diff --git a/docs/my-website/docs/proxy/config_settings.md b/docs/my-website/docs/proxy/config_settings.md
index 5a586035bc..e2337205c3 100644
--- a/docs/my-website/docs/proxy/config_settings.md
+++ b/docs/my-website/docs/proxy/config_settings.md
@@ -475,6 +475,8 @@ router_settings:
 | DEFAULT_ALLOWED_FAILS | Maximum failures allowed before cooling down a model. Default is 3
 | DEFAULT_ANTHROPIC_CHAT_MAX_TOKENS | Default maximum tokens for Anthropic chat completions. Default is 4096
 | DEFAULT_BATCH_SIZE | Default batch size for operations. Default is 512
+| DEFAULT_CHUNK_OVERLAP | Default chunk overlap for RAG text splitters. Default is 200
+| DEFAULT_CHUNK_SIZE | Default chunk size for RAG text splitters. Default is 1000
 | DEFAULT_CLIENT_DISCONNECT_CHECK_TIMEOUT_SECONDS | Timeout in seconds for checking client disconnection. Default is 1
 | DEFAULT_COOLDOWN_TIME_SECONDS | Duration in seconds to cooldown a model after failures. Default is 5
 | DEFAULT_CRON_JOB_LOCK_TTL_SECONDS | Time-to-live for cron job locks in seconds. Default is 60 (1 minute)
diff --git a/litellm-proxy-extras/poetry.lock b/litellm-proxy-extras/poetry.lock
index f526fec8da..301d0d2b07 100644
--- a/litellm-proxy-extras/poetry.lock
+++ b/litellm-proxy-extras/poetry.lock
@@ -1,7 +1,7 @@
-# This file is automatically @generated by Poetry 1.8.3 and should not be changed by hand.
+# This file is automatically @generated by Poetry 2.2.0 and should not be changed by hand.
 package = []
 
 [metadata]
-lock-version = "2.0"
+lock-version = "2.1"
 python-versions = ">=3.8.1,<4.0, !=3.9.7"
 content-hash = "2cf39473e67ff0615f0a61c9d2ac9f02b38cc08cbb1bdb893d89bee002646623"
diff --git a/litellm-proxy-extras/pyproject.toml b/litellm-proxy-extras/pyproject.toml
index 78e34ccd01..a22e3ca330 100644
--- a/litellm-proxy-extras/pyproject.toml
+++ b/litellm-proxy-extras/pyproject.toml
@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "litellm-proxy-extras"
-version = "0.4.6"
+version = "0.4.7"
 description = "Additional files for the LiteLLM Proxy. Reduces the size of the main litellm package."
 authors = ["BerriAI"]
 readme = "README.md"
@@ -22,7 +22,7 @@ requires = ["poetry-core"]
 build-backend = "poetry.core.masonry.api"
 
 [tool.commitizen]
-version = "0.4.6"
+version = "0.4.7"
 version_files = [
     "pyproject.toml:version",
     "../requirements.txt:litellm-proxy-extras==",
diff --git a/litellm/__init__.py b/litellm/__init__.py
index ec813cc4bf..890bb2ab7d 100644
--- a/litellm/__init__.py
+++ b/litellm/__init__.py
@@ -533,6 +533,7 @@ featherless_ai_models: Set = set()
 palm_models: Set = set()
 groq_models: Set = set()
 azure_models: Set = set()
+azure_anthropic_models: Set = set()
 azure_text_models: Set = set()
 anyscale_models: Set = set()
 cerebras_models: Set = set()
@@ -737,6 +738,8 @@ def add_known_models():
             groq_models.add(key)
         elif value.get("litellm_provider") == "azure":
             azure_models.add(key)
+        elif value.get("litellm_provider") == "azure_anthropic":
+            azure_anthropic_models.add(key)
         elif value.get("litellm_provider") == "anyscale":
             anyscale_models.add(key)
         elif value.get("litellm_provider") == "cerebras":
@@ -876,6 +879,7 @@ model_list = list(
     | palm_models
     | groq_models
     | azure_models
+    | azure_anthropic_models
     | anyscale_models
     | cerebras_models
     | galadriel_models
@@ -965,6 +969,7 @@ models_by_provider: dict = {
     "palm": palm_models,
     "groq": groq_models,
     "azure": azure_models | azure_text_models,
+    "azure_anthropic": azure_anthropic_models,
     "azure_text": azure_text_models,
     "anyscale": anyscale_models,
     "cerebras": cerebras_models,
diff --git a/litellm/llms/vertex_ai/videos/transformation.py b/litellm/llms/vertex_ai/videos/transformation.py
index 5d73a42286..4cf3e036d3 100644
--- a/litellm/llms/vertex_ai/videos/transformation.py
+++ b/litellm/llms/vertex_ai/videos/transformation.py
@@ -163,7 +163,7 @@ class VertexAIVideoConfig(BaseVideoConfig, VertexBase):
         headers: dict,
         model: str,
         api_key: Optional[str] = None,
-        litellm_params: Optional[GenericLiteLLMParams] = None,
+        litellm_params: Optional[Union[GenericLiteLLMParams, dict]] = None,
     ) -> dict:
         """
         Validate environment and return headers for Vertex AI OCR.
diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json
index 1fe299815c..1b1ebf936a 100644
--- a/litellm/model_prices_and_context_window_backup.json
+++ b/litellm/model_prices_and_context_window_backup.json
@@ -10140,6 +10140,19 @@
         "supports_response_schema": true,
         "supports_tool_choice": true
     },
+    "fireworks_ai/accounts/fireworks/models/glm-4p6": {
+        "input_cost_per_token": 0.55e-06,
+        "output_cost_per_token": 2.19e-06,
+        "litellm_provider": "fireworks_ai",
+        "max_input_tokens": 202800,
+        "max_output_tokens": 202800,
+        "max_tokens": 202800,
+        "mode": "chat",
+        "source": "https://fireworks.ai/pricing",
+        "supports_function_calling": true,
+        "supports_response_schema": true,
+        "supports_tool_choice": true
+    },
     "fireworks_ai/accounts/fireworks/models/gpt-oss-120b": {
         "input_cost_per_token": 1.5e-07,
         "litellm_provider": "fireworks_ai",
diff --git a/litellm/proxy/pass_through_endpoints/llm_provider_handlers/vertex_passthrough_logging_handler.py b/litellm/proxy/pass_through_endpoints/llm_provider_handlers/vertex_passthrough_logging_handler.py
index 407cbd2f3d..b34a6f455c 100644
--- a/litellm/proxy/pass_through_endpoints/llm_provider_handlers/vertex_passthrough_logging_handler.py
+++ b/litellm/proxy/pass_through_endpoints/llm_provider_handlers/vertex_passthrough_logging_handler.py
@@ -89,82 +89,12 @@ class VertexPassthroughLoggingHandler:
             }
 
         elif "predict" in url_route:
-            from litellm.llms.vertex_ai.image_generation.image_generation_handler import (
-                VertexImageGeneration,
+            return VertexPassthroughLoggingHandler._handle_predict_response(
+                httpx_response=httpx_response,
+                logging_obj=logging_obj,
+                url_route=url_route,
+                kwargs=kwargs,
             )
-            from litellm.llms.vertex_ai.multimodal_embeddings.transformation import (
-                VertexAIMultimodalEmbeddingConfig,
-            )
-            from litellm.types.utils import PassthroughCallTypes
-
-            vertex_image_generation_class = VertexImageGeneration()
-
-            model = VertexPassthroughLoggingHandler.extract_model_from_url(url_route)
-
-            _json_response = httpx_response.json()
-
-            litellm_prediction_response: Union[
-                ModelResponse, EmbeddingResponse, ImageResponse
-            ] = ModelResponse()
-            if vertex_image_generation_class.is_image_generation_response(
-                _json_response
-            ):
-                litellm_prediction_response = (
-                    vertex_image_generation_class.process_image_generation_response(
-                        _json_response,
-                        model_response=litellm.ImageResponse(),
-                        model=model,
-                    )
-                )
-
-                logging_obj.call_type = (
-                    PassthroughCallTypes.passthrough_image_generation.value
-                )
-            elif VertexPassthroughLoggingHandler._is_multimodal_embedding_response(
-                json_response=_json_response,
-            ):
-                # Use multimodal embedding transformation
-                vertex_multimodal_config = VertexAIMultimodalEmbeddingConfig()
-                litellm_prediction_response = (
-                    vertex_multimodal_config.transform_embedding_response(
-                        model=model,
-                        raw_response=httpx_response,
-                        model_response=litellm.EmbeddingResponse(),
-                        logging_obj=logging_obj,
-                        api_key="",
-                        request_data={},
-                        optional_params={},
-                        litellm_params={},
-                    )
-                )
-            else:
-                litellm_prediction_response = litellm.vertexAITextEmbeddingConfig.transform_vertex_response_to_openai(
-                    response=_json_response,
-                    model=model,
-                    model_response=litellm.EmbeddingResponse(),
-                )
-            if isinstance(litellm_prediction_response, litellm.EmbeddingResponse):
-                litellm_prediction_response.model = model
-
-            logging_obj.model = model
-            logging_obj.model_call_details["model"] = logging_obj.model
-            logging_obj.model_call_details["custom_llm_provider"] = "vertex_ai"
-            logging_obj.custom_llm_provider = "vertex_ai"
-            response_cost = litellm.completion_cost(
-                completion_response=litellm_prediction_response,
-                model=model,
-                custom_llm_provider="vertex_ai",
-            )
-
-            kwargs["response_cost"] = response_cost
-            kwargs["model"] = model
-            kwargs["custom_llm_provider"] = "vertex_ai"
-            logging_obj.model_call_details["response_cost"] = response_cost
-
-            return {
-                "result": litellm_prediction_response,
-                "kwargs": kwargs,
-            }
         elif "rawPredict" in url_route or "streamRawPredict" in url_route:
             from litellm.llms.vertex_ai.vertex_ai_partner_models import (
                 get_vertex_ai_partner_model_config,
@@ -266,6 +196,91 @@ class VertexPassthroughLoggingHandler:
                 "kwargs": kwargs,
             }
 
