diff --git a/docs/my-website/docs/completion/input.md b/docs/my-website/docs/completion/input.md
index 082b82d4f..6f6cfb1e2 100644
--- a/docs/my-website/docs/completion/input.md
+++ b/docs/my-website/docs/completion/input.md
@@ -84,8 +84,11 @@ def completion(
     api_base: Optional[str] = None,
     api_version: Optional[str] = None,
     api_key: Optional[str] = None,
+    num_retries: Optional[int] = None, # set to retry a model if an APIError, TimeoutError, or ServiceUnavailableError occurs 
+    context_window_fallback_dict: Optional[dict] = None, # mapping of model to use if call fails due to context window error
     fallbacks: Optional[list] = None, # pass in a list of api_base,keys, etc. 
     metadata: Optional[dict] = None # additional call metadata, passed to logging integrations / custom callbacks
+    
 
     **kwargs,
 ) -> ModelResponse:
@@ -143,10 +146,16 @@ def completion(
 
 - `request_timeout`: *int (optional)* - Timeout in seconds for completion requests (Defaults to 600 seconds)
 
+#### litellm-specific params 
+
 - `api_base`: *string (optional)* - The api endpoint you want to call the model with
 
 - `api_version`: *string (optional)* - (Azure-specific) the api version for the call
 
+- `num_retries`: *int (optional)* - The number of times to retry the API call if an APIError, TimeoutError or ServiceUnavailableError occurs 
+
+- `context_window_fallback_dict`: *dict (optional)* - A mapping of model to use if call fails due to context window error
+
 - `fallbacks`: *list (optional)* - A list of model names + params to be used, in case the initial call fails
 
 - `metadata`: *dict (optional)* - Any additional data you want to be logged when the call is made (sent to logging integrations, eg. promptlayer and accessible via custom callback function)
diff --git a/docs/my-website/docs/completion/reliable_completions.md b/docs/my-website/docs/completion/reliable_completions.md
index 2b340a5d0..eb64eaf91 100644
--- a/docs/my-website/docs/completion/reliable_completions.md
+++ b/docs/my-website/docs/completion/reliable_completions.md
@@ -1,62 +1,53 @@
 # Reliability
+
+LiteLLM helps prevent failed requests in 2 ways: 
+- Retries
+- Fallbacks: Context Window + General
+
 ## Helper utils 
 LiteLLM supports the following functions for reliability:
 * `litellm.longer_context_model_fallback_dict`: Dictionary which has a mapping for those models which have larger equivalents  
-* `completion_with_retries`: use tenacity retries
+* `num_retries`: use tenacity retries
 * `completion()` with fallbacks: switch between models/keys/api bases in case of errors. 
 
-## Context Window Errors 
-
-```python 
-from litellm import longer_context_model_fallback_dict, ContextWindowExceededError
-
-sample_text = "how does a court case get to the Supreme Court?" * 1000
-messages = [{"content": user_message, "role": "user"}]
-model = "gpt-3.5-turbo"
-try: 
-    # try the original model
-    response = completion(model=model, messages=messages) 
-# catch the context window error
-except ContextWindowExceededError as e:
-    if model in longer_context_model_fallback_dict: 
-        # switch to the equivalent larger model -> gpt.3.5-turbo-16k 
-        new_model = longer_context_model_fallback_dict[model]
-        response = completion(new_model, messages)
-
-print(response)
-```
-
-
 ## Retry failed requests
 
-You can use this as a drop-in replacement for the `completion()` function to use tenacity retries - by default we retry the call 3 times. 
+Call it in completion like this `completion(..num_retries=2)`.
+
 
 Here's a quick look at how you can use it: 
 
 ```python 
-from litellm import completion_with_retries
+from litellm import completion
 
 user_message = "Hello, whats the weather in San Francisco??"
 messages = [{"content": user_message, "role": "user"}]
 
 # normal call 
-def test_completion_custom_provider_model_name():
-    try:
-        response = completion_with_retries(
+response = completion(
             model="gpt-3.5-turbo",
             messages=messages,
+            num_retries=2
         )
-        # Add any assertions here to check the response
-        print(response)
-    except Exception as e:
-        printf"Error occurred: {e}")
 ```
 
-## Switch Models/API Keys/API Bases
+## Fallbacks 
+
+### Context Window Fallbacks
+```python 
+from litellm import completion
+
+fallback_dict = {"gpt-3.5-turbo": "gpt-3.5-turbo-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=ctx_window_fallback_dict)
+```
+
+### Fallbacks - Switch Models/API Keys/API Bases
 
 LLM APIs can be unstable, completion() with fallbacks ensures you'll always get a response from your calls
 
-### Usage 
+#### Usage 
 To use fallback models with `completion()`, specify a list of models in the `fallbacks` parameter. 
 
