diff --git a/litellm/llms/bedrock.py b/litellm/llms/bedrock.py
index 99550280a57..617964a749b 100644
--- a/litellm/llms/bedrock.py
+++ b/litellm/llms/bedrock.py
@@ -2,7 +2,7 @@ import json, copy, types
 import os
 from enum import Enum
 import time
-from typing import Callable, Optional, Any
+from typing import Callable, Optional, Any, Union
 import litellm
 from litellm.utils import ModelResponse, get_secret, Usage
 from .prompt_templates.factory import prompt_factory, custom_prompt
@@ -714,7 +714,7 @@ def _embedding_func_single(
 
 def embedding(
     model: str,
-    input: list,
+    input: Union[list, str],
     api_key: Optional[str] = None,
     logging_obj=None,
     model_response=None,
@@ -737,18 +737,28 @@ def embedding(
         aws_region_name=aws_region_name,
         aws_bedrock_runtime_endpoint=aws_bedrock_runtime_endpoint,
     )
-
-    ## Embedding Call
-    embeddings = [
-        _embedding_func_single(
-            model,
-            i,
-            optional_params=optional_params,
-            client=client,
-            logging_obj=logging_obj,
-        )
-        for i in input
-    ]  # [TODO]: make these parallel calls
+    if type(input) == str:
+        embeddings = [
+            _embedding_func_single(
+                model,
+                input,
+                optional_params=optional_params,
+                client=client,
+                logging_obj=logging_obj,
+            )
+        ]
+    else:
+        ## Embedding Call
+        embeddings = [
+            _embedding_func_single(
+                model,
+                i,
+                optional_params=optional_params,
+                client=client,
+                logging_obj=logging_obj,
+            )
+            for i in input
+        ]  # [TODO]: make these parallel calls
 
     ## Populate OpenAI compliant dictionary
     embedding_response = []
diff --git a/litellm/tests/test_embedding.py b/litellm/tests/test_embedding.py
index 954a53e2a83..6505d432dc1 100644
--- a/litellm/tests/test_embedding.py
+++ b/litellm/tests/test_embedding.py
@@ -186,13 +186,16 @@ def test_cohere_embedding3():
 
 def test_bedrock_embedding_titan():
     try:
+        # this tests if we support str input for bedrock embedding
         litellm.set_verbose = True
+        litellm.enable_cache()
+        import time
+
+        current_time = str(time.time())
+        # DO NOT MAKE THE INPUT A LIST in this test
         response = embedding(
-            model="amazon.titan-embed-text-v1",
-            input=[
-                "good morning from litellm, attempting to embed data",
-                "lets test a second string for good measure",
-            ],
+            model="bedrock/amazon.titan-embed-text-v1",
+            input=f"good morning from litellm, attempting to embed data {current_time}",  # input should always be a string in this test
         )
         print(f"response:", response)
         assert isinstance(
@@ -202,11 +205,28 @@ def test_bedrock_embedding_titan():
         assert all(
             isinstance(x, float) for x in response["data"][0]["embedding"]
         ), "Expected response to be a list of floats"
+
+        # this also tests if we can return a cache response for this scenario
+        import time
+
+        start_time = time.time()
+
+        response = embedding(
+            model="bedrock/amazon.titan-embed-text-v1",
+            input=f"good morning from litellm, attempting to embed data {current_time}",  # input should always be a string in this test
+        )
+        print(response)
+
+        end_time = time.time()
+        print(f"Embedding 2 response time: {end_time - start_time} seconds")
+
+        assert end_time - start_time < 0.1
+        litellm.disable_cache()
     except Exception as e:
         pytest.fail(f"Error occurred: {e}")
 
 
-# test_bedrock_embedding_titan()
+test_bedrock_embedding_titan()
 
 
 def test_bedrock_embedding_cohere():
@@ -280,7 +300,7 @@ def test_aembedding():
         pytest.fail(f"Error occurred: {e}")
 
 
-test_aembedding()
+# test_aembedding()
 
 
 def test_aembedding_azure():