+    @staticmethod
+    def _handle_predict_response(
+        httpx_response: httpx.Response,
+        logging_obj: LiteLLMLoggingObj,
+        url_route: str,
+        kwargs: dict,
+    ) -> PassThroughEndpointLoggingTypedDict:
+        """Handle predict endpoint responses (embeddings, image generation)."""
+        from litellm.llms.vertex_ai.image_generation.image_generation_handler import (
+            VertexImageGeneration,
+        )
+        from litellm.llms.vertex_ai.multimodal_embeddings.transformation import (
+            VertexAIMultimodalEmbeddingConfig,
+        )
+        from litellm.types.utils import PassthroughCallTypes
+
+        vertex_image_generation_class = VertexImageGeneration()
+
+        model = VertexPassthroughLoggingHandler.extract_model_from_url(url_route)
+
+        _json_response = httpx_response.json()
+
+        litellm_prediction_response: Union[
+            ModelResponse, EmbeddingResponse, ImageResponse
+        ] = ModelResponse()
+        if vertex_image_generation_class.is_image_generation_response(
+            _json_response
+        ):
+            litellm_prediction_response = (
+                vertex_image_generation_class.process_image_generation_response(
+                    _json_response,
+                    model_response=litellm.ImageResponse(),
+                    model=model,
+                )
+            )
+
+            logging_obj.call_type = (
+                PassthroughCallTypes.passthrough_image_generation.value
+            )
+        elif VertexPassthroughLoggingHandler._is_multimodal_embedding_response(
+            json_response=_json_response,
+        ):
+            # Use multimodal embedding transformation
+            vertex_multimodal_config = VertexAIMultimodalEmbeddingConfig()
+            litellm_prediction_response = (
+                vertex_multimodal_config.transform_embedding_response(
+                    model=model,
+                    raw_response=httpx_response,
+                    model_response=litellm.EmbeddingResponse(),
+                    logging_obj=logging_obj,
+                    api_key="",
+                    request_data={},
+                    optional_params={},
+                    litellm_params={},
+                )
+            )
+        else:
+            litellm_prediction_response = litellm.vertexAITextEmbeddingConfig.transform_vertex_response_to_openai(
+                response=_json_response,
+                model=model,
+                model_response=litellm.EmbeddingResponse(),
+            )
+        if isinstance(litellm_prediction_response, litellm.EmbeddingResponse):
+            litellm_prediction_response.model = model
+
+        logging_obj.model = model
+        logging_obj.model_call_details["model"] = logging_obj.model
+        logging_obj.model_call_details["custom_llm_provider"] = "vertex_ai"
+        logging_obj.custom_llm_provider = "vertex_ai"
+        response_cost = litellm.completion_cost(
+            completion_response=litellm_prediction_response,
+            model=model,
+            custom_llm_provider="vertex_ai",
+        )
+
+        kwargs["response_cost"] = response_cost
+        kwargs["model"] = model
+        kwargs["custom_llm_provider"] = "vertex_ai"
+        logging_obj.model_call_details["response_cost"] = response_cost
+
+        return {
+            "result": litellm_prediction_response,
+            "kwargs": kwargs,
+        }
+
     @staticmethod
     def _handle_logging_vertex_collected_chunks(
         litellm_logging_obj: LiteLLMLoggingObj,
diff --git a/litellm/proxy/public_endpoints/provider_create_fields.json b/litellm/proxy/public_endpoints/provider_create_fields.json
index f5802aac6a..8e08bd8d99 100644
--- a/litellm/proxy/public_endpoints/provider_create_fields.json
+++ b/litellm/proxy/public_endpoints/provider_create_fields.json
@@ -126,6 +126,16 @@
         "options": null,
         "default_value": null
       },
+      {
+        "key": "api_key",
+        "label": "AWS Bedrock API Key",
+        "placeholder": null,
+        "tooltip": "You can provide the API Key for accessing the Bedrock API.",
+        "required": false,
+        "field_type": "password",
+        "options": null,
+        "default_value": null
+      },
       {
         "key": "aws_session_token",
         "label": "AWS Session Token",
diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json
index 1fe299815c..1b1ebf936a 100644
--- a/model_prices_and_context_window.json
+++ b/model_prices_and_context_window.json
@@ -10140,6 +10140,19 @@
         "supports_response_schema": true,
         "supports_tool_choice": true
     },
+    "fireworks_ai/accounts/fireworks/models/glm-4p6": {
+        "input_cost_per_token": 0.55e-06,
+        "output_cost_per_token": 2.19e-06,
+        "litellm_provider": "fireworks_ai",
+        "max_input_tokens": 202800,
+        "max_output_tokens": 202800,
+        "max_tokens": 202800,
+        "mode": "chat",
+        "source": "https://fireworks.ai/pricing",
+        "supports_function_calling": true,
+        "supports_response_schema": true,
+        "supports_tool_choice": true
+    },
     "fireworks_ai/accounts/fireworks/models/gpt-oss-120b": {
         "input_cost_per_token": 1.5e-07,
         "litellm_provider": "fireworks_ai",
diff --git a/poetry.lock b/poetry.lock
index 649462d438..b840e472ef 100644
--- a/poetry.lock
+++ b/poetry.lock
@@ -1,4 +1,4 @@
-# This file is automatically @generated by Poetry 2.1.4 and should not be changed by hand.
+# This file is automatically @generated by Poetry 2.2.0 and should not be changed by hand.
 
 [[package]]
 name = "aiofiles"
@@ -2055,6 +2055,26 @@ requests = ["requests (>=2.20.0,<3.0.0)"]
 testing = ["aiohttp (<3.10.0)", "aiohttp (>=3.6.2,<4.0.0)", "aioresponses", "cryptography (<39.0.0) ; python_version < \"3.8\"", "cryptography (<39.0.0) ; python_version < \"3.8\"", "cryptography (>=38.0.3)", "cryptography (>=38.0.3)", "flask", "freezegun", "grpcio", "mock", "oauth2client", "packaging", "pyjwt (>=2.0)", "pyopenssl (<24.3.0)", "pyopenssl (>=20.0.0)", "pytest", "pytest-asyncio", "pytest-cov", "pytest-localserver", "pyu2f (>=0.1.5)", "requests (>=2.20.0,<3.0.0)", "responses", "urllib3"]
 urllib3 = ["packaging", "urllib3"]
 
