diff --git a/llama-index-integrations/multi_modal_llms/llama-index-multi-modal-llms-nvidia/llama_index/multi_modal_llms/nvidia/base.py b/llama-index-integrations/multi_modal_llms/llama-index-multi-modal-llms-nvidia/llama_index/multi_modal_llms/nvidia/base.py
index 02cea8ed17ed7c6378d1d04dc08e53e04932f23a..e14dfa616f510769c85a3335954641896057452a 100644
--- a/llama-index-integrations/multi_modal_llms/llama-index-multi-modal-llms-nvidia/llama_index/multi_modal_llms/nvidia/base.py
+++ b/llama-index-integrations/multi_modal_llms/llama-index-multi-modal-llms-nvidia/llama_index/multi_modal_llms/nvidia/base.py
@@ -39,6 +39,12 @@ from llama_index.multi_modal_llms.nvidia.utils import (
 import aiohttp
 import json
 
+from llama_index.core.bridge.pydantic import BaseModel
+
+
+class Model(BaseModel):
+    id: str
+
 
 class NVIDIAClient:
     def __init__(
@@ -58,14 +64,14 @@ class NVIDIAClient:
         headers["accept"] = "text/event-stream" if stream else "application/json"
         return headers
 
-    def get_model_details(self) -> List[str]:
+    def get_model_details(self) -> List[Model]:
         """
         Get model details.
 
         Returns:
             List of models
         """
-        return list(NVIDIA_MULTI_MODAL_MODELS.keys())
+        return [Model(id=model) for model in NVIDIA_MULTI_MODAL_MODELS]
 
     def request(
         self,
@@ -198,7 +204,7 @@ class NVIDIAMultiModal(MultiModalLLM):
         )
 
     @property
-    def available_models(self):
+    def available_models(self) -> List[Model]:
         return self._client.get_model_details()
 
     def _get_credential_kwargs(self) -> Dict[str, Any]:
diff --git a/llama-index-integrations/multi_modal_llms/llama-index-multi-modal-llms-nvidia/pyproject.toml b/llama-index-integrations/multi_modal_llms/llama-index-multi-modal-llms-nvidia/pyproject.toml
index 9555020026cb10a9348f5fe873ce6676eaeed519..32d8121d7eaa67d7a6368a74b9de49b72c056353 100644
--- a/llama-index-integrations/multi_modal_llms/llama-index-multi-modal-llms-nvidia/pyproject.toml
+++ b/llama-index-integrations/multi_modal_llms/llama-index-multi-modal-llms-nvidia/pyproject.toml
@@ -27,7 +27,7 @@ license = "MIT"
 name = "llama-index-multi-modal-llms-nvidia"
 packages = [{include = "llama_index/"}]
 readme = "README.md"
-version = "0.1.0"
+version = "0.2.0"
 
 [tool.poetry.dependencies]
 python = ">=3.8.1,<4.0"
diff --git a/llama-index-integrations/multi_modal_llms/llama-index-multi-modal-llms-nvidia/tests/test_available_models.py b/llama-index-integrations/multi_modal_llms/llama-index-multi-modal-llms-nvidia/tests/test_available_models.py
index 829622e8724401a47135a0d12c3edb51e00c94d3..26d14ad038abfb18b44f3c480bb552a2c0683be8 100644
--- a/llama-index-integrations/multi_modal_llms/llama-index-multi-modal-llms-nvidia/tests/test_available_models.py
+++ b/llama-index-integrations/multi_modal_llms/llama-index-multi-modal-llms-nvidia/tests/test_available_models.py
@@ -8,4 +8,4 @@ def test_available_models() -> None:
     models = NVIDIAMultiModal().available_models
     assert models
     assert isinstance(models, list)
-    assert all(isinstance(model, str) for model in models)
+    assert all(isinstance(model.id, str) for model in models)