diff --git a/litellm/batches/main.py b/litellm/batches/main.py
index 995c45b925..57a9857dd6 100644
--- a/litellm/batches/main.py
+++ b/litellm/batches/main.py
@@ -1045,28 +1045,44 @@ def _handle_async_invoke_status(
         # Transform response to a LiteLLMBatch object
         from litellm.types.utils import LiteLLMBatch
 
+        # Normalize status to lowercase (AWS returns 'Completed', 'Failed', etc.)
+        aws_status_raw = status_response.get("status", "")
+        aws_status_lower = aws_status_raw.lower()
+        # Map AWS status values to LiteLLM expected values
+        status_mapping = {
+            "completed": "completed",
+            "failed": "failed",
+            "inprogress": "in_progress",
+            "in_progress": "in_progress",
+        }
+        normalized_status = status_mapping.get(aws_status_lower, aws_status_lower)
+
+        # Get output S3 URI safely
+        output_s3_uri = ""
+        try:
+            output_s3_uri = status_response["outputDataConfig"]["s3OutputDataConfig"]["s3Uri"]
+        except (KeyError, TypeError):
+            pass
+        
+        # Use BedrockBatchesConfig's timestamp parsing method (expects raw AWS status string)
+        from litellm.llms.bedrock.batches.transformation import BedrockBatchesConfig
+        created_at, in_progress_at, completed_at, failed_at, _, _ = BedrockBatchesConfig()._parse_timestamps_and_status(status_response, aws_status_raw)
         result = LiteLLMBatch(
             id=status_response["invocationArn"],
             object="batch",
-            status=status_response["status"],
-            created_at=status_response["submitTime"],
-            in_progress_at=status_response["lastModifiedTime"],
-            completed_at=status_response.get("endTime"),
-            failed_at=(
-                status_response.get("endTime")
-                if status_response["status"] == "failed"
-                else None
-            ),
+            status=normalized_status,
+            created_at=created_at,
+            in_progress_at=in_progress_at,
+            completed_at=completed_at,
+            failed_at=failed_at,
             request_counts=BatchRequestCounts(
                 total=1,
-                completed=1 if status_response["status"] == "completed" else 0,
-                failed=1 if status_response["status"] == "failed" else 0,
+                completed=1 if normalized_status == "completed" else 0,
+                failed=1 if normalized_status == "failed" else 0,
             ),
             metadata=dict(
                 **{
-                    "output_file_id": status_response["outputDataConfig"][
-                        "s3OutputDataConfig"
-                    ]["s3Uri"],
+                    "output_file_id": output_s3_uri,
                     "failure_message": status_response.get("failureMessage") or "",
                     "model_arn": status_response["modelArn"],
                 }
diff --git a/litellm/llms/bedrock/embed/amazon_nova_transformation.py b/litellm/llms/bedrock/embed/amazon_nova_transformation.py
index 97652175a9..ada49d0ff2 100644
--- a/litellm/llms/bedrock/embed/amazon_nova_transformation.py
+++ b/litellm/llms/bedrock/embed/amazon_nova_transformation.py
@@ -83,6 +83,8 @@ class AmazonNovaEmbeddingConfig:
         # Start with inference_params (user-provided params)
         embedding_params = inference_params.copy()
         
+        embedding_params.pop("output_s3_uri", None)
+        
         # Map OpenAI dimensions to embeddingDimension if provided
         if "dimensions" in embedding_params:
             embedding_params["embeddingDimension"] = embedding_params.pop("dimensions")
diff --git a/litellm/llms/bedrock/embed/embedding.py b/litellm/llms/bedrock/embed/embedding.py
index be2bfcd70e..c9eea516eb 100644
--- a/litellm/llms/bedrock/embed/embedding.py
+++ b/litellm/llms/bedrock/embed/embedding.py
@@ -603,22 +603,39 @@ class BedrockEmbedding(BaseAWSLLM):
             aws_region_name=aws_region_name,
         )
 
-        # Construct the status check URL
-        status_url = f"{endpoint_url}/async-invoke/{invocation_arn}"
 
-        # Prepare headers
+        from urllib.parse import quote
+
+        # Encode the ARN for use in URL path
+        encoded_arn = quote(invocation_arn, safe="")
+        status_url = f"{endpoint_url.rstrip('/')}/async-invoke/{encoded_arn}"
+
+        # Prepare headers for GET request
         headers = {"Content-Type": "application/json"}
 
-        # Get AWS signed headers
-        prepped = self.get_request_headers(  # type: ignore
-            credentials=credentials,
-            aws_region_name=aws_region_name,
-            extra_headers=None,
-            endpoint_url=status_url,
-            data="",  # GET request, no body
+        # Use AWSRequest directly for GET requests (get_request_headers hardcodes POST)
+        try:
+            from botocore.auth import SigV4Auth
+            from botocore.awsrequest import AWSRequest
+        except ImportError:
+            raise ImportError(
+                "Missing boto3 to call bedrock. Run 'pip install boto3'."
+            )
+
+        # Create AWSRequest with GET method and encoded URL
+        request = AWSRequest(
+            method="GET",
+            url=status_url,
+            data=None,  # GET request, no body
             headers=headers,
-            api_key=None,
         )
+        
+        # Sign the request - SigV4Auth will create canonical string from request URL
+        sigv4 = SigV4Auth(credentials, "bedrock", aws_region_name)
+        sigv4.add_auth(request)
+        
+        # Prepare the request
+        prepped = request.prepare()
 
         # LOGGING
         if logging_obj is not None: