diff --git a/README.md b/README.md
index b3cfea0f0..d155d2d4c 100644
--- a/README.md
+++ b/README.md
@@ -45,8 +45,13 @@ from litellm import completion
 import os
 
 ## set ENV variables 
+<<<<<<< HEAD
 os.environ["OPENAI_API_KEY"] = "your-openai-key" 
 os.environ["COHERE_API_KEY"] = "your-cohere-key" 
+=======
+os.environ["OPENAI_API_KEY"] = "your-api-key"
+os.environ["COHERE_API_KEY"] = "your-api-key"
+>>>>>>> 6a9d754 (remove api key from docs)
 
 messages = [{ "content": "Hello, how are you?","role": "user"}]
 
diff --git a/docs/my-website/docs/completion/config.md b/docs/my-website/docs/completion/config.md
index 4bfd003fd..44ff6e8a7 100644
--- a/docs/my-website/docs/completion/config.md
+++ b/docs/my-website/docs/completion/config.md
@@ -17,8 +17,8 @@ config = {
 }
 
 # set env var
-os.environ["OPENAI_API_KEY"] = "sk-litellm-7_NPZhMGxY2GoHC59LgbDw" # [OPTIONAL] replace with your openai key
-os.environ["ANTHROPIC_API_KEY"] = "sk-litellm-7_NPZhMGxY2GoHC59LgbDw" # [OPTIONAL] replace with your anthropic key
+os.environ["OPENAI_API_KEY"] = "your-api-key"
+os.environ["ANTHROPIC_API_KEY"] = "your-api-key"
 
 
 sample_text = "how does a court case get to the Supreme Court?" * 1000
diff --git a/docs/my-website/docs/completion/output.md b/docs/my-website/docs/completion/output.md
index 4b56e7baa..eda86ac27 100644
--- a/docs/my-website/docs/completion/output.md
+++ b/docs/my-website/docs/completion/output.md
@@ -57,7 +57,7 @@ You can also access information like latency.
 
 ```python
 import litellm
-os.environ["ANTHROPIC_API_KEY"] = "sk-litellm-5b46387675a944d2"
+os.environ["ANTHROPIC_API_KEY"] = "your-api-key"
 
 messages=[{"role": "user", "content": "Hey!"}]
 
diff --git a/docs/my-website/docs/getting_started.md b/docs/my-website/docs/getting_started.md
index 050a951e8..00d455e0c 100644
--- a/docs/my-website/docs/getting_started.md
+++ b/docs/my-website/docs/getting_started.md
@@ -12,8 +12,8 @@ By default we provide a free $10 community-key to try all providers supported on
 from litellm import completion
 
 ## set ENV variables
-os.environ["OPENAI_API_KEY"] = "sk-litellm-7_NPZhMGxY2GoHC59LgbDw" # [OPTIONAL] replace with your openai key
-os.environ["COHERE_API_KEY"] = "sk-litellm-7_NPZhMGxY2GoHC59LgbDw" # [OPTIONAL] replace with your cohere key
+os.environ["OPENAI_API_KEY"] = "your-api-key"
+os.environ["COHERE_API_KEY"] = "your-api-key"
 
 messages = [{ "content": "Hello, how are you?","role": "user"}]
 
diff --git a/docs/my-website/docs/index.md b/docs/my-website/docs/index.md
index a0c519320..1a22b114e 100644
--- a/docs/my-website/docs/index.md
+++ b/docs/my-website/docs/index.md
@@ -23,7 +23,7 @@ from litellm import completion
 import os
 
 ## set ENV variables
-os.environ["OPENAI_API_KEY"] = "sk-litellm-7_NPZhMGxY2GoHC59LgbDw" # [OPTIONAL] replace with your openai key
+os.environ["OPENAI_API_KEY"] = "your-api-key"
 
 response = completion(
   model="gpt-3.5-turbo", 
@@ -39,7 +39,7 @@ from litellm import completion
 import os
 
 ## set ENV variables
-os.environ["ANTHROPIC_API_KEY"] = "sk-litellm-7_NPZhMGxY2GoHC59LgbDw" # [OPTIONAL] replace with your openai key
+os.environ["ANTHROPIC_API_KEY"] = "your-api-key"
 
 response = completion(
   model="claude-2", 
@@ -133,7 +133,7 @@ from litellm import completion
 import os
 
 ## set ENV variables
-os.environ["OPENAI_API_KEY"] = "sk-litellm-7_NPZhMGxY2GoHC59LgbDw" # [OPTIONAL] replace with your openai key
+os.environ["OPENAI_API_KEY"] = "your-api-key"
 
 response = completion(
   model="gpt-3.5-turbo", 
@@ -150,7 +150,7 @@ from litellm import completion
 import os
 
 ## set ENV variables
-os.environ["ANTHROPIC_API_KEY"] = "sk-litellm-7_NPZhMGxY2GoHC59LgbDw" # [OPTIONAL] replace with your openai key
+os.environ["ANTHROPIC_API_KEY"] = "your-api-key"
 
 response = completion(
   model="claude-2", 
@@ -262,7 +262,7 @@ Pass the completion response to `litellm.completion_cost(completion_response=res
 ```python
 from litellm import completion, completion_cost
 import os
-os.environ["OPENAI_API_KEY"] = "sk-litellm-7_NPZhMGxY2GoHC59LgbDw"
+os.environ["OPENAI_API_KEY"] = "your-api-key"
 
 response = completion(
   model="gpt-3.5-turbo", 
@@ -289,7 +289,7 @@ import os
 from litellm import completion
 
 # use the LiteLLM API Key
-os.environ["ANTHROPIC_API_KEY"] = "sk-litellm-7_NPZhMGxY2GoHC59LgbDw"
+os.environ["ANTHROPIC_API_KEY"] = "your-api-key"
 
 messages = [{ "content": "Hello, how are you?","role": "user"}]
 
@@ -304,7 +304,7 @@ import os
 from litellm import completion
 
 # use the LiteLLM API Key
-os.environ["OPENAI_API_KEY"] = "sk-litellm-7_NPZhMGxY2GoHC59LgbDw"
+os.environ["OPENAI_API_KEY"] = "your-api-key"
 
 messages = [{ "content": "Hello, how are you?","role": "user"}]
 
@@ -319,7 +319,7 @@ import os
 from litellm import completion
 
 # use the LiteLLM API Key
-os.environ["TOGETHERAI_API_KEY"] = "sk-litellm-7_NPZhMGxY2GoHC59LgbDw"
+os.environ["TOGETHERAI_API_KEY"] = "your-api-key"
 
 messages = [{ "content": "Hello, how are you?","role": "user"}]
 
@@ -335,7 +335,7 @@ import os
 from litellm import completion
 
 # use the LiteLLM API Key
-os.environ["TOGETHERAI_API_KEY"] = "sk-litellm-7_NPZhMGxY2GoHC59LgbDw"
+os.environ["TOGETHERAI_API_KEY"] = "your-api-key"
 
 messages = [{ "content": "Hello, how are you?","role": "user"}]
 
diff --git a/docs/my-website/docs/providers/ai21.md b/docs/my-website/docs/providers/ai21.md
index db5c90b39..c0987b312 100644
--- a/docs/my-website/docs/providers/ai21.md
+++ b/docs/my-website/docs/providers/ai21.md
@@ -5,24 +5,18 @@ LiteLLM supports j2-light, j2-mid and j2-ultra from [AI21](https://www.ai21.com/
 They're available to use without a waitlist.
 
 ### API KEYS
-We provide a free $10 community-key for testing all providers on LiteLLM. You can replace this with your own key. 
-
 ```python
 import os 
-os.environ["AI21_API_KEY"] = "sk-litellm-7_NPZhMGxY2GoHC59LgbDw" # [OPTIONAL] replace with your ai21 key
+os.environ["AI21_API_KEY"] = "your-api-key"
 ```
-**Need a dedicated key?**
-Email us @ krrish@berri.ai 
-
-[**See all supported models by the litellm api key**](../proxy_api.md#supported-models-for-litellm-key)
 
 ### Sample Usage
 
 ```python
 from litellm import completion 
 
-# set env variable - [OPTIONAL] replace with your ai21 key
-os.environ["AI21_API_KEY"] = "sk-litellm-7_NPZhMGxY2GoHC59LgbDw"
+# set env variable 
+os.environ["AI21_API_KEY"] = "your-api-key"
 
 messages = [{"role": "user", "content": "Write me a poem about the blue sky"}]
 
diff --git a/docs/my-website/docs/providers/anthropic.md b/docs/my-website/docs/providers/anthropic.md
index c6fee4539..2ae162cea 100644
--- a/docs/my-website/docs/providers/anthropic.md
+++ b/docs/my-website/docs/providers/anthropic.md
@@ -2,18 +2,12 @@
 LiteLLM supports Claude-1, 1.2 and Claude-2.
 
 ## API Keys
-We provide a free $10 community-key for testing all providers on LiteLLM. You can replace this with your own key. 
 