+[[package]]
+name = "google-cloud-iam"
+version = "2.19.1"
+description = "Google Cloud Iam API client library"
+optional = true
+python-versions = ">=3.7"
+groups = ["main"]
+markers = "python_version >= \"3.14\" and extra == \"extra-proxy\""
+files = [
+    {file = "google_cloud_iam-2.19.1-py3-none-any.whl", hash = "sha256:11b08b86d82510021f9dd9f0beb5a08219e070deab09e28d4c0ce49f8c70997d"},
+    {file = "google_cloud_iam-2.19.1.tar.gz", hash = "sha256:f059c369ad98af6be3401f0f5d087775d775fb96833be1e9ab8048c422fb1bf4"},
+]
+
+[package.dependencies]
+google-api-core = {version = ">=1.34.1,<2.0.dev0 || >=2.11.dev0,<3.0.0", extras = ["grpc"]}
+google-auth = ">=2.14.1,<2.24.0 || >2.24.0,<2.25.0 || >2.25.0,<3.0.0"
+grpc-google-iam-v1 = ">=0.12.4,<1.0.0"
+proto-plus = {version = ">=1.25.0,<2.0.0", markers = "python_version >= \"3.13\""}
+protobuf = ">=3.20.2,<4.21.0 || >4.21.0,<4.21.1 || >4.21.1,<4.21.2 || >4.21.2,<4.21.3 || >4.21.3,<4.21.4 || >4.21.4,<4.21.5 || >4.21.5,<7.0.0"
+
 [[package]]
 name = "google-cloud-iam"
 version = "2.20.0"
@@ -2062,7 +2082,7 @@ description = "Google Cloud Iam API client library"
 optional = true
 python-versions = ">=3.7"
 groups = ["main"]
-markers = "extra == \"extra-proxy\""
+markers = "extra == \"extra-proxy\" and python_version < \"3.14\""
 files = [
     {file = "google_cloud_iam-2.20.0-py3-none-any.whl", hash = "sha256:643fcf6db3100772f222c7173bc1af15541a05ec1c43785191e835146ed150b8"},
     {file = "google_cloud_iam-2.20.0.tar.gz", hash = "sha256:06568ed8313f59fac46d21a5aae4c54eb1dda9f6bcecf2736c58ab1065dc9173"},
@@ -2072,10 +2092,7 @@ files = [
 google-api-core = {version = ">=1.34.1,<2.0.dev0 || >=2.11.dev0,<3.0.0", extras = ["grpc"]}
 google-auth = ">=2.14.1,<2.24.0 || >2.24.0,<2.25.0 || >2.25.0,<3.0.0"
 grpc-google-iam-v1 = ">=0.12.4,<1.0.0"
-grpcio = [
-    {version = ">=1.33.2,<2.0.0"},
-    {version = ">=1.75.1,<2.0.0", markers = "python_version >= \"3.14\""},
-]
+grpcio = ">=1.33.2,<2.0.0"
 proto-plus = [
     {version = ">=1.22.3,<2.0.0"},
     {version = ">=1.25.0,<2.0.0", markers = "python_version >= \"3.13\""},
@@ -2191,6 +2208,8 @@ files = [
     {file = "greenlet-3.2.4-cp310-cp310-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:c2ca18a03a8cfb5b25bc1cbe20f3d9a4c80d8c3b13ba3df49ac3961af0b1018d"},
     {file = "greenlet-3.2.4-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:9fe0a28a7b952a21e2c062cd5756d34354117796c6d9215a87f55e38d15402c5"},
     {file = "greenlet-3.2.4-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:8854167e06950ca75b898b104b63cc646573aa5fef1353d4508ecdd1ee76254f"},
+    {file = "greenlet-3.2.4-cp310-cp310-musllinux_1_2_aarch64.whl", hash = "sha256:f47617f698838ba98f4ff4189aef02e7343952df3a615f847bb575c3feb177a7"},
+    {file = "greenlet-3.2.4-cp310-cp310-musllinux_1_2_x86_64.whl", hash = "sha256:af41be48a4f60429d5cad9d22175217805098a9ef7c40bfef44f7669fb9d74d8"},
     {file = "greenlet-3.2.4-cp310-cp310-win_amd64.whl", hash = "sha256:73f49b5368b5359d04e18d15828eecc1806033db5233397748f4ca813ff1056c"},
     {file = "greenlet-3.2.4-cp311-cp311-macosx_11_0_universal2.whl", hash = "sha256:96378df1de302bc38e99c3a9aa311967b7dc80ced1dcc6f171e99842987882a2"},
     {file = "greenlet-3.2.4-cp311-cp311-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:1ee8fae0519a337f2329cb78bd7a8e128ec0f881073d43f023c7b8d4831d5246"},
@@ -2200,6 +2219,8 @@ files = [
     {file = "greenlet-3.2.4-cp311-cp311-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:2523e5246274f54fdadbce8494458a2ebdcdbc7b802318466ac5606d3cded1f8"},
     {file = "greenlet-3.2.4-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:1987de92fec508535687fb807a5cea1560f6196285a4cde35c100b8cd632cc52"},
     {file = "greenlet-3.2.4-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:55e9c5affaa6775e2c6b67659f3a71684de4c549b3dd9afca3bc773533d284fa"},
+    {file = "greenlet-3.2.4-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:c9c6de1940a7d828635fbd254d69db79e54619f165ee7ce32fda763a9cb6a58c"},
+    {file = "greenlet-3.2.4-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:03c5136e7be905045160b1b9fdca93dd6727b180feeafda6818e6496434ed8c5"},
     {file = "greenlet-3.2.4-cp311-cp311-win_amd64.whl", hash = "sha256:9c40adce87eaa9ddb593ccb0fa6a07caf34015a29bf8d344811665b573138db9"},
     {file = "greenlet-3.2.4-cp312-cp312-macosx_11_0_universal2.whl", hash = "sha256:3b67ca49f54cede0186854a008109d6ee71f66bd57bb36abd6d0a0267b540cdd"},
     {file = "greenlet-3.2.4-cp312-cp312-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:ddf9164e7a5b08e9d22511526865780a576f19ddd00d62f8a665949327fde8bb"},
@@ -2209,6 +2230,8 @@ files = [
     {file = "greenlet-3.2.4-cp312-cp312-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:3b3812d8d0c9579967815af437d96623f45c0f2ae5f04e366de62a12d83a8fb0"},
     {file = "greenlet-3.2.4-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:abbf57b5a870d30c4675928c37278493044d7c14378350b3aa5d484fa65575f0"},
     {file = "greenlet-3.2.4-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:20fb936b4652b6e307b8f347665e2c615540d4b42b3b4c8a321d8286da7e520f"},
+    {file = "greenlet-3.2.4-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:ee7a6ec486883397d70eec05059353b8e83eca9168b9f3f9a361971e77e0bcd0"},
+    {file = "greenlet-3.2.4-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:326d234cbf337c9c3def0676412eb7040a35a768efc92504b947b3e9cfc7543d"},
     {file = "greenlet-3.2.4-cp312-cp312-win_amd64.whl", hash = "sha256:a7d4e128405eea3814a12cc2605e0e6aedb4035bf32697f72deca74de4105e02"},
     {file = "greenlet-3.2.4-cp313-cp313-macosx_11_0_universal2.whl", hash = "sha256:1a921e542453fe531144e91e1feedf12e07351b1cf6c9e8a3325ea600a715a31"},
     {file = "greenlet-3.2.4-cp313-cp313-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:cd3c8e693bff0fff6ba55f140bf390fa92c994083f838fece0f63be121334945"},
@@ -2218,6 +2241,8 @@ files = [
     {file = "greenlet-3.2.4-cp313-cp313-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:23768528f2911bcd7e475210822ffb5254ed10d71f4028387e5a99b4c6699671"},
     {file = "greenlet-3.2.4-cp313-cp313-musllinux_1_1_aarch64.whl", hash = "sha256:00fadb3fedccc447f517ee0d3fd8fe49eae949e1cd0f6a611818f4f6fb7dc83b"},
     {file = "greenlet-3.2.4-cp313-cp313-musllinux_1_1_x86_64.whl", hash = "sha256:d25c5091190f2dc0eaa3f950252122edbbadbb682aa7b1ef2f8af0f8c0afefae"},
+    {file = "greenlet-3.2.4-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:6e343822feb58ac4d0a1211bd9399de2b3a04963ddeec21530fc426cc121f19b"},
+    {file = "greenlet-3.2.4-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:ca7f6f1f2649b89ce02f6f229d7c19f680a6238af656f61e0115b24857917929"},
     {file = "greenlet-3.2.4-cp313-cp313-win_amd64.whl", hash = "sha256:554b03b6e73aaabec3745364d6239e9e012d64c68ccd0b8430c64ccc14939a8b"},
     {file = "greenlet-3.2.4-cp314-cp314-macosx_11_0_universal2.whl", hash = "sha256:49a30d5fda2507ae77be16479bdb62a660fa51b1eb4928b524975b3bde77b3c0"},
     {file = "greenlet-3.2.4-cp314-cp314-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:299fd615cd8fc86267b47597123e3f43ad79c9d8a22bebdce535e53550763e2f"},
@@ -2225,6 +2250,8 @@ files = [
     {file = "greenlet-3.2.4-cp314-cp314-manylinux2014_s390x.manylinux_2_17_s390x.whl", hash = "sha256:b4a1870c51720687af7fa3e7cda6d08d801dae660f75a76f3845b642b4da6ee1"},
     {file = "greenlet-3.2.4-cp314-cp314-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:061dc4cf2c34852b052a8620d40f36324554bc192be474b9e9770e8c042fd735"},
     {file = "greenlet-3.2.4-cp314-cp314-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:44358b9bf66c8576a9f57a590d5f5d6e72fa4228b763d0e43fee6d3b06d3a337"},
+    {file = "greenlet-3.2.4-cp314-cp314-musllinux_1_2_aarch64.whl", hash = "sha256:2917bdf657f5859fbf3386b12d68ede4cf1f04c90c3a6bc1f013dd68a22e2269"},
+    {file = "greenlet-3.2.4-cp314-cp314-musllinux_1_2_x86_64.whl", hash = "sha256:015d48959d4add5d6c9f6c5210ee3803a830dce46356e3bc326d6776bde54681"},
     {file = "greenlet-3.2.4-cp314-cp314-win_amd64.whl", hash = "sha256:e37ab26028f12dbb0ff65f29a8d3d44a765c61e729647bf2ddfbbed621726f01"},
     {file = "greenlet-3.2.4-cp39-cp39-macosx_11_0_universal2.whl", hash = "sha256:b6a7c19cf0d2742d0809a4c05975db036fdff50cd294a93632d6a310bf9ac02c"},
     {file = "greenlet-3.2.4-cp39-cp39-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:27890167f55d2387576d1f41d9487ef171849ea0359ce1510ca6e06c8bece11d"},
@@ -2234,6 +2261,8 @@ files = [
     {file = "greenlet-3.2.4-cp39-cp39-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:c9913f1a30e4526f432991f89ae263459b1c64d1608c0d22a5c79c287b3c70df"},
     {file = "greenlet-3.2.4-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:b90654e092f928f110e0007f572007c9727b5265f7632c2fa7415b4689351594"},
     {file = "greenlet-3.2.4-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:81701fd84f26330f0d5f4944d4e92e61afe6319dcd9775e39396e39d7c3e5f98"},
+    {file = "greenlet-3.2.4-cp39-cp39-musllinux_1_2_aarch64.whl", hash = "sha256:28a3c6b7cd72a96f61b0e4b2a36f681025b60ae4779cc73c1535eb5f29560b10"},
+    {file = "greenlet-3.2.4-cp39-cp39-musllinux_1_2_x86_64.whl", hash = "sha256:52206cd642670b0b320a1fd1cbfd95bca0e043179c1d8a045f2c6109dfe973be"},
     {file = "greenlet-3.2.4-cp39-cp39-win32.whl", hash = "sha256:65458b409c1ed459ea899e939f0e1cdb14f58dbc803f2f93c5eab5694d32671b"},
     {file = "greenlet-3.2.4-cp39-cp39-win_amd64.whl", hash = "sha256:d2e685ade4dafd447ede19c31277a224a239a0a1a4eca4e6390efedf20260cfb"},
     {file = "greenlet-3.2.4.tar.gz", hash = "sha256:0dca0d95ff849f9a364385f36ab49f50065d76964944638be9691e1832e9f86d"},
@@ -2263,81 +2292,71 @@ protobuf = ">=3.20.2,<4.21.1 || >4.21.1,<4.21.2 || >4.21.2,<4.21.3 || >4.21.3,<4
 
