diff --git a/litellm/proxy/batches_endpoints/endpoints.py b/litellm/proxy/batches_endpoints/endpoints.py
index 1e10d628c1e..dde0591f399 100644
--- a/litellm/proxy/batches_endpoints/endpoints.py
+++ b/litellm/proxy/batches_endpoints/endpoints.py
@@ -374,7 +374,9 @@ async def create_batch(
             )
 
             # Create batch using model credentials
+            _create_batch_data.pop("model", None)  # avoid duplicate kwarg if data has model
             response = await litellm.acreate_batch(
+                model=model_from_file_id,
                 custom_llm_provider=credentials["custom_llm_provider"],
                 **_create_batch_data,
             )