diff --git a/docs/my-website/docs/completion/reliable_completions.md b/docs/my-website/docs/completion/reliable_completions.md
index e9a0a2f6c..a58975c1b 100644
--- a/docs/my-website/docs/completion/reliable_completions.md
+++ b/docs/my-website/docs/completion/reliable_completions.md
@@ -1,10 +1,36 @@
 # Reliability
 
+
+
+## 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
 * `completion()` with fallback models: set `fallback_models=['gpt-3.5-turbo', 'command-nightly', 'llama2`]. If primary model fails try fallback models
 
-## Completion with Retries
+## 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. 
 
@@ -29,7 +55,7 @@ def test_completion_custom_provider_model_name():
         printf"Error occurred: {e}")
 ```
 
-## Completion with Fallbacks
+## Specify fallback models
 LLM APIs can be unstable, completion() with fallbacks ensures you'll always get a response from your calls
 
 ## Usage 
diff --git a/litellm/__init__.py b/litellm/__init__.py
index ce1cace84..df81cf7b3 100644
--- a/litellm/__init__.py
+++ b/litellm/__init__.py
@@ -261,7 +261,7 @@ models_by_provider: dict = {
 }
 
 # mapping for those models which have larger equivalents 
-longer_context_model_fallback_dict = {
+longer_context_model_fallback_dict: dict = {
     # openai chat completion models
     "gpt-3.5-turbo": "gpt-3.5-turbo-16k", 
     "gpt-3.5-turbo-0301": "gpt-3.5-turbo-16k-0301", 
diff --git a/litellm/__pycache__/__init__.cpython-311.pyc b/litellm/__pycache__/__init__.cpython-311.pyc
index 05a7c09e2..d18aa4f22 100644
Binary files a/litellm/__pycache__/__init__.cpython-311.pyc and b/litellm/__pycache__/__init__.cpython-311.pyc differ
diff --git a/litellm/tests/test_longer_context_fallback.py b/litellm/tests/test_longer_context_fallback.py
new file mode 100644
index 000000000..8f8942897
--- /dev/null
+++ b/litellm/tests/test_longer_context_fallback.py
@@ -0,0 +1,13 @@
+#### What this tests ####
+#    This tests context fallback dict
+
+import sys, os
+import traceback
+import pytest
+sys.path.insert(
+    0, os.path.abspath("../..")
+)  # Adds the parent directory to the system path
+import litellm
+from litellm import longer_context_model_fallback_dict
+
+print(longer_context_model_fallback_dict)
\ No newline at end of file
diff --git a/pyproject.toml b/pyproject.toml
index d68537b92..6a70ee9c3 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "litellm"
-version = "0.1.749"
+version = "0.1.750"
 description = "Library to easily interface with LLM API providers"
 authors = ["BerriAI"]
 license = "MIT License"