diff --git a/litellm/llms/bedrock/embed/amazon_titan_multimodal_transformation.py b/litellm/llms/bedrock/embed/amazon_titan_multimodal_transformation.py
index 07b04734c30..d67f936aa88 100644
--- a/litellm/llms/bedrock/embed/amazon_titan_multimodal_transformation.py
+++ b/litellm/llms/bedrock/embed/amazon_titan_multimodal_transformation.py
@@ -93,9 +93,9 @@ class AmazonTitanMultimodalEmbeddingG1Config:
             )
 
         usage = Usage(
-            prompt_tokens=total_prompt_tokens,
+            prompt_tokens=total_prompt_tokens + image_count,
             completion_tokens=0,
-            total_tokens=total_prompt_tokens,
+            total_tokens=total_prompt_tokens + image_count,
             prompt_tokens_details=prompt_tokens_details,
         )
         return EmbeddingResponse(model=model, usage=usage, data=transformed_responses)
diff --git a/tests/test_litellm/llms/bedrock/embed/test_bedrock_embedding.py b/tests/test_litellm/llms/bedrock/embed/test_bedrock_embedding.py
index a38a6612f79..d2813ecb3a8 100644
--- a/tests/test_litellm/llms/bedrock/embed/test_bedrock_embedding.py
+++ b/tests/test_litellm/llms/bedrock/embed/test_bedrock_embedding.py
@@ -863,6 +863,8 @@ def test_titan_multimodal_embedding_image_cost_tracking():
     )
 
     assert result.usage is not None
+    assert result.usage.prompt_tokens == 1  # image_count included in prompt_tokens
+    assert result.usage.total_tokens == 1
     assert result.usage.prompt_tokens_details is not None
     assert result.usage.prompt_tokens_details.image_count == 1