 [[package]]
 name = "grpcio"
-version = "1.76.0"
+version = "1.67.1"
 description = "HTTP/2-based RPC framework"
 optional = false
-python-versions = ">=3.9"
+python-versions = ">=3.8"
 groups = ["main", "dev", "proxy-dev"]
 files = [
-    {file = "grpcio-1.76.0-cp310-cp310-linux_armv7l.whl", hash = "sha256:65a20de41e85648e00305c1bb09a3598f840422e522277641145a32d42dcefcc"},
-    {file = "grpcio-1.76.0-cp310-cp310-macosx_11_0_universal2.whl", hash = "sha256:40ad3afe81676fd9ec6d9d406eda00933f218038433980aa19d401490e46ecde"},
-    {file = "grpcio-1.76.0-cp310-cp310-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:035d90bc79eaa4bed83f524331d55e35820725c9fbb00ffa1904d5550ed7ede3"},
-    {file = "grpcio-1.76.0-cp310-cp310-manylinux2014_i686.manylinux_2_17_i686.whl", hash = "sha256:4215d3a102bd95e2e11b5395c78562967959824156af11fa93d18fdd18050990"},
-    {file = "grpcio-1.76.0-cp310-cp310-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:49ce47231818806067aea3324d4bf13825b658ad662d3b25fada0bdad9b8a6af"},
-    {file = "grpcio-1.76.0-cp310-cp310-musllinux_1_2_aarch64.whl", hash = "sha256:8cc3309d8e08fd79089e13ed4819d0af72aa935dd8f435a195fd152796752ff2"},
-    {file = "grpcio-1.76.0-cp310-cp310-musllinux_1_2_i686.whl", hash = "sha256:971fd5a1d6e62e00d945423a567e42eb1fa678ba89072832185ca836a94daaa6"},
-    {file = "grpcio-1.76.0-cp310-cp310-musllinux_1_2_x86_64.whl", hash = "sha256:9d9adda641db7207e800a7f089068f6f645959f2df27e870ee81d44701dd9db3"},
-    {file = "grpcio-1.76.0-cp310-cp310-win32.whl", hash = "sha256:063065249d9e7e0782d03d2bca50787f53bd0fb89a67de9a7b521c4a01f1989b"},
-    {file = "grpcio-1.76.0-cp310-cp310-win_amd64.whl", hash = "sha256:a6ae758eb08088d36812dd5d9af7a9859c05b1e0f714470ea243694b49278e7b"},
-    {file = "grpcio-1.76.0-cp311-cp311-linux_armv7l.whl", hash = "sha256:2e1743fbd7f5fa713a1b0a8ac8ebabf0ec980b5d8809ec358d488e273b9cf02a"},
-    {file = "grpcio-1.76.0-cp311-cp311-macosx_11_0_universal2.whl", hash = "sha256:a8c2cf1209497cf659a667d7dea88985e834c24b7c3b605e6254cbb5076d985c"},
-    {file = "grpcio-1.76.0-cp311-cp311-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:08caea849a9d3c71a542827d6df9d5a69067b0a1efbea8a855633ff5d9571465"},
-    {file = "grpcio-1.76.0-cp311-cp311-manylinux2014_i686.manylinux_2_17_i686.whl", hash = "sha256:f0e34c2079d47ae9f6188211db9e777c619a21d4faba6977774e8fa43b085e48"},
-    {file = "grpcio-1.76.0-cp311-cp311-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:8843114c0cfce61b40ad48df65abcfc00d4dba82eae8718fab5352390848c5da"},
-    {file = "grpcio-1.76.0-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:8eddfb4d203a237da6f3cc8a540dad0517d274b5a1e9e636fd8d2c79b5c1d397"},
-    {file = "grpcio-1.76.0-cp311-cp311-musllinux_1_2_i686.whl", hash = "sha256:32483fe2aab2c3794101c2a159070584e5db11d0aa091b2c0ea9c4fc43d0d749"},
-    {file = "grpcio-1.76.0-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:dcfe41187da8992c5f40aa8c5ec086fa3672834d2be57a32384c08d5a05b4c00"},
-    {file = "grpcio-1.76.0-cp311-cp311-win32.whl", hash = "sha256:2107b0c024d1b35f4083f11245c0e23846ae64d02f40b2b226684840260ed054"},
-    {file = "grpcio-1.76.0-cp311-cp311-win_amd64.whl", hash = "sha256:522175aba7af9113c48ec10cc471b9b9bd4f6ceb36aeb4544a8e2c80ed9d252d"},
-    {file = "grpcio-1.76.0-cp312-cp312-linux_armv7l.whl", hash = "sha256:81fd9652b37b36f16138611c7e884eb82e0cec137c40d3ef7c3f9b3ed00f6ed8"},
-    {file = "grpcio-1.76.0-cp312-cp312-macosx_11_0_universal2.whl", hash = "sha256:04bbe1bfe3a68bbfd4e52402ab7d4eb59d72d02647ae2042204326cf4bbad280"},
-    {file = "grpcio-1.76.0-cp312-cp312-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:d388087771c837cdb6515539f43b9d4bf0b0f23593a24054ac16f7a960be16f4"},
-    {file = "grpcio-1.76.0-cp312-cp312-manylinux2014_i686.manylinux_2_17_i686.whl", hash = "sha256:9f8f757bebaaea112c00dba718fc0d3260052ce714e25804a03f93f5d1c6cc11"},
-    {file = "grpcio-1.76.0-cp312-cp312-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:980a846182ce88c4f2f7e2c22c56aefd515daeb36149d1c897f83cf57999e0b6"},
-    {file = "grpcio-1.76.0-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:f92f88e6c033db65a5ae3d97905c8fea9c725b63e28d5a75cb73b49bda5024d8"},
-    {file = "grpcio-1.76.0-cp312-cp312-musllinux_1_2_i686.whl", hash = "sha256:4baf3cbe2f0be3289eb68ac8ae771156971848bb8aaff60bad42005539431980"},
-    {file = "grpcio-1.76.0-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:615ba64c208aaceb5ec83bfdce7728b80bfeb8be97562944836a7a0a9647d882"},
-    {file = "grpcio-1.76.0-cp312-cp312-win32.whl", hash = "sha256:45d59a649a82df5718fd9527ce775fd66d1af35e6d31abdcdc906a49c6822958"},
-    {file = "grpcio-1.76.0-cp312-cp312-win_amd64.whl", hash = "sha256:c088e7a90b6017307f423efbb9d1ba97a22aa2170876223f9709e9d1de0b5347"},
-    {file = "grpcio-1.76.0-cp313-cp313-linux_armv7l.whl", hash = "sha256:26ef06c73eb53267c2b319f43e6634c7556ea37672029241a056629af27c10e2"},
-    {file = "grpcio-1.76.0-cp313-cp313-macosx_11_0_universal2.whl", hash = "sha256:45e0111e73f43f735d70786557dc38141185072d7ff8dc1829d6a77ac1471468"},
-    {file = "grpcio-1.76.0-cp313-cp313-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:83d57312a58dcfe2a3a0f9d1389b299438909a02db60e2f2ea2ae2d8034909d3"},
-    {file = "grpcio-1.76.0-cp313-cp313-manylinux2014_i686.manylinux_2_17_i686.whl", hash = "sha256:3e2a27c89eb9ac3d81ec8835e12414d73536c6e620355d65102503064a4ed6eb"},
-    {file = "grpcio-1.76.0-cp313-cp313-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:61f69297cba3950a524f61c7c8ee12e55c486cb5f7db47ff9dcee33da6f0d3ae"},
-    {file = "grpcio-1.76.0-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:6a15c17af8839b6801d554263c546c69c4d7718ad4321e3166175b37eaacca77"},
-    {file = "grpcio-1.76.0-cp313-cp313-musllinux_1_2_i686.whl", hash = "sha256:25a18e9810fbc7e7f03ec2516addc116a957f8cbb8cbc95ccc80faa072743d03"},
-    {file = "grpcio-1.76.0-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:931091142fd8cc14edccc0845a79248bc155425eee9a98b2db2ea4f00a235a42"},
-    {file = "grpcio-1.76.0-cp313-cp313-win32.whl", hash = "sha256:5e8571632780e08526f118f74170ad8d50fb0a48c23a746bef2a6ebade3abd6f"},
-    {file = "grpcio-1.76.0-cp313-cp313-win_amd64.whl", hash = "sha256:f9f7bd5faab55f47231ad8dba7787866b69f5e93bc306e3915606779bbfb4ba8"},
-    {file = "grpcio-1.76.0-cp314-cp314-linux_armv7l.whl", hash = "sha256:ff8a59ea85a1f2191a0ffcc61298c571bc566332f82e5f5be1b83c9d8e668a62"},
-    {file = "grpcio-1.76.0-cp314-cp314-macosx_11_0_universal2.whl", hash = "sha256:06c3d6b076e7b593905d04fdba6a0525711b3466f43b3400266f04ff735de0cd"},
-    {file = "grpcio-1.76.0-cp314-cp314-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:fd5ef5932f6475c436c4a55e4336ebbe47bd3272be04964a03d316bbf4afbcbc"},
-    {file = "grpcio-1.76.0-cp314-cp314-manylinux2014_i686.manylinux_2_17_i686.whl", hash = "sha256:b331680e46239e090f5b3cead313cc772f6caa7d0fc8de349337563125361a4a"},
-    {file = "grpcio-1.76.0-cp314-cp314-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:2229ae655ec4e8999599469559e97630185fdd53ae1e8997d147b7c9b2b72cba"},
-    {file = "grpcio-1.76.0-cp314-cp314-musllinux_1_2_aarch64.whl", hash = "sha256:490fa6d203992c47c7b9e4a9d39003a0c2bcc1c9aa3c058730884bbbb0ee9f09"},
-    {file = "grpcio-1.76.0-cp314-cp314-musllinux_1_2_i686.whl", hash = "sha256:479496325ce554792dba6548fae3df31a72cef7bad71ca2e12b0e58f9b336bfc"},
-    {file = "grpcio-1.76.0-cp314-cp314-musllinux_1_2_x86_64.whl", hash = "sha256:1c9b93f79f48b03ada57ea24725d83a30284a012ec27eab2cf7e50a550cbbbcc"},
-    {file = "grpcio-1.76.0-cp314-cp314-win32.whl", hash = "sha256:747fa73efa9b8b1488a95d0ba1039c8e2dca0f741612d80415b1e1c560febf4e"},
-    {file = "grpcio-1.76.0-cp314-cp314-win_amd64.whl", hash = "sha256:922fa70ba549fce362d2e2871ab542082d66e2aaf0c19480ea453905b01f384e"},
-    {file = "grpcio-1.76.0-cp39-cp39-linux_armv7l.whl", hash = "sha256:8ebe63ee5f8fa4296b1b8cfc743f870d10e902ca18afc65c68cf46fd39bb0783"},
-    {file = "grpcio-1.76.0-cp39-cp39-macosx_11_0_universal2.whl", hash = "sha256:3bf0f392c0b806905ed174dcd8bdd5e418a40d5567a05615a030a5aeddea692d"},
-    {file = "grpcio-1.76.0-cp39-cp39-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:0b7604868b38c1bfd5cf72d768aedd7db41d78cb6a4a18585e33fb0f9f2363fd"},
-    {file = "grpcio-1.76.0-cp39-cp39-manylinux2014_i686.manylinux_2_17_i686.whl", hash = "sha256:e6d1db20594d9daba22f90da738b1a0441a7427552cc6e2e3d1297aeddc00378"},
-    {file = "grpcio-1.76.0-cp39-cp39-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:d099566accf23d21037f18a2a63d323075bebace807742e4b0ac210971d4dd70"},
-    {file = "grpcio-1.76.0-cp39-cp39-musllinux_1_2_aarch64.whl", hash = "sha256:ebea5cc3aa8ea72e04df9913492f9a96d9348db876f9dda3ad729cfedf7ac416"},
-    {file = "grpcio-1.76.0-cp39-cp39-musllinux_1_2_i686.whl", hash = "sha256:0c37db8606c258e2ee0c56b78c62fc9dee0e901b5dbdcf816c2dd4ad652b8b0c"},
-    {file = "grpcio-1.76.0-cp39-cp39-musllinux_1_2_x86_64.whl", hash = "sha256:ebebf83299b0cb1721a8859ea98f3a77811e35dce7609c5c963b9ad90728f886"},
-    {file = "grpcio-1.76.0-cp39-cp39-win32.whl", hash = "sha256:0aaa82d0813fd4c8e589fac9b65d7dd88702555f702fb10417f96e2a2a6d4c0f"},
-    {file = "grpcio-1.76.0-cp39-cp39-win_amd64.whl", hash = "sha256:acab0277c40eff7143c2323190ea57b9ee5fd353d8190ee9652369fae735668a"},
-    {file = "grpcio-1.76.0.tar.gz", hash = "sha256:7be78388d6da1a25c0d5ec506523db58b18be22d9c37d8d3a32c08be4987bd73"},
+    {file = "grpcio-1.67.1-cp310-cp310-linux_armv7l.whl", hash = "sha256:8b0341d66a57f8a3119b77ab32207072be60c9bf79760fa609c5609f2deb1f3f"},
+    {file = "grpcio-1.67.1-cp310-cp310-macosx_12_0_universal2.whl", hash = "sha256:f5a27dddefe0e2357d3e617b9079b4bfdc91341a91565111a21ed6ebbc51b22d"},
+    {file = "grpcio-1.67.1-cp310-cp310-manylinux_2_17_aarch64.whl", hash = "sha256:43112046864317498a33bdc4797ae6a268c36345a910de9b9c17159d8346602f"},
+    {file = "grpcio-1.67.1-cp310-cp310-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:c9b929f13677b10f63124c1a410994a401cdd85214ad83ab67cc077fc7e480f0"},
+    {file = "grpcio-1.67.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:e7d1797a8a3845437d327145959a2c0c47c05947c9eef5ff1a4c80e499dcc6fa"},
+    {file = "grpcio-1.67.1-cp310-cp310-musllinux_1_1_i686.whl", hash = "sha256:0489063974d1452436139501bf6b180f63d4977223ee87488fe36858c5725292"},
+    {file = "grpcio-1.67.1-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:9fd042de4a82e3e7aca44008ee2fb5da01b3e5adb316348c21980f7f58adc311"},
+    {file = "grpcio-1.67.1-cp310-cp310-win32.whl", hash = "sha256:638354e698fd0c6c76b04540a850bf1db27b4d2515a19fcd5cf645c48d3eb1ed"},
+    {file = "grpcio-1.67.1-cp310-cp310-win_amd64.whl", hash = "sha256:608d87d1bdabf9e2868b12338cd38a79969eaf920c89d698ead08f48de9c0f9e"},
+    {file = "grpcio-1.67.1-cp311-cp311-linux_armv7l.whl", hash = "sha256:7818c0454027ae3384235a65210bbf5464bd715450e30a3d40385453a85a70cb"},
+    {file = "grpcio-1.67.1-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:ea33986b70f83844cd00814cee4451055cd8cab36f00ac64a31f5bb09b31919e"},
+    {file = "grpcio-1.67.1-cp311-cp311-manylinux_2_17_aarch64.whl", hash = "sha256:c7a01337407dd89005527623a4a72c5c8e2894d22bead0895306b23c6695698f"},
+    {file = "grpcio-1.67.1-cp311-cp311-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:80b866f73224b0634f4312a4674c1be21b2b4afa73cb20953cbbb73a6b36c3cc"},
+    {file = "grpcio-1.67.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f9fff78ba10d4250bfc07a01bd6254a6d87dc67f9627adece85c0b2ed754fa96"},
+    {file = "grpcio-1.67.1-cp311-cp311-musllinux_1_1_i686.whl", hash = "sha256:8a23cbcc5bb11ea7dc6163078be36c065db68d915c24f5faa4f872c573bb400f"},
+    {file = "grpcio-1.67.1-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:1a65b503d008f066e994f34f456e0647e5ceb34cfcec5ad180b1b44020ad4970"},
+    {file = "grpcio-1.67.1-cp311-cp311-win32.whl", hash = "sha256:e29ca27bec8e163dca0c98084040edec3bc49afd10f18b412f483cc68c712744"},
+    {file = "grpcio-1.67.1-cp311-cp311-win_amd64.whl", hash = "sha256:786a5b18544622bfb1e25cc08402bd44ea83edfb04b93798d85dca4d1a0b5be5"},
+    {file = "grpcio-1.67.1-cp312-cp312-linux_armv7l.whl", hash = "sha256:267d1745894200e4c604958da5f856da6293f063327cb049a51fe67348e4f953"},
+    {file = "grpcio-1.67.1-cp312-cp312-macosx_10_9_universal2.whl", hash = "sha256:85f69fdc1d28ce7cff8de3f9c67db2b0ca9ba4449644488c1e0303c146135ddb"},
+    {file = "grpcio-1.67.1-cp312-cp312-manylinux_2_17_aarch64.whl", hash = "sha256:f26b0b547eb8d00e195274cdfc63ce64c8fc2d3e2d00b12bf468ece41a0423a0"},
+    {file = "grpcio-1.67.1-cp312-cp312-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:4422581cdc628f77302270ff839a44f4c24fdc57887dc2a45b7e53d8fc2376af"},
+    {file = "grpcio-1.67.1-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:1d7616d2ded471231c701489190379e0c311ee0a6c756f3c03e6a62b95a7146e"},
+    {file = "grpcio-1.67.1-cp312-cp312-musllinux_1_1_i686.whl", hash = "sha256:8a00efecde9d6fcc3ab00c13f816313c040a28450e5e25739c24f432fc6d3c75"},
+    {file = "grpcio-1.67.1-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:699e964923b70f3101393710793289e42845791ea07565654ada0969522d0a38"},
+    {file = "grpcio-1.67.1-cp312-cp312-win32.whl", hash = "sha256:4e7b904484a634a0fff132958dabdb10d63e0927398273917da3ee103e8d1f78"},
+    {file = "grpcio-1.67.1-cp312-cp312-win_amd64.whl", hash = "sha256:5721e66a594a6c4204458004852719b38f3d5522082be9061d6510b455c90afc"},
+    {file = "grpcio-1.67.1-cp313-cp313-linux_armv7l.whl", hash = "sha256:aa0162e56fd10a5547fac8774c4899fc3e18c1aa4a4759d0ce2cd00d3696ea6b"},
+    {file = "grpcio-1.67.1-cp313-cp313-macosx_10_13_universal2.whl", hash = "sha256:beee96c8c0b1a75d556fe57b92b58b4347c77a65781ee2ac749d550f2a365dc1"},
+    {file = "grpcio-1.67.1-cp313-cp313-manylinux_2_17_aarch64.whl", hash = "sha256:a93deda571a1bf94ec1f6fcda2872dad3ae538700d94dc283c672a3b508ba3af"},
+    {file = "grpcio-1.67.1-cp313-cp313-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:0e6f255980afef598a9e64a24efce87b625e3e3c80a45162d111a461a9f92955"},
+    {file = "grpcio-1.67.1-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:9e838cad2176ebd5d4a8bb03955138d6589ce9e2ce5d51c3ada34396dbd2dba8"},
+    {file = "grpcio-1.67.1-cp313-cp313-musllinux_1_1_i686.whl", hash = "sha256:a6703916c43b1d468d0756c8077b12017a9fcb6a1ef13faf49e67d20d7ebda62"},
+    {file = "grpcio-1.67.1-cp313-cp313-musllinux_1_1_x86_64.whl", hash = "sha256:917e8d8994eed1d86b907ba2a61b9f0aef27a2155bca6cbb322430fc7135b7bb"},
+    {file = "grpcio-1.67.1-cp313-cp313-win32.whl", hash = "sha256:e279330bef1744040db8fc432becc8a727b84f456ab62b744d3fdb83f327e121"},
+    {file = "grpcio-1.67.1-cp313-cp313-win_amd64.whl", hash = "sha256:fa0c739ad8b1996bd24823950e3cb5152ae91fca1c09cc791190bf1627ffefba"},
+    {file = "grpcio-1.67.1-cp38-cp38-linux_armv7l.whl", hash = "sha256:178f5db771c4f9a9facb2ab37a434c46cb9be1a75e820f187ee3d1e7805c4f65"},
+    {file = "grpcio-1.67.1-cp38-cp38-macosx_10_9_universal2.whl", hash = "sha256:0f3e49c738396e93b7ba9016e153eb09e0778e776df6090c1b8c91877cc1c426"},
+    {file = "grpcio-1.67.1-cp38-cp38-manylinux_2_17_aarch64.whl", hash = "sha256:24e8a26dbfc5274d7474c27759b54486b8de23c709d76695237515bc8b5baeab"},
+    {file = "grpcio-1.67.1-cp38-cp38-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:3b6c16489326d79ead41689c4b84bc40d522c9a7617219f4ad94bc7f448c5085"},
+    {file = "grpcio-1.67.1-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:60e6a4dcf5af7bbc36fd9f81c9f372e8ae580870a9e4b6eafe948cd334b81cf3"},
+    {file = "grpcio-1.67.1-cp38-cp38-musllinux_1_1_i686.whl", hash = "sha256:95b5f2b857856ed78d72da93cd7d09b6db8ef30102e5e7fe0961fe4d9f7d48e8"},
+    {file = "grpcio-1.67.1-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:b49359977c6ec9f5d0573ea4e0071ad278ef905aa74e420acc73fd28ce39e9ce"},
+    {file = "grpcio-1.67.1-cp38-cp38-win32.whl", hash = "sha256:f5b76ff64aaac53fede0cc93abf57894ab2a7362986ba22243d06218b93efe46"},
+    {file = "grpcio-1.67.1-cp38-cp38-win_amd64.whl", hash = "sha256:804c6457c3cd3ec04fe6006c739579b8d35c86ae3298ffca8de57b493524b771"},
+    {file = "grpcio-1.67.1-cp39-cp39-linux_armv7l.whl", hash = "sha256:a25bdea92b13ff4d7790962190bf6bf5c4639876e01c0f3dda70fc2769616335"},
+    {file = "grpcio-1.67.1-cp39-cp39-macosx_10_9_universal2.whl", hash = "sha256:cdc491ae35a13535fd9196acb5afe1af37c8237df2e54427be3eecda3653127e"},
+    {file = "grpcio-1.67.1-cp39-cp39-manylinux_2_17_aarch64.whl", hash = "sha256:85f862069b86a305497e74d0dc43c02de3d1d184fc2c180993aa8aa86fbd19b8"},
+    {file = "grpcio-1.67.1-cp39-cp39-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:ec74ef02010186185de82cc594058a3ccd8d86821842bbac9873fd4a2cf8be8d"},
+    {file = "grpcio-1.67.1-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:01f616a964e540638af5130469451cf580ba8c7329f45ca998ab66e0c7dcdb04"},
+    {file = "grpcio-1.67.1-cp39-cp39-musllinux_1_1_i686.whl", hash = "sha256:299b3d8c4f790c6bcca485f9963b4846dd92cf6f1b65d3697145d005c80f9fe8"},
+    {file = "grpcio-1.67.1-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:60336bff760fbb47d7e86165408126f1dded184448e9a4c892189eb7c9d3f90f"},
+    {file = "grpcio-1.67.1-cp39-cp39-win32.whl", hash = "sha256:5ed601c4c6008429e3d247ddb367fe8c7259c355757448d7c1ef7bd4a6739e8e"},
+    {file = "grpcio-1.67.1-cp39-cp39-win_amd64.whl", hash = "sha256:5db70d32d6703b89912af16d6d45d78406374a8b8ef0d28140351dd0ec610e98"},
+    {file = "grpcio-1.67.1.tar.gz", hash = "sha256:3dc2ed4cabea4dc14d5e708c2b426205956077cc5de419b4d4079315017e9732"},
 ]
-markers = {main = "extra == \"extra-proxy\""}
-
-[package.dependencies]
-typing-extensions = ">=4.12,<5.0"
 