 ```python 
 import os 
 
-os.environ["ANTHROPIC_API_KEY"] = "sk-litellm-7_NPZhMGxY2GoHC59LgbDw" # [OPTIONAL] replace with your anthropic key
+os.environ["ANTHROPIC_API_KEY"] = "your-api-key"
 ```
-**Need a dedicated key?**
-Email us @ krrish@berri.ai 
-
-## Supported Models for LiteLLM Key
-These are the models that currently work with the "sk-litellm-.." keys.
 
 ## Sample Usage
 
@@ -22,7 +16,7 @@ import os
 from litellm import completion 
 
 # set env - [OPTIONAL] replace with your anthropic key
-os.environ["ANTHROPIC_API_KEY"] = "sk-litellm-7_NPZhMGxY2GoHC59LgbDw" 
+os.environ["ANTHROPIC_API_KEY"] = "your-api-key" 
 
 messages = [{"role": "user", "content": "Hey! how's it going?"}]
 response = completion(model="claude-instant-1", messages=messages)
@@ -36,8 +30,8 @@ Just set `stream=True` when calling completion.
 import os
 from litellm import completion 
 
-# set env - [OPTIONAL] replace with your anthropic key
-os.environ["ANTHROPIC_API_KEY"] = "sk-litellm-7_NPZhMGxY2GoHC59LgbDw" 
+# set env 
+os.environ["ANTHROPIC_API_KEY"] = "your-api-key" 
 
 messages = [{"role": "user", "content": "Hey! how's it going?"}]
 response = completion(model="claude-instant-1", messages=messages, stream=True)
diff --git a/docs/my-website/docs/providers/nlp_cloud.md b/docs/my-website/docs/providers/nlp_cloud.md
index 399707b45..3d74fb7e1 100644
--- a/docs/my-website/docs/providers/nlp_cloud.md
+++ b/docs/my-website/docs/providers/nlp_cloud.md
@@ -3,17 +3,12 @@
 LiteLLM supports all LLMs on NLP Cloud.
 
 ## API Keys
-We provide a free $10 community-key for testing all providers on LiteLLM. You can replace this with your own key. 
 
 ```python 
 import os 
 
-os.environ["NLP_CLOUD_API_KEY"] = "sk-litellm-7_NPZhMGxY2GoHC59LgbDw" # [OPTIONAL] replace with your nlp cloud key
+os.environ["NLP_CLOUD_API_KEY"] = "your-api-key"
 ```
-**Need a dedicated key?**
-Email us @ krrish@berri.ai 
-
-[**See all supported models by the litellm api key**](../proxy_api.md#supported-models-for-litellm-key)
 
 ## Sample Usage
 
@@ -21,8 +16,8 @@ Email us @ krrish@berri.ai
 import os
 from litellm import completion 
 
-# set env - [OPTIONAL] replace with your nlp cloud key
-os.environ["NLP_CLOUD_API_KEY"] = "sk-litellm-7_NPZhMGxY2GoHC59LgbDw" 
+# set env
+os.environ["NLP_CLOUD_API_KEY"] = "your-api-key" 
 
 messages = [{"role": "user", "content": "Hey! how's it going?"}]
 response = completion(model="dolphin", messages=messages)
@@ -36,8 +31,8 @@ Just set `stream=True` when calling completion.
 import os
 from litellm import completion 
 
-# set env - [OPTIONAL] replace with your nlp cloud key
-os.environ["NLP_CLOUD_API_KEY"] = "sk-litellm-7_NPZhMGxY2GoHC59LgbDw" 
+# set env
+os.environ["NLP_CLOUD_API_KEY"] = "your-api-key" 
 
 messages = [{"role": "user", "content": "Hey! how's it going?"}]
 response = completion(model="dolphin", messages=messages, stream=True)
@@ -57,7 +52,7 @@ import os
 from litellm import completion 
 
 # set env - [OPTIONAL] replace with your nlp cloud key
-os.environ["NLP_CLOUD_API_KEY"] = "sk-litellm-7_NPZhMGxY2GoHC59LgbDw" 
+os.environ["NLP_CLOUD_API_KEY"] = "your-api-key" 
 
 messages = [{"role": "user", "content": "Hey! how's it going?"}]
 
diff --git a/docs/my-website/docs/providers/openai.md b/docs/my-website/docs/providers/openai.md
index d2db29871..634f9dbbb 100644
--- a/docs/my-website/docs/providers/openai.md
+++ b/docs/my-website/docs/providers/openai.md
@@ -2,12 +2,11 @@
 LiteLLM supports OpenAI Chat + Text completion and embedding calls.
 
 ### API Keys
-We provide a free $10 community-key for testing all providers on LiteLLM. You can replace this with your own key. 
 
