  [{'model': 'gpt-3.5-turbo', 'spend': 0.000684, 'api_key': '0323facdf3af551594017b9ef162434a9b9a8ca1bbd9ccbd9d6ce173b1015605', 'total_tokens': 498}]
+# Metadata:  [{'model': 'gpt-4o', 'spend': 0.000684, 'api_key': '0323facdf3af551594017b9ef162434a9b9a8ca1bbd9ccbd9d6ce173b1015605', 'total_tokens': 498}]
 
 # Date: 2024-05-13T00:00:00+00:00
 # Team: local_test_team
 # Total Spend: 0.0005715000000000001
-# Metadata:  [{'model': 'gpt-3.5-turbo', 'spend': 0.0005715000000000001, 'api_key': 'b94d5e0bc3a71a573917fe1335dc0c14728c7016337451af9714924ff3a729db', 'total_tokens': 423}]
+# Metadata:  [{'model': 'gpt-4o', 'spend': 0.0005715000000000001, 'api_key': 'b94d5e0bc3a71a573917fe1335dc0c14728c7016337451af9714924ff3a729db', 'total_tokens': 423}]
 ```
 
 </TabItem>
@@ -700,7 +700,7 @@ curl -X GET 'http://localhost:4000/global/spend/report?start_date=2024-04-01&end
                         "api_key": "898c28.." # the hashed api key
                     },
                     {
-                        "model": "gpt-3.5-turbo",
+                        "model": "gpt-4o",
                         "spend": 0.0000825,
                         "total_tokens": 85,
                         "api_key": "84dc28.." # the hashed api key
@@ -778,7 +778,7 @@ curl -X GET 'http://localhost:4000/global/spend/report?start_date=2024-04-01&end
     "total_output_tokens": 872.0,
     "model_details": [
       {
-        "model": "gpt-3.5-turbo-instruct",
+        "model": "gpt-4o-instruct",
         "total_cost": 5.85e-05,
         "total_input_tokens": 15,
         "total_output_tokens": 18
@@ -798,7 +798,7 @@ curl -X GET 'http://localhost:4000/global/spend/report?start_date=2024-04-01&end
     "total_output_tokens": 27.0,
     "model_details": [
       {
-        "model": "gpt-3.5-turbo",
+        "model": "gpt-4o",
         "total_cost": 5.2499999999999995e-05,
         "total_input_tokens": 24,
         "total_output_tokens": 27
@@ -931,7 +931,7 @@ client = openai.OpenAI(
 
 # request sent to model set on litellm proxy, `litellm --model`
 response = client.chat.completions.create(
-    model="gpt-3.5-turbo",
+    model="gpt-4o",
     messages = [
         {
             "role": "user",
@@ -961,7 +961,7 @@ client = openai.OpenAI(
 
 # Pass spend logs metadata via headers
 response = client.chat.completions.create(
-    model="gpt-3.5-turbo",
+    model="gpt-4o",
     messages = [
         {
             "role": "user",
@@ -992,7 +992,7 @@ async function runOpenAI() {
 
   try {
     const response = await client.chat.completions.create({
-      model: 'gpt-3.5-turbo',
+      model: 'gpt-4o',
       messages: [
         {
           role: 'user',
@@ -1029,7 +1029,7 @@ async function runOpenAI() {
 
   try {
     const response = await client.chat.completions.create({
-      model: 'gpt-3.5-turbo',
+      model: 'gpt-4o',
       messages: [
         {
           role: 'user',
@@ -1062,7 +1062,7 @@ Pass `metadata` as part of the request body
 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",
@@ -1089,7 +1089,7 @@ curl --location 'http://0.0.0.0:4000/chat/completions' \
     --header 'Authorization: Bearer sk-1234' \
     --header 'x-litellm-spend-logs-metadata: {"user_id": "12345", "project_id": "proj_abc", "request_type": "chat_completion"}' \
     --data '{
-    "model": "gpt-3.5-turbo",
+    "model": "gpt-4o",
     "messages": [
         {
         "role": "user",
@@ -1113,7 +1113,7 @@ from langchain.schema import HumanMessage, SystemMessage
 
 chat = ChatOpenAI(
     openai_api_base="http://0.0.0.0:4000",
-    model = "gpt-3.5-turbo",
+    model = "gpt-4o",
     temperature=0.1,
     extra_body={
         "metadata": {
diff --git a/docs/my-website/docs/proxy/custom_sso.md b/docs/my-website/docs/proxy/custom_sso.md
index 41ecde6e369..25bfa40cc8a 100644
--- a/docs/my-website/docs/proxy/custom_sso.md
+++ b/docs/my-website/docs/proxy/custom_sso.md
@@ -81,7 +81,7 @@ custom_ui_sso_sign_in_handler = MyCustomSSOLoginHandler()
 model_list: 
   - model_name: "openai-model"
     litellm_params: 
-      model: "gpt-3.5-turbo"
+      model: "gpt-4o"
 
 general_settings:
   custom_ui_sso_sign_in_handler: custom_sso_handler.custom_ui_sso_sign_in_handler
@@ -184,7 +184,7 @@ e.g. if they're both in the same dir - `./config.yaml` and `./custom_sso.py`, th
 model_list: 
   - model_name: "openai-model"
     litellm_params: 
-      model: "gpt-3.5-turbo"
+      model: "gpt-4o"
 
 general_settings:
   custom_sso: custom_sso.custom_sso_handler
diff --git a/docs/my-website/docs/proxy/customer_usage.md b/docs/my-website/docs/proxy/customer_usage.md
index 5a6c06fdc81..5d9d46c6828 100644
--- a/docs/my-website/docs/proxy/customer_usage.md
+++ b/docs/my-website/docs/proxy/customer_usage.md
@@ -36,7 +36,7 @@ curl -X POST 'http://0.0.0.0:4000/chat/completions' \
   --header 'Content-Type: application/json' \
   --header 'Authorization: Bearer sk-1234' \
   --data '{
-    "model": "gpt-3.5-turbo",
+    "model": "gpt-4o",
     "user": "customer-123",
     "messages": [
       {
@@ -64,7 +64,7 @@ curl -X POST 'http://0.0.0.0:4000/chat/completions' \
   --header 'Authorization: Bearer sk-1234' \
   --header 'x-litellm-customer-id: customer-123' \
   --data '{
-    "model": "gpt-3.5-turbo",
+    "model": "gpt-4o",
     "messages": [
       {
         "role": "user",
diff --git a/docs/my-website/docs/proxy/debugging.md b/docs/my-website/docs/proxy/debugging.md
index fbcac24a4d6..d9cffbb0cb1 100644
--- a/docs/my-website/docs/proxy/debugging.md
+++ b/docs/my-website/docs/proxy/debugging.md
@@ -48,7 +48,7 @@ POST Request Sent from LiteLLM:
 curl -X POST \
 https://api.openai.com/v1/chat/completions \
 -H 'content-type: application/json' -H 'Authorization: Bearer sk-qnWGUIW9****************************************' \
--d '{"model": "gpt-3.5-turbo", "messages": [{"role": "user", "content": "this is a test request, write a short poem"}]}'
+-d '{"model": "gpt-4o", "messages": [{"role": "user", "content": "this is a test request, write a short poem"}]}'
 ```
 