 [package.extras]
-protobuf = ["grpcio-tools (>=1.76.0)"]
+protobuf = ["grpcio-tools (>=1.67.1)"]
 
 [[package]]
 name = "grpcio-status"
@@ -3070,15 +3089,15 @@ files = [
 
 [[package]]
 name = "litellm-proxy-extras"
-version = "0.4.6"
+version = "0.4.7"
 description = "Additional files for the LiteLLM Proxy. Reduces the size of the main litellm package."
 optional = true
 python-versions = "!=2.7.*,!=3.0.*,!=3.1.*,!=3.2.*,!=3.3.*,!=3.4.*,!=3.5.*,!=3.6.*,!=3.7.*,>=3.8"
 groups = ["main"]
 markers = "extra == \"proxy\""
 files = [
-    {file = "litellm_proxy_extras-0.4.6-py3-none-any.whl", hash = "sha256:665ad022fdfd06f3fe97071e49f3b240554a931e57d27850fb815a19d3ea901d"},
-    {file = "litellm_proxy_extras-0.4.6.tar.gz", hash = "sha256:3864bdae26a92906081e591dcf72e1864277e6d58582bee224befb7385fda508"},
+    {file = "litellm_proxy_extras-0.4.7-py3-none-any.whl", hash = "sha256:0ca3c03155ba9553889a83e6c164986d9f128fb7dc584460f3929b6171ac3fe0"},
+    {file = "litellm_proxy_extras-0.4.7.tar.gz", hash = "sha256:bd9e646605c13c277472bff727a7d7cade712c6f4ce2a4683d3df818167030fd"},
 ]
 
 [[package]]
@@ -6949,26 +6968,6 @@ examples = ["aiosqlite (>=0.21.0)", "fastapi (>=0.115.12)", "sqlalchemy[asyncio]
 granian = ["granian (>=2.3.1)"]
 uvicorn = ["uvicorn (>=0.34.0)"]
 
-[[package]]
-name = "starlette"
-version = "0.49.3"
-description = "The little ASGI library that shines."
-optional = false
-python-versions = ">=3.9"
-groups = ["main", "dev"]
-files = [
-    {file = "starlette-0.49.3-py3-none-any.whl", hash = "sha256:b579b99715fdc2980cf88c8ec96d3bf1ce16f5a8051a7c2b84ef9b1cdecaea2f"},
-    {file = "starlette-0.49.3.tar.gz", hash = "sha256:1c14546f299b5901a1ea0e34410575bc33bbd741377a10484a54445588d00284"},
-]
-markers = {main = "python_version == \"3.9\" and extra == \"proxy\"", dev = "python_version == \"3.9\""}
-
-[package.dependencies]
-anyio = ">=3.6.2,<5"
-typing-extensions = {version = ">=4.10.0", markers = "python_version < \"3.13\""}
-
-[package.extras]
-full = ["httpx (>=0.27.0,<0.29.0)", "itsdangerous", "jinja2", "python-multipart (>=0.0.18)", "pyyaml"]
-
 [[package]]
 name = "starlette"
 version = "0.50.0"
@@ -6980,7 +6979,7 @@ files = [
     {file = "starlette-0.50.0-py3-none-any.whl", hash = "sha256:9e5391843ec9b6e472eed1365a78c8098cfceb7a74bfd4d6b1c0c0095efb3bca"},
     {file = "starlette-0.50.0.tar.gz", hash = "sha256:a2a17b22203254bcbc2e1f926d2d55f3f9497f769416b3190768befe598fa3ca"},
 ]
-markers = {main = "python_version >= \"3.10\" and (extra == \"mlflow\" or extra == \"proxy\")", dev = "python_version >= \"3.10\""}
+markers = {main = "python_version >= \"3.10\" and (extra == \"mlflow\" or extra == \"proxy\") or extra == \"proxy\""}
 
 [package.dependencies]
 anyio = ">=3.6.2,<5"
@@ -8007,4 +8006,4 @@ utils = ["numpydoc"]
 [metadata]
 lock-version = "2.1"
 python-versions = ">=3.9,<4.0"
-content-hash = "1f482f89088b4a28edb7aa58459d17bfd7df36b30c0d53e88e4f7a9b4a65b369"
+content-hash = "3b6e1c0e9697842545d175e3c9ba5b562635d271fe636b95158de874a1bbb1d5"
diff --git a/pyproject.toml b/pyproject.toml
index f32a2d4d28..83f12ef739 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -59,7 +59,7 @@ websockets = {version = "^13.1.0", optional = true}
 boto3 = {version = "1.36.0", optional = true}
 redisvl = {version = "^0.4.1", optional = true, markers = "python_version >= '3.9' and python_version < '3.14'"}
 mcp = {version = "^1.21.2", optional = true, python = ">=3.10"}
-litellm-proxy-extras = {version = "0.4.6", optional = true}
+litellm-proxy-extras = {version = "0.4.7", optional = true}
 rich = {version = "13.7.1", optional = true}
 litellm-enterprise = {version = "0.1.22", optional = true}
 diskcache = {version = "^5.6.1", optional = true}
diff --git a/requirements.txt b/requirements.txt
index 08129155d7..c60a180730 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -44,7 +44,7 @@ sentry_sdk==2.21.0 # for sentry error handling
 detect-secrets==1.5.0 # Enterprise - secret detection / masking in LLM requests
 cryptography==44.0.1
 tzdata==2025.1 # IANA time zone database
-litellm-proxy-extras==0.4.6 # for proxy extras - e.g. prisma migrations
+litellm-proxy-extras==0.4.7 # for proxy extras - e.g. prisma migrations
 ### LITELLM PACKAGE DEPENDENCIES
 python-dotenv==1.0.1 # for env
 tiktoken==0.8.0 # for calculating usage
diff --git a/tests/mcp_tests/test_mcp_logging.py b/tests/mcp_tests/test_mcp_logging.py
index 2b1f2699fd..44acd60ad4 100644
--- a/tests/mcp_tests/test_mcp_logging.py
+++ b/tests/mcp_tests/test_mcp_logging.py
@@ -2,7 +2,6 @@ import os
 import sys
 import pytest
 import asyncio
-import json
 from typing import Optional
 from unittest.mock import AsyncMock, patch
 
@@ -106,7 +105,7 @@ async def test_mcp_cost_tracking():
             await asyncio.sleep(2)
 
             logged_standard_logging_payload = test_logger.standard_logging_payload
-            print("logged_standard_logging_payload", json.dumps(logged_standard_logging_payload, indent=4))
+            print("logged_standard_logging_payload", logged_standard_logging_payload)
             
             # Add assertions
             assert response is not None
@@ -208,7 +207,7 @@ async def test_mcp_cost_tracking_per_tool():
             await asyncio.sleep(2)
 
             logged_standard_logging_payload_1 = test_logger.standard_logging_payload
-            print("logged_standard_logging_payload_1", json.dumps(logged_standard_logging_payload_1, indent=4))
+            print("logged_standard_logging_payload_1", logged_standard_logging_payload_1)
             
             # Verify expensive tool cost
             assert logged_standard_logging_payload_1 is not None, "Standard logging payload 1 should not be None"
@@ -229,7 +228,7 @@ async def test_mcp_cost_tracking_per_tool():
             await asyncio.sleep(2)
 
             logged_standard_logging_payload_2 = test_logger.standard_logging_payload
-            print("logged_standard_logging_payload_2", json.dumps(logged_standard_logging_payload_2, indent=4))
+            print("logged_standard_logging_payload_2", logged_standard_logging_payload_2)
             
             # Verify cheap tool cost
             assert logged_standard_logging_payload_2 is not None, "Standard logging payload 2 should not be None"
@@ -340,6 +339,6 @@ async def test_mcp_tool_call_hook():
 
