diff --git a/README.md b/README.md
index 53fd56048..603751013 100644
--- a/README.md
+++ b/README.md
@@ -113,7 +113,7 @@ import openai
 
 openai.api_base = "http://0.0.0.0:8000"
 
-print(openai.ChatCompletion.create(model="test", messages=[{"role":"user", "content":"Hey!"}]))
+print(openai.chat.completions.create(model="test", messages=[{"role":"user", "content":"Hey!"}]))
 ```
 
 ## Supported Provider ([Docs](https://docs.litellm.ai/docs/providers))
diff --git a/docs/my-website/docs/providers/azure.md b/docs/my-website/docs/providers/azure.md
index a07b28d70..e9ad7bd58 100644
--- a/docs/my-website/docs/providers/azure.md
+++ b/docs/my-website/docs/providers/azure.md
@@ -109,7 +109,7 @@ model_list = [{ # list of model deployments
 
 router = Router(model_list=model_list)
 
-# openai.ChatCompletion.create replacement
+# openai.chat.completions.create replacement
 response = router.completion(model="gpt-3.5-turbo", 
 				messages=[{"role": "user", "content": "Hey, how's it going?"}]
 
diff --git a/docs/my-website/docs/providers/ollama.md b/docs/my-website/docs/providers/ollama.md
index 88927aba7..f5a1b0d6d 100644
--- a/docs/my-website/docs/providers/ollama.md
+++ b/docs/my-website/docs/providers/ollama.md
@@ -115,7 +115,7 @@ print(openai.api_base)
 
 
 print(f'LiteLLM: response from proxy with streaming')
-response = openai.ChatCompletion.create(
+response = openai.chat.completions.create(
     model="ollama/llama2", 
     messages = [
         {
diff --git a/docs/my-website/docs/simple_proxy.md b/docs/my-website/docs/simple_proxy.md
index 3eda0c6c5..77977cd75 100644
--- a/docs/my-website/docs/simple_proxy.md
+++ b/docs/my-website/docs/simple_proxy.md
@@ -33,7 +33,7 @@ import openai
 
 openai.api_base = "http://0.0.0.0:8000"
 
-print(openai.ChatCompletion.create(model="test", messages=[{"role":"user", "content":"Hey!"}]))
+print(openai.chat.completions.create(model="test", messages=[{"role":"user", "content":"Hey!"}]))
 ```
 
 ### Supported LLMs
@@ -541,7 +541,7 @@ If you're repo let's you set model name, you can call the specific model by just
 import openai 
 openai.api_base = "http://0.0.0.0:8000" 
 
-completion = openai.ChatCompletion.create(model="zephyr-alpha", messages=[{"role": "user", "content": "Hello world"}])
+completion = openai.chat.completions.create(model="zephyr-alpha", messages=[{"role": "user", "content": "Hello world"}])
 print(completion.choices[0].message.content)
 ```
 
@@ -551,7 +551,7 @@ If you're repo only let's you specify api base, then you can add the model name
 import openai 
 openai.api_base = "http://0.0.0.0:8000/openai/deployments/zephyr-alpha/chat/completions" # zephyr-alpha will be used 
 
-completion = openai.ChatCompletion.create(model="gpt-3.5-turbo", messages=[{"role": "user", "content": "Hello world"}])
+completion = openai.chat.completions.create(model="gpt-3.5-turbo", messages=[{"role": "user", "content": "Hello world"}])
 print(completion.choices[0].message.content)
 ```
 
diff --git a/litellm/proxy/README.md b/litellm/proxy/README.md
index 994f921c1..93339b82c 100644
--- a/litellm/proxy/README.md
+++ b/litellm/proxy/README.md
@@ -19,7 +19,7 @@ import openai
 
 openai.api_base = "http://0.0.0.0:8000"
 