 ```python
 import os 
 
-os.environ["OPENAI_API_KEY"] = "sk-litellm-7_NPZhMGxY2GoHC59LgbDw" # [OPTIONAL] replace with your openai key
+os.environ["OPENAI_API_KEY"] = "your-api-key"
 ```
 **Need a dedicated key?**
 Email us @ krrish@berri.ai 
@@ -19,7 +18,7 @@ Email us @ krrish@berri.ai
 import os 
 from litellm import completion
 
-os.environ["OPENAI_API_KEY"] = "sk-litellm-7_NPZhMGxY2GoHC59LgbDw" # [OPTIONAL] replace with your openai key
+os.environ["OPENAI_API_KEY"] = "your-api-key"
 
 
 messages = [{ "content": "Hello, how are you?","role": "user"}]
diff --git a/docs/my-website/docs/providers/togetherai.md b/docs/my-website/docs/providers/togetherai.md
index d8275f061..d718619f0 100644
--- a/docs/my-website/docs/providers/togetherai.md
+++ b/docs/my-website/docs/providers/togetherai.md
@@ -2,26 +2,17 @@
 LiteLLM supports all models on Together AI. 
 
 ## API Keys
-We provide a free $10 community-key for testing all providers on LiteLLM. You can replace this with your own key. 
 
 ```python 
 import os 
-os.environ["TOGETHERAI_API_KEY"] = "sk-litellm-7_NPZhMGxY2GoHC59LgbDw" # [OPTIONAL] replace with your together ai key
+os.environ["TOGETHERAI_API_KEY"] = "your-api-key"
 ```
-
-**Need a dedicated key?**
-Email us @ krrish@berri.ai 
-
-[**See all supported models by the litellm api key**](../proxy_api.md#supported-models-for-litellm-key)
-
-
 ## Sample Usage
 
 ```python
 from litellm import completion 
 
-# set env variable - [OPTIONAL] replace with your together ai key
-os.environ["TOGETHERAI_API_KEY"] = "sk-litellm-7_NPZhMGxY2GoHC59LgbDw"
+os.environ["TOGETHERAI_API_KEY"] = "your-api-key"
 
 messages = [{"role": "user", "content": "Write me a poem about the blue sky"}]
 
diff --git a/docs/my-website/docs/proxy_api.md b/docs/my-website/docs/proxy_api.md
index cbc6198aa..89bfacbe1 100644
--- a/docs/my-website/docs/proxy_api.md
+++ b/docs/my-website/docs/proxy_api.md
@@ -9,8 +9,8 @@ import os
 from litellm import completion
 
 ## set ENV variables
-os.environ["OPENAI_API_KEY"] = "sk-litellm-7_NPZhMGxY2GoHC59LgbDw" # [OPTIONAL] replace with your openai key
-os.environ["COHERE_API_KEY"] = "sk-litellm-7_NPZhMGxY2GoHC59LgbDw" # [OPTIONAL] replace with your cohere key
+os.environ["OPENAI_API_KEY"] = "your-api-key"
+os.environ["COHERE_API_KEY"] = "your-api-key"
 
 messages = [{ "content": "Hello, how are you?","role": "user"}]
 
diff --git a/litellm/__pycache__/main.cpython-311.pyc b/litellm/__pycache__/main.cpython-311.pyc
index 5fbe7b9e0..795fb81a0 100644
Binary files a/litellm/__pycache__/main.cpython-311.pyc and b/litellm/__pycache__/main.cpython-311.pyc differ
diff --git a/litellm/__pycache__/utils.cpython-311.pyc b/litellm/__pycache__/utils.cpython-311.pyc
index 38371ff60..5c9909cc2 100644
Binary files a/litellm/__pycache__/utils.cpython-311.pyc and b/litellm/__pycache__/utils.cpython-311.pyc differ
diff --git a/litellm/tests/test_completion.py b/litellm/tests/test_completion.py
index 4cc36beb7..6071f8c1c 100644
--- a/litellm/tests/test_completion.py
+++ b/litellm/tests/test_completion.py
@@ -437,7 +437,6 @@ def test_completion_openai_litellm_key():
 