 The `fallbacks` list should include the primary model you want to use, followed by additional models that can be used as backups in case the primary model fails to provide a response.
@@ -76,6 +67,11 @@ response = completion(model="azure/gpt-4", messages=messages, api_key=api_key,
     fallbacks=[{"api_key": "good-key-1"}, {"api_key": "good-key-2", "api_base": "good-api-base-2"}])
 ```
 
+[Check out this section for implementation details](#fallbacks-1)
+
+## Implementation Details 
+
+### Fallbacks
 #### Output from calls
 ```
 Completion with 'bad-model': got exception Unable to map your input to a model. Check your input - {'model': 'bad-model'
@@ -112,7 +108,7 @@ completion call gpt-3.5-turbo
 When you pass `fallbacks` to `completion`, it makes the first `completion` call using the primary model specified as `model` in `completion(model=model)`. If the primary model fails or encounters an error, it automatically tries the `fallbacks` models in the specified order. This ensures a response even if the primary model is unavailable.
 
 
-### Key components of Model Fallbacks implementation:
+#### Key components of Model Fallbacks implementation:
 * Looping through `fallbacks`
 * Cool-Downs for rate-limited models
 
diff --git a/docs/my-website/docs/routing.md b/docs/my-website/docs/routing.md
index d91009986..391b20b2f 100644
--- a/docs/my-website/docs/routing.md
+++ b/docs/my-website/docs/routing.md
@@ -1,17 +1,78 @@
-# Reliability - Fallbacks, Multiple Deployments
+# Reliability - Fallbacks, Azure Deployments, etc.
 
-## Model Fallbacks
-Never fail a request using LiteLLM, LiteLLM allows you to define fallback models for completion requests
-```python
+# Reliability
+
+LiteLLM helps prevent failed requests in 3 ways: 
+- Retries
+- Fallbacks: Context Window + General
+- RateLimitManager
+
+## Helper utils 
+LiteLLM supports the following functions for reliability:
+* `litellm.longer_context_model_fallback_dict`: Dictionary which has a mapping for those models which have larger equivalents  
+* `num_retries`: use tenacity retries
+* `completion()` with fallbacks: switch between models/keys/api bases in case of errors. 
+* `router()`: An abstraction on top of completion + embeddings to route the request to a deployment with capacity (available tpm/rpm).
+
+## Retry failed requests
+
+Call it in completion like this `completion(..num_retries=2)`.
+
+
+Here's a quick look at how you can use it: 
+
+```python 
 from litellm import completion
-# if gpt-4 fails, retry the request with gpt-3.5-turbo->command-nightly->claude-instant-1
-response = completion(model="gpt-4",messages=messages, fallbacks=["gpt-3.5-turbo" "command-nightly", "claude-instant-1"])
 
-# if azure/gpt-4 fails, retry the request with fallback api_keys/api_base
-response = completion(model="azure/gpt-4", messages=messages, api_key=api_key, fallbacks=[{"api_key": "good-key-1"}, {"api_key": "good-key-2", "api_base": "good-api-base-2"}])
+user_message = "Hello, whats the weather in San Francisco??"
+messages = [{"content": user_message, "role": "user"}]
 