-print(openai.ChatCompletion.create(model="test", messages=[{"role":"user", "content":"Hey!"}]))
+print(openai.chat.completions.create(model="test", messages=[{"role":"user", "content":"Hey!"}]))
 ``` 
 
 [**See how to call Huggingface,Bedrock,TogetherAI,Anthropic, etc.**](https://docs.litellm.ai/docs/simple_proxy)
diff --git a/litellm/proxy/proxy_cli.py b/litellm/proxy/proxy_cli.py
index 064436751..bc80b8b98 100644
--- a/litellm/proxy/proxy_cli.py
+++ b/litellm/proxy/proxy_cli.py
@@ -125,11 +125,10 @@ def run_server(host, port, api_base, api_version, model, alias, add_key, headers
         openai.api_base = api_base
         openai.api_key = "temp-key"
         print(openai.api_base)
-
-        response = openai.Completion.create(model="gpt-3.5-turbo", prompt='this is a test request, write a short poem')
+        response = openai.completions.create(model="gpt-3.5-turbo", prompt='this is a test request, write a short poem')
         print(response)
 
-        response = openai.ChatCompletion.create(model="gpt-3.5-turbo", messages = [
+        response = openai.chat.completions.create(model="gpt-3.5-turbo", messages = [
             {
                 "role": "user",
                 "content": "this is a test request, write a short poem"
@@ -138,7 +137,7 @@ def run_server(host, port, api_base, api_version, model, alias, add_key, headers
         click.echo(f'LiteLLM: response from proxy {response}')
 
         click.echo(f'LiteLLM: response from proxy with streaming {response}')
-        response = openai.ChatCompletion.create(model="gpt-3.5-turbo", messages = [
+        response = openai.chat.completions.create(model="gpt-3.5-turbo", messages = [
             {
                 "role": "user",
                 "content": "this is a test request, write a short poem"
diff --git a/litellm_server/tests/test_bedrock.py b/litellm_server/tests/test_bedrock.py
index 7f6bd5613..7825de891 100644
--- a/litellm_server/tests/test_bedrock.py
+++ b/litellm_server/tests/test_bedrock.py
@@ -4,7 +4,7 @@ print("making request")
 openai.api_key = "anything" # this gets passed as a header 
 
 
-response = openai.ChatCompletion.create(
+response = openai.chat.completions.create(
     model = "bedrock/anthropic.claude-instant-v1",
     messages = [
         {
@@ -22,7 +22,7 @@ response = openai.ChatCompletion.create(
 print(response)
 
 
-# response = openai.ChatCompletion.create(
+# response = openai.chat.completions.create(
 #     model = "gpt-3.5-turbo",
 #     messages = [
 #         {
diff --git a/litellm_server/tests/test_caching.py b/litellm_server/tests/test_caching.py
index 36843e7d2..c95d31924 100644
--- a/litellm_server/tests/test_caching.py
+++ b/litellm_server/tests/test_caching.py
@@ -4,7 +4,7 @@ dotenv.load_dotenv()
 openai.api_key = os.getenv("ANTHROPIC_API_KEY") # this gets passed as a header 
 
 
-response1 = openai.ChatCompletion.create(
+response1 = openai.chat.completions.create(
     model = "claude-instant-1",
     messages = [
         {
@@ -21,7 +21,7 @@ except:
 
 time.sleep(1) # allow time for request to be stored 
 
-response2 = openai.ChatCompletion.create(
+response2 = openai.chat.completions.create(
     model = "claude-instant-1",
     messages = [
         {
@@ -39,7 +39,7 @@ except:
 openai.api_key = os.getenv("OPENAI_API_KEY")
 
 try: 
-    response3 = openai.ChatCompletion.create(
+    response3 = openai.chat.completions.create(
         model = "gpt-3.5-turbo",
         messages = [
             {
@@ -58,7 +58,7 @@ except:
 
 openai.api_key = os.getenv("ANTHROPIC_API_KEY") # this gets passed as a header 
 # switch caching off using cache flag
-response4 = openai.ChatCompletion.create(
+response4 = openai.chat.completions.create(
     model = "claude-instant-1",
     messages = [
         {
diff --git a/litellm_server/tests/test_openai.py b/litellm_server/tests/test_openai.py
index dfbb2188e..1a0556dbb 100644
--- a/litellm_server/tests/test_openai.py
+++ b/litellm_server/tests/test_openai.py
@@ -5,7 +5,7 @@ openai.api_key = "this can be anything"
 print("making request")
 
 api_key = "" 
-response = openai.ChatCompletion.create(
+response = openai.chat.completions.create(
     model = "gpt-3.5-turbo",
     messages = [
         {
@@ -21,7 +21,7 @@ response = openai.ChatCompletion.create(
 print(response)
 
 
-response = openai.ChatCompletion.create(
+response = openai.chat.completions.create(
     model = "gpt-3.5-turbo",
     messages = [
         {
diff --git a/litellm_server/tests/test_openrouter.py b/litellm_server/tests/test_openrouter.py
index 0ee8fd799..861fb771e 100644
--- a/litellm_server/tests/test_openrouter.py
+++ b/litellm_server/tests/test_openrouter.py
@@ -4,7 +4,7 @@ openai.api_key = "this can be anything"
 print("making request")
 
 api_key = ""
-response = openai.ChatCompletion.create(
+response = openai.chat.completions.create(
     model = "openrouter/google/palm-2-chat-bison",
     messages = [
         {
@@ -20,7 +20,7 @@ response = openai.ChatCompletion.create(
 print(response)
 
 
-response = openai.ChatCompletion.create(
+response = openai.chat.completions.create(
     model = "openrouter/google/palm-2-chat-bison",
     messages = [
         {