 ## Debug single request
@@ -81,7 +81,7 @@ https://exampleopenaiendpoint-production.up.railway.app/chat/completions \
 
 
 20:14:06 - LiteLLM:WARNING: litellm_logging.py:1015 - RAW RESPONSE:
-{"id":"chatcmpl-817fc08f0d6c451485d571dab39b26a1","object":"chat.completion","created":1677652288,"model":"gpt-3.5-turbo-0301","system_fingerprint":"fp_44709d6fcb","choices":[{"index":0,"message":{"role":"assistant","content":"\n\nHello there, how may I assist you today?"},"logprobs":null,"finish_reason":"stop"}],"usage":{"prompt_tokens":9,"completion_tokens":12,"total_tokens":21}}
+{"id":"chatcmpl-817fc08f0d6c451485d571dab39b26a1","object":"chat.completion","created":1677652288,"model":"gpt-4o-0301","system_fingerprint":"fp_44709d6fcb","choices":[{"index":0,"message":{"role":"assistant","content":"\n\nHello there, how may I assist you today?"},"logprobs":null,"finish_reason":"stop"}],"usage":{"prompt_tokens":9,"completion_tokens":12,"total_tokens":21}}
 
 
 INFO:     127.0.0.1:56155 - "POST /chat/completions HTTP/1.1" 200 OK
diff --git a/docs/my-website/docs/proxy/rules.md b/docs/my-website/docs/proxy/rules.md
index 60e990d91b4..753547324aa 100644
--- a/docs/my-website/docs/proxy/rules.md
+++ b/docs/my-website/docs/proxy/rules.md
@@ -34,7 +34,7 @@ curl --location 'http://0.0.0.0:4000/v1/chat/completions' \
 --header 'Content-Type: application/json' \
 --header 'Authorization: Bearer sk-1234' \
 --data '{
-  "model": "gpt-3.5-turbo",
+  "model": "gpt-4o",
   "messages": [{"role":"user","content":"What llm are you?"}],
   "temperature": 0.7,
   "max_tokens": 10,