+# normal call 
+response = completion(
+            model="gpt-3.5-turbo",
+            messages=messages,
+            num_retries=2
+        )
 ```
 
+## Fallbacks 
+
+### Context Window Fallbacks
+```python 
+from litellm import completion
+
+fallback_dict = {"gpt-3.5-turbo": "gpt-3.5-turbo-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=ctx_window_fallback_dict)
+```
+
+### Fallbacks - Switch Models/API Keys/API Bases
+
+LLM APIs can be unstable, completion() with fallbacks ensures you'll always get a response from your calls
+
+#### Usage 
+To use fallback models with `completion()`, specify a list of models in the `fallbacks` parameter. 
+
+The `fallbacks` list should include the primary model you want to use, followed by additional models that can be used as backups in case the primary model fails to provide a response.
+
+#### switch models 
+```python
+response = completion(model="bad-model", messages=messages, 
+    fallbacks=["gpt-3.5-turbo" "command-nightly"])
+```
+
+#### switch api keys/bases (E.g. azure deployment)
+Switch between different keys for the same azure deployment, or use another deployment as well. 
+
+```python
+api_key="bad-key"
+response = completion(model="azure/gpt-4", messages=messages, api_key=api_key,
+    fallbacks=[{"api_key": "good-key-1"}, {"api_key": "good-key-2", "api_base": "good-api-base-2"}])
+```
+
+[Check out this section for implementation details](#fallbacks-1)
+
 ## Manage Multiple Deployments
 
 Use this if you're trying to load-balance across multiple deployments (e.g. Azure/OpenAI). 
@@ -109,4 +170,131 @@ curl 'http://0.0.0.0:8000/router/completions' \
     "model": "gpt-3.5-turbo",
     "messages": [{"role": "user", "content": "Hey"}]
 }'
+```
+
+
+## Implementation Details 
+
+### Fallbacks
+#### Output from calls
+```
+Completion with 'bad-model': got exception Unable to map your input to a model. Check your input - {'model': 'bad-model'
+
+
+
+completion call gpt-3.5-turbo
+{
+  "id": "chatcmpl-7qTmVRuO3m3gIBg4aTmAumV1TmQhB",
+  "object": "chat.completion",
+  "created": 1692741891,
+  "model": "gpt-3.5-turbo-0613",
+  "choices": [
+    {
+      "index": 0,
+      "message": {
+        "role": "assistant",
+        "content": "I apologize, but as an AI, I do not have the capability to provide real-time weather updates. However, you can easily check the current weather in San Francisco by using a search engine or checking a weather website or app."
+      },
+      "finish_reason": "stop"
+    }
+  ],
+  "usage": {
+    "prompt_tokens": 16,
+    "completion_tokens": 46,
+    "total_tokens": 62
+  }
+}
+
+```
+
+#### How does fallbacks work
+
+When you pass `fallbacks` to `completion`, it makes the first `completion` call using the primary model specified as `model` in `completion(model=model)`. If the primary model fails or encounters an error, it automatically tries the `fallbacks` models in the specified order. This ensures a response even if the primary model is unavailable.
+
+
+#### Key components of Model Fallbacks implementation:
+* Looping through `fallbacks`
+* Cool-Downs for rate-limited models
+
+#### Looping through `fallbacks`
+Allow `45seconds` for each request. In the 45s this function tries calling the primary model set as `model`. If model fails it loops through the backup `fallbacks` models and attempts to get a response in the allocated `45s` time set here: 
+```python
+while response == None and time.time() - start_time < 45:
+        for model in fallbacks:
+```
+
+#### Cool-Downs for rate-limited models
+If a model API call leads to an error - allow it to cooldown for `60s`
+```python
+except Exception as e:
+  print(f"got exception {e} for model {model}")
+  rate_limited_models.add(model)
+  model_expiration_times[model] = (
+      time.time() + 60
+  )  # cool down this selected model
+  pass
+```
+
+Before making an LLM API call we check if the selected model is in `rate_limited_models`, if so skip making the API call
+```python
+if (
+  model in rate_limited_models
+):  # check if model is currently cooling down
+  if (
+      model_expiration_times.get(model)
+      and time.time() >= model_expiration_times[model]
+  ):
+      rate_limited_models.remove(
+          model
+      )  # check if it's been 60s of cool down and remove model
+  else:
+      continue  # skip model
+
+```
+
+#### Full code of completion with fallbacks()
+```python
+
+    response = None
+    rate_limited_models = set()
+    model_expiration_times = {}
+    start_time = time.time()
+    fallbacks = [kwargs["model"]] + kwargs["fallbacks"]
+    del kwargs["fallbacks"]  # remove fallbacks so it's not recursive
+
+    while response == None and time.time() - start_time < 45:
+        for model in fallbacks:
+            # loop thru all models
+            try:
+                if (
+                    model in rate_limited_models
+                ):  # check if model is currently cooling down
+                    if (
+                        model_expiration_times.get(model)
+                        and time.time() >= model_expiration_times[model]
+                    ):
+                        rate_limited_models.remove(
+                            model
+                        )  # check if it's been 60s of cool down and remove model
+                    else:
+                        continue  # skip model
+
+                # delete model from kwargs if it exists
+                if kwargs.get("model"):
+                    del kwargs["model"]
+
+                print("making completion call", model)
+                response = litellm.completion(**kwargs, model=model)
+
+                if response != None:
+                    return response
+
+            except Exception as e:
+                print(f"got exception {e} for model {model}")
+                rate_limited_models.add(model)
+                model_expiration_times[model] = (
+                    time.time() + 60
+                )  # cool down this selected model
+                pass
+    return response
 ```
\ No newline at end of file
diff --git a/docs/my-website/sidebars.js b/docs/my-website/sidebars.js
index 5fb55c6b5..c5404f2c4 100644
--- a/docs/my-website/sidebars.js
+++ b/docs/my-website/sidebars.js
@@ -36,7 +36,6 @@ const sidebars = {
         "completion/message_trimming",
         "completion/function_call",
         "completion/model_alias", 
-        "completion/reliable_completions", 
         "completion/config",
         "completion/batching",
         "completion/mock_requests",
diff --git a/litellm/tests/test_completion.py b/litellm/tests/test_completion.py
index 5c2b96704..3fbaa79d9 100644
--- a/litellm/tests/test_completion.py
+++ b/litellm/tests/test_completion.py
@@ -1149,7 +1149,7 @@ def test_completion_with_fallbacks():
     except Exception as e:
         pytest.fail(f"Error occurred: {e}")
 
-# test_completion_with_fallbacks()
+test_completion_with_fallbacks()
 def test_completion_anyscale_api():
     try:
         # litellm.set_verbose=True