             # check logged standard logging payload
             logged_standard_logging_payload = test_logger.standard_logging_payload
-            print("logged_standard_logging_payload", json.dumps(logged_standard_logging_payload, indent=4))
+            print("logged_standard_logging_payload", logged_standard_logging_payload)
             assert logged_standard_logging_payload is not None, "Standard logging payload should not be None"
             assert logged_standard_logging_payload["response_cost"] == 1.42
diff --git a/tests/proxy_unit_tests/test_proxy_token_counter.py b/tests/proxy_unit_tests/test_proxy_token_counter.py
index eb364ebf5b..a8486358f7 100644
--- a/tests/proxy_unit_tests/test_proxy_token_counter.py
+++ b/tests/proxy_unit_tests/test_proxy_token_counter.py
@@ -821,18 +821,22 @@ async def test_vertex_ai_anthropic_token_counting():
         assert response.original_response["input_tokens"] == 15
 
 @pytest.mark.parametrize("vertex_location", ["global", "us-central1"])
-def test_vertex_ai_gemini_token_counting_endpoint(vertex_location):
+def test_vertex_ai_partner_models_token_counting_endpoint(vertex_location):
+    """
+    Test that the VertexAIPartnerModelsTokenCounter builds the correct endpoint URL
+    for different vertex locations, including the special 'global' location.
+    """
     from litellm.llms.vertex_ai.vertex_ai_partner_models.count_tokens.handler import (
         VertexAIPartnerModelsTokenCounter,
     )
 
     endpoint = VertexAIPartnerModelsTokenCounter()._build_count_tokens_endpoint(
-        model="gemini-2.5-pro",
+        model="claude-3-5-sonnet-20241022",
         project_id="test-project",
         vertex_location=vertex_location,
         api_base=None,
     )
     if vertex_location == "global":
-        assert endpoint == "https://aiplatform.googleapis.com"
+        assert endpoint.startswith("https://aiplatform.googleapis.com")
     else:
-        assert endpoint == f"https://{vertex_location}-aiplatform.googleapis.com"
\ No newline at end of file
+        assert endpoint.startswith(f"https://{vertex_location}-aiplatform.googleapis.com")
\ No newline at end of file
diff --git a/tests/store_model_in_db_tests/test_mcp_servers.py b/tests/store_model_in_db_tests/test_mcp_servers.py
index ca9b92afb9..8e0f11aee1 100644
--- a/tests/store_model_in_db_tests/test_mcp_servers.py
+++ b/tests/store_model_in_db_tests/test_mcp_servers.py
@@ -139,7 +139,7 @@ async def test_create_mcp_server_direct():
         mock_get_prisma.return_value = mock_prisma
 
         # Mock server manager
-        mock_manager.add_update_server = mock.Mock()
+        mock_manager.add_update_server = mock.AsyncMock()
         mock_manager.reload_servers_from_database = mock.AsyncMock()
 
         # Set up test data
diff --git a/ui/litellm-dashboard/src/app/(dashboard)/hooks/common/queryKeysFactory.ts b/ui/litellm-dashboard/src/app/(dashboard)/hooks/common/queryKeysFactory.ts
new file mode 100644
index 0000000000..eceaae9d42
--- /dev/null
+++ b/ui/litellm-dashboard/src/app/(dashboard)/hooks/common/queryKeysFactory.ts
@@ -0,0 +1,35 @@
+// Query keys factory
+
+type ListParams = {
+  page?: number;
+  limit?: number;
+  filters?: Record<string, string | number>;
+};
+
+/**
+ * Generates a query keys factory for a given resource.
+ *
+ * @param resource - The name of the resource (e.g., "books", "users", "keys")
+ * @returns An object with query key generators following the standard pattern
+ *
+ * @example
+ * ```ts
+ * const bookKeys = createQueryKeys("books");
+ * // bookKeys.all -> ["books"]
+ * // bookKeys.lists() -> ["books", "list"]
+ * // bookKeys.list({ page: 1 }) -> ["books", "list", { params: { page: 1 } }]
+ * // bookKeys.details() -> ["books", "detail"]
+ * // bookKeys.detail("123") -> ["books", "detail", "123"]
+ * ```
+ */
+export function createQueryKeys<T extends string>(resource: T) {
+  const all = [resource] as const;
+
+  return {
+    all,
+    lists: () => [...all, "list"] as const,
+    list: (params?: ListParams) => [...all, "list", { params }] as const,
+    details: () => [...all, "detail"] as const,
+    detail: (uid: string) => [...all, "detail", uid] as const,
+  };
+}
diff --git a/ui/litellm-dashboard/src/app/(dashboard)/hooks/models/useModels.ts b/ui/litellm-dashboard/src/app/(dashboard)/hooks/models/useModels.ts
new file mode 100644
index 0000000000..aef05b1af2
--- /dev/null
+++ b/ui/litellm-dashboard/src/app/(dashboard)/hooks/models/useModels.ts
@@ -0,0 +1,27 @@
+import { useQuery } from "@tanstack/react-query";
+import { createQueryKeys } from "../common/queryKeysFactory";
+import { modelInfoCall, modelHubCall } from "@/components/networking";
+
+const modelKeys = createQueryKeys("models");
+const modelHubKeys = createQueryKeys("modelHub");
+
+export const useModelsInfo = (accessToken: string | null, userID: string | null, userRole: string | null) => {
+  return useQuery({
+    queryKey: modelKeys.list({
+      filters: {
+        ...(userID && { userID }),
+        ...(userRole && { userRole }),
+      },
+    }),
+    queryFn: async () => await modelInfoCall(accessToken!, userID!, userRole!),
+    enabled: Boolean(accessToken && userID && userRole),
+  });
+};
+
+export const useModelHub = (accessToken: string | null) => {
+  return useQuery({
+    queryKey: modelHubKeys.list({}),
+    queryFn: async () => await modelHubCall(accessToken!),
+    enabled: Boolean(accessToken),
+  });
+};
diff --git a/ui/litellm-dashboard/src/app/(dashboard)/hooks/useAuthorized.ts b/ui/litellm-dashboard/src/app/(dashboard)/hooks/useAuthorized.ts
index 0ce0cab183..cba7c1a3dc 100644
--- a/ui/litellm-dashboard/src/app/(dashboard)/hooks/useAuthorized.ts
+++ b/ui/litellm-dashboard/src/app/(dashboard)/hooks/useAuthorized.ts
@@ -67,7 +67,7 @@ const useAuthorized = () => {
     userRole: formatUserRole(decoded?.user_role ?? null),
     premiumUser: decoded?.premium_user ?? null,
     disabledPersonalKeyCreation: decoded?.disabled_non_admin_personal_key_creation ?? null,
-    showSSOBanner: decoded?.login_method === "username_password" ?? false,
+    showSSOBanner: decoded?.login_method === "username_password",
   };
 };
 
diff --git a/ui/litellm-dashboard/src/app/(dashboard)/models-and-endpoints/ModelsAndEndpointsView.test.tsx b/ui/litellm-dashboard/src/app/(dashboard)/models-and-endpoints/ModelsAndEndpointsView.test.tsx
index 630eecb352..b165b71be7 100644
--- a/ui/litellm-dashboard/src/app/(dashboard)/models-and-endpoints/ModelsAndEndpointsView.test.tsx
+++ b/ui/litellm-dashboard/src/app/(dashboard)/models-and-endpoints/ModelsAndEndpointsView.test.tsx
@@ -1,6 +1,7 @@
 /* @vitest-environment jsdom */
 import { render } from "@testing-library/react";
 import { describe, it, expect, vi } from "vitest";
+import { QueryClient, QueryClientProvider } from "@tanstack/react-query";
 import ModelsAndEndpointsView from "./ModelsAndEndpointsView";
 
 // Minimal stubs to avoid Next.js router and network usage during render
@@ -56,19 +57,24 @@ vi.mock("@/app/(dashboard)/hooks/useTeams", () => ({
   }),
 }));
 
+const createQueryClient = () =>
+  new QueryClient({
+    defaultOptions: { queries: { retry: false, gcTime: 0 } },
+  });
+
 describe("ModelsAndEndpointsView", () => {
-  it(
-    "should render the models and endpoints view",
-    async () => {
-      // JSDOM polyfill for libraries expecting ResizeObserver (e.g., recharts)
-      // Note: ResizeObserver is now globally mocked in setupTests.ts, but keeping this for backwards compatibility
-      // eslint-disable-next-line @typescript-eslint/no-explicit-any
-      (global as any).ResizeObserver = class {
-        observe() {}
-        unobserve() {}
-        disconnect() {}
-      };
-      const { findByText } = render(
+  it("should render the models and endpoints view", async () => {
+    // JSDOM polyfill for libraries expecting ResizeObserver (e.g., recharts)
+    // Note: ResizeObserver is now globally mocked in setupTests.ts, but keeping this for backwards compatibility
+    // eslint-disable-next-line @typescript-eslint/no-explicit-any
+    (global as any).ResizeObserver = class {
+      observe() {}
+      unobserve() {}
+      disconnect() {}
+    };
+    const queryClient = createQueryClient();
+    const { findByText } = render(
+      <QueryClientProvider client={queryClient}>
         <ModelsAndEndpointsView
           accessToken="123"
           token="123"
@@ -79,10 +85,9 @@ describe("ModelsAndEndpointsView", () => {
           setModelData={() => {}}
           premiumUser={false}
           teams={[]}
-        />,
-      );
-      expect(await findByText("Model Management", {}, { timeout: 10000 })).toBeInTheDocument();
-    },
-    15000,
-  );
+        />
+      </QueryClientProvider>,
+    );
+    expect(await findByText("Model Management", {}, { timeout: 10000 })).toBeInTheDocument();
+  }, 15000);
 });
diff --git a/ui/litellm-dashboard/src/app/(dashboard)/models-and-endpoints/ModelsAndEndpointsView.tsx b/ui/litellm-dashboard/src/app/(dashboard)/models-and-endpoints/ModelsAndEndpointsView.tsx
index 5ff7548816..4f33ba6585 100644
--- a/ui/litellm-dashboard/src/app/(dashboard)/models-and-endpoints/ModelsAndEndpointsView.tsx
+++ b/ui/litellm-dashboard/src/app/(dashboard)/models-and-endpoints/ModelsAndEndpointsView.tsx
@@ -1,5 +1,6 @@
 import React, { useState, useEffect, useRef } from "react";
 import { Text, Grid, Col } from "@tremor/react";
+import { useQueryClient } from "@tanstack/react-query";
 import { CredentialItem, credentialListCall, CredentialsResponse } from "@/components/networking";
 
 import { handleAddModelSubmit } from "@/components/add_model/handle_add_model_submit";
@@ -9,7 +10,6 @@ import { getDisplayModelName } from "@/components/view_model/model_name_display"
 import { TabPanel, TabPanels, TabGroup, TabList, Tab, Icon } from "@tremor/react";
 import { DateRangePickerValue } from "@tremor/react";
 import {
-  modelInfoCall,
   modelCostMap,
   modelMetricsCall,
   streamingModelMetricsCall,
@@ -22,6 +22,7 @@ import {
   adminGlobalActivityExceptionsPerDeployment,
   allEndUsersCall,
 } from "@/components/networking";
+import { useModelsInfo } from "@/app/(dashboard)/hooks/models/useModels";
 import { Form } from "antd";
 import { Typography } from "antd";
 import { RefreshIcon } from "@heroicons/react/outline";
@@ -152,6 +153,14 @@ const ModelsAndEndpointsView: React.FC<ModelDashboardProps> = ({
   const dropdownRef = useRef<HTMLDivElement>(null);
 
   const [selectedTabIndex, setSelectedTabIndex] = useState(0);
+
+  const queryClient = useQueryClient();
+  const {
+    data: modelDataResponse,
+    isLoading: isLoadingModels,
+    refetch: refetchModels,
+  } = useModelsInfo(accessToken, userID, userRole);
+
   const setProviderModelsFn = (provider: Providers) => {
     const _providerModels = getProviderModels(provider, modelMap);
     setProviderModels(_providerModels);
@@ -180,6 +189,7 @@ const ModelsAndEndpointsView: React.FC<ModelDashboardProps> = ({
   const uploadProps: UploadProps = {
     name: "file",
     accept: ".json",
+    pastable: false,
     beforeUpload: (file) => {
       if (file.type === "application/json") {
         const reader = new FileReader();
@@ -207,6 +217,9 @@ const ModelsAndEndpointsView: React.FC<ModelDashboardProps> = ({
     // Update the 'lastRefreshed' state to the current date and time
     const currentDate = new Date();
     setLastRefreshed(currentDate.toLocaleString());
+    // Invalidate and refetch models data using React Query
+    queryClient.invalidateQueries({ queryKey: ["models", "list"] });
+    refetchModels();
   };
 
   const handleSaveRetrySettings = async () => {
@@ -239,13 +252,11 @@ const ModelsAndEndpointsView: React.FC<ModelDashboardProps> = ({
   };
 
   useEffect(() => {
-    if (!accessToken || !token || !userRole || !userID) {
+    if (!accessToken || !token || !userRole || !userID || !modelDataResponse) {
       return;
     }
     const fetchData = async () => {
       try {
-        // Replace with your actual API call for model data
-        const modelDataResponse = await modelInfoCall(accessToken, userID, userRole);
         setModelData(modelDataResponse);
         const _providerSettings = await modelSettingsCall(accessToken);
         if (_providerSettings) {
@@ -372,7 +383,7 @@ const ModelsAndEndpointsView: React.FC<ModelDashboardProps> = ({
       }
     };
 
-    if (accessToken && token && userRole && userID) {
+    if (accessToken && token && userRole && userID && modelDataResponse) {
       fetchData();
     }
 
@@ -383,11 +394,9 @@ const ModelsAndEndpointsView: React.FC<ModelDashboardProps> = ({
     if (modelMap == null) {
       fetchModelMap();
     }
+  }, [accessToken, token, userRole, userID, modelDataResponse]);
 
-    handleRefreshClick();
-  }, [accessToken, token, userRole, userID, modelMap, lastRefreshed, selectedTeam]);
-
-  if (!modelData) {
+  if (!modelData || isLoadingModels) {
     return <div>Loading...</div>;
   }
 
@@ -597,15 +606,25 @@ const ModelsAndEndpointsView: React.FC<ModelDashboardProps> = ({
               setEditModalVisible={setEditModalVisible}
               setSelectedModel={setSelectedModel}
               onModelUpdate={(updatedModel) => {
-                // Update the model in the modelData.data array
-                const updatedModelData = {
-                  ...modelData,
-                  data: modelData.data.map((model: any) =>
-                    model.model_info.id === updatedModel.model_info.id ? updatedModel : model,
-                  ),
-                };
-                setModelData(updatedModelData);
-                // Trigger a refresh to update UI
+                // Handle model deletion
+                if (updatedModel.deleted) {
+                  const updatedModelData = {
+                    ...modelData,
+                    data: modelData.data.filter((model: any) => model.model_info.id !== updatedModel.model_info.id),
+                  };
+                  setModelData(updatedModelData);
+                } else {
+                  // Update the model in the modelData.data array
+                  const updatedModelData = {
+                    ...modelData,
+                    data: modelData.data.map((model: any) =>
+                      model.model_info.id === updatedModel.model_info.id ? updatedModel : model,
+                    ),
+                  };
+                  setModelData(updatedModelData);
+                }
+                // Invalidate cache and trigger a refresh to update UI
+                queryClient.invalidateQueries({ queryKey: ["models", "list"] });
                 handleRefreshClick();
               }}
               modelAccessGroups={availableModelAccessGroups}
diff --git a/ui/litellm-dashboard/src/components/molecules/models/ProviderLogo.test.tsx b/ui/litellm-dashboard/src/components/molecules/models/ProviderLogo.test.tsx
new file mode 100644
index 0000000000..9a9c631890
--- /dev/null
+++ b/ui/litellm-dashboard/src/components/molecules/models/ProviderLogo.test.tsx
@@ -0,0 +1,39 @@
+import React from "react";
+import { describe, it, expect, vi, beforeEach } from "vitest";
+import { screen, render, fireEvent, act } from "@testing-library/react";
+import { ProviderLogo } from "./ProviderLogo";
+import * as providerInfoHelpers from "../../provider_info_helpers";
+
+vi.mock("../../provider_info_helpers");
+
+describe("ProviderLogo", () => {
+  beforeEach(() => {
+    vi.resetAllMocks();
+  });
+
+  it("should render the component", () => {
+    vi.mocked(providerInfoHelpers.getProviderLogoAndName).mockReturnValue({
+      logo: "",
+      displayName: "Test Provider",
+    });
+    render(<ProviderLogo provider="test" />);
+    expect(screen.getByText("t")).toBeInTheDocument();
+  });
+
+  it("should show fallback when image fails to load", () => {
+    vi.mocked(providerInfoHelpers.getProviderLogoAndName).mockReturnValue({
+      logo: "/path/to/logo.png",
+      displayName: "Test Provider",
+    });
+    render(<ProviderLogo provider="test" />);
+    const img = screen.getByRole("img", { name: "test logo" });
+    expect(img).toBeInTheDocument();
+
+    act(() => {
+      fireEvent.error(img);
+    });
+
+    expect(screen.getByText("t")).toBeInTheDocument();
+    expect(screen.queryByRole("img")).not.toBeInTheDocument();
+  });
+});
diff --git a/ui/litellm-dashboard/src/components/molecules/models/ProviderLogo.tsx b/ui/litellm-dashboard/src/components/molecules/models/ProviderLogo.tsx
new file mode 100644
index 0000000000..4a9da15e33
--- /dev/null
+++ b/ui/litellm-dashboard/src/components/molecules/models/ProviderLogo.tsx
@@ -0,0 +1,24 @@
+import React, { useState } from "react";
+import { getProviderLogoAndName } from "../../provider_info_helpers";
+
+interface ProviderLogoProps {
+  provider: string;
+  className?: string;
+}
+
+export const ProviderLogo: React.FC<ProviderLogoProps> = ({ provider, className = "w-4 h-4" }) => {
+  const [hasError, setHasError] = useState(false);
+  const { logo } = getProviderLogoAndName(provider);
+
+  const showFallback = hasError || !logo;
+
+  if (showFallback) {
+    return (
+      <div className={`${className} rounded-full bg-gray-200 flex items-center justify-center text-xs`}>
+        {provider?.charAt(0) || "-"}
+      </div>
+    );
+  }
+
+  return <img src={logo} alt={`${provider} logo`} className={className} onError={() => setHasError(true)} />;
+};
diff --git a/ui/litellm-dashboard/src/components/molecules/models/columns.tsx b/ui/litellm-dashboard/src/components/molecules/models/columns.tsx
index 91a65a502f..c1a16e3936 100644
--- a/ui/litellm-dashboard/src/components/molecules/models/columns.tsx
+++ b/ui/litellm-dashboard/src/components/molecules/models/columns.tsx
@@ -3,7 +3,7 @@ import { ColumnDef } from "@tanstack/react-table";
 import { Badge, Button, Icon } from "@tremor/react";
 import { Tooltip } from "antd";
 import { ModelData } from "../../model_dashboard/types";
-import { getProviderLogoAndName } from "../../provider_info_helpers";
+import { ProviderLogo } from "./ProviderLogo";
 
 export const columns = (
   userRole: string,
@@ -62,28 +62,7 @@ export const columns = (
             {/* Provider Icon */}
             <div className="flex-shrink-0 mt-0.5">
               {model.provider ? (
-                <img
-                  src={getProviderLogoAndName(model.provider).logo}
-                  alt={`${model.provider} logo`}
-                  className="w-4 h-4"
-                  onError={(e) => {
-                    const target = e.currentTarget as HTMLImageElement;
-                    const parent = target.parentElement;
-                    if (!parent || !parent.contains(target)) {
-                      return;
-                    }
-
-                    try {
-                      const fallbackDiv = document.createElement("div");
-                      fallbackDiv.className =
-                        "w-4 h-4 rounded-full bg-gray-200 flex items-center justify-center text-xs";
-                      fallbackDiv.textContent = model.provider?.charAt(0) || "-";
-                      parent.replaceChild(fallbackDiv, target);
-                    } catch (error) {
-                      console.error("Failed to replace provider logo fallback:", error);
-                    }
-                  }}
-                />
+                <ProviderLogo provider={model.provider} />
               ) : (
                 <div className="w-4 h-4 rounded-full bg-gray-200 flex items-center justify-center text-xs">-</div>
               )}