Merge branch 'main' into litellm_add_managed_files_db

2025-04-24 18:24:20 +00:00 · 2025-04-12 07:49:33 -07:00 · 2025-04-12 07:49:33 -07:00 · 37b4f5f5c9
commit 37b4f5f5c9
parent f6e7f06eee eb19639215
59 changed files with 2902 additions and 361 deletions
--- a/deploy/charts/litellm-helm/Chart.yaml
+++ b/deploy/charts/litellm-helm/Chart.yaml
@ -18,7 +18,7 @@ type: application
 # This is the chart version. This version number should be incremented each time you make changes
 # to the chart and its templates, including the app version.
 # Versions are expected to follow Semantic Versioning (https://semver.org/)
-version: 0.4.2
+version: 0.4.3

 # This is the version number of the application being deployed. This version number should be
 # incremented each time you make changes to the application. Versions are not expected to
--- a/deploy/charts/litellm-helm/templates/deployment.yaml
+++ b/deploy/charts/litellm-helm/templates/deployment.yaml
@ -97,6 +97,9 @@ spec:
              value: {{ $val | quote }}
            {{- end }}
            {{- end }}
+            {{- with .Values.extraEnvVars }}
+              {{- toYaml . | nindent 12 }}
+            {{- end }}
          envFrom:
          {{- range .Values.environmentSecrets }}
            - secretRef:
--- a/deploy/charts/litellm-helm/tests/deployment_tests.yaml
+++ b/deploy/charts/litellm-helm/tests/deployment_tests.yaml
@ -80,3 +80,38 @@ tests:
              secretKeyRef:
                name: my-secret
                key: my-key
+  - it: should work with extraEnvVars
+    template: deployment.yaml
+    set:
+      extraEnvVars:
+        - name: EXTRA_ENV_VAR
+          valueFrom:
+            fieldRef:
+              fieldPath: metadata.labels['env']
+    asserts:
+      - contains:
+          path: spec.template.spec.containers[0].env
+          content:
+            name: EXTRA_ENV_VAR
+            valueFrom:
+              fieldRef:
+                fieldPath: metadata.labels['env']
+  - it: should work with both extraEnvVars and envVars
+    template: deployment.yaml
+    set:
+      envVars:
+        ENV_VAR: ENV_VAR_VALUE
+      extraEnvVars:
+        - name: EXTRA_ENV_VAR
+          value: EXTRA_ENV_VAR_VALUE
+    asserts:
+      - contains:
+          path: spec.template.spec.containers[0].env
+          content:
+            name: ENV_VAR
+            value: ENV_VAR_VALUE
+      - contains:
+          path: spec.template.spec.containers[0].env
+          content:
+            name: EXTRA_ENV_VAR
+            value: EXTRA_ENV_VAR_VALUE
--- a/deploy/charts/litellm-helm/values.yaml
+++ b/deploy/charts/litellm-helm/values.yaml
@ -195,9 +195,15 @@ migrationJob:
  annotations: {}
  ttlSecondsAfterFinished: 120

-# Additional environment variables to be added to the deployment
+# Additional environment variables to be added to the deployment as a map of key-value pairs
 envVars: {
    # USE_DDTRACE: "true"
 }

+# Additional environment variables to be added to the deployment as a list of k8s env vars
+extraEnvVars: {
+    # - name: EXTRA_ENV_VAR
+    #   value: EXTRA_ENV_VAR_VALUE
+}
+

--- a/docs/my-website/docs/providers/azure.md
+++ b/docs/my-website/docs/providers/azure.md
@ -478,7 +478,7 @@ response.stream_to_file(speech_file_path)
 ## **Authentication**


-### Entrata ID - use `azure_ad_token`
+### Entra ID - use `azure_ad_token`

 This is a walkthrough on how to use Azure Active Directory Tokens - Microsoft Entra ID to make `litellm.completion()` calls 

@ -545,7 +545,7 @@ model_list:
 </TabItem>
 </Tabs>

-### Entrata ID - use tenant_id, client_id, client_secret
+### Entra ID - use tenant_id, client_id, client_secret

 Here is an example of setting up `tenant_id`, `client_id`, `client_secret` in your litellm proxy `config.yaml`
 ```yaml
@ -581,7 +581,7 @@ Example video of using `tenant_id`, `client_id`, `client_secret` with LiteLLM Pr

 <iframe width="840" height="500" src="https://www.loom.com/embed/70d3f219ee7f4e5d84778b7f17bba506?sid=04b8ff29-485f-4cb8-929e-6b392722f36d" frameborder="0" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>

-### Entrata ID - use client_id, username, password
+### Entra ID - use client_id, username, password

 Here is an example of setting up `client_id`, `azure_username`, `azure_password` in your litellm proxy `config.yaml`
 ```yaml
--- a/docs/my-website/docs/providers/xai.md
+++ b/docs/my-website/docs/providers/xai.md
@ -18,13 +18,14 @@ os.environ['XAI_API_KEY']
 ```

 ## Sample Usage
-```python
+
+```python showLineNumbers title="LiteLLM python sdk usage - Non-streaming"
 from litellm import completion
 import os

 os.environ['XAI_API_KEY'] = ""
 response = completion(
-    model="xai/grok-2-latest",
+    model="xai/grok-3-mini-beta",
    messages=[
        {
            "role": "user",
@ -45,13 +46,14 @@ print(response)
 ```

 ## Sample Usage - Streaming
-```python
+
+```python showLineNumbers title="