 # test_completion_openai_litellm_key()
 
-# commented out for now, as openrouter is quite flaky - causing our deployments to fail. Please run this before pushing changes.
 def test_completion_openrouter1():
     try:
         response = completion(
@@ -453,7 +452,7 @@ def test_completion_openrouter1():
 def test_completion_openrouter2():
     try:
         response = completion(
-            model="google/palm-2-chat-bison",
+            model="openrouter/openai/gpt-4-32k",
             messages=messages,
             max_tokens=5,
         )
@@ -464,6 +463,47 @@ def test_completion_openrouter2():
 
 # test_completion_openrouter()
 
+def test_completion_hf_model_no_provider():
+    try:
+        response = completion(
+            model="WizardLM/WizardLM-70B-V1.0",
+            messages=messages,
+            max_tokens=5,
+        )
+        # Add any assertions here to check the response
+        print(response)
+        pytest.fail(f"Error occurred: {e}")
+    except Exception as e:
+        pass
+
+test_completion_hf_model_no_provider()
+
+def test_completion_hf_model_no_provider_2():
+    try:
+        response = completion(
+            model="meta-llama/Llama-2-70b-chat-hf",
+            messages=messages,
+            max_tokens=5,
+        )
+        # Add any assertions here to check the response
+        pytest.fail(f"Error occurred: {e}")
+    except Exception as e:
+        pass
+
+test_completion_hf_model_no_provider_2()
+
+def test_completion_openrouter2():
+    try:
+        response = completion(
+            model="openrouter/openai/gpt-4-32k",
+            messages=messages,
+            max_tokens=5,
+        )
+        # Add any assertions here to check the response
+        print(response)
+    except Exception as e:
+        pytest.fail(f"Error occurred: {e}")
+
 def test_completion_openai_with_more_optional_params():
     try:
         response = completion(
@@ -865,7 +905,6 @@ def test_completion_with_fallbacks():
     except Exception as e:
         pytest.fail(f"Error occurred: {e}")
 
-
 # def test_completion_with_fallbacks_multiple_keys():
 #     print(f"backup key 1: {os.getenv('BACKUP_OPENAI_API_KEY_1')}")
 #     print(f"backup key 2: {os.getenv('BACKUP_OPENAI_API_KEY_2')}")
diff --git a/litellm/utils.py b/litellm/utils.py
index 94ede879c..b5c9ad2fe 100644
--- a/litellm/utils.py
+++ b/litellm/utils.py
@@ -1187,7 +1187,7 @@ def get_llm_provider(model: str, custom_llm_provider: Optional[str] = None):
             model = model.split("/", 1)[1]
             return model, custom_llm_provider
 
-        # check if model in known model provider list 
+        # check if model in known model provider list  -> for huggingface models, raise exception as they don't have a fixed provider (can be togetherai, anyscale, baseten, runpod, et.)
         ## openai - chatcompletion + text completion
         if model in litellm.open_ai_chat_completion_models:
             custom_llm_provider = "openai"
@@ -1208,15 +1208,9 @@ def get_llm_provider(model: str, custom_llm_provider: Optional[str] = None):
         ## vertex - text + chat models
         elif model in litellm.vertex_chat_models or model in litellm.vertex_text_models:
             custom_llm_provider = "vertex_ai"
-        ## huggingface 
-        elif model in litellm.huggingface_models:
-            custom_llm_provider = "huggingface"
         ## ai21 
         elif model in litellm.ai21_models:
             custom_llm_provider = "ai21"
-        ## together_ai 
-        elif model in litellm.together_ai_models:
-            custom_llm_provider = "together_ai"
         ## aleph_alpha 
         elif model in litellm.aleph_alpha_models:
             custom_llm_provider = "aleph_alpha"
@@ -1231,6 +1225,9 @@ def get_llm_provider(model: str, custom_llm_provider: Optional[str] = None):
             custom_llm_provider = "petals"
         
         if custom_llm_provider is None or custom_llm_provider=="":
+            print()
+            print("\033[1;31mProvider List: https://docs.litellm.ai/docs/providers\033[0m")
+            print()
             raise ValueError(f"LLM Provider NOT provided. Pass in the LLM provider you are trying to call. E.g. For 'Huggingface' inference endpoints pass in `completion(model='huggingface/{model}',..)` Learn more: https://docs.litellm.ai/docs/providers")
         return model, custom_llm_provider
     except Exception as e: