diff --git a/litellm/proxy/post_call_rules.py b/litellm/proxy/post_call_rules.py
new file mode 100644
index 000000000..23ec93f5b
--- /dev/null
+++ b/litellm/proxy/post_call_rules.py
@@ -0,0 +1,8 @@
+def post_response_rule(input):  # receives the model response
+    print(f"post_response_rule:input={input}")  # noqa
+    if len(input) < 200:
+        return {
+            "decision": False,
+            "message": "This violates LiteLLM Proxy Rules. Response too short",
+        }
+    return {"decision": True}  # message not required since, request will pass
diff --git a/litellm/proxy/proxy_config.yaml b/litellm/proxy/proxy_config.yaml
index 81374c8ee..2699e9d9c 100644
--- a/litellm/proxy/proxy_config.yaml
+++ b/litellm/proxy/proxy_config.yaml
@@ -14,6 +14,9 @@ model_list:
   - model_name: BEDROCK_GROUP
     litellm_params:
       model: bedrock/cohere.command-text-v14
+  - model_name: sagemaker
+    litellm_params:
+      model: sagemaker/berri-benchmarking-Llama-2-70b-chat-hf-4
   - model_name: openai-gpt-3.5
     litellm_params:
       model: gpt-3.5-turbo
@@ -42,6 +45,7 @@ model_list:
     model_info:
       mode: embedding
 litellm_settings:
+  post_call_rules: post_call_rules.post_response_rule
   fallbacks: [{"openai-gpt-3.5": ["azure-gpt-3.5"]}]
   # cache: True     
   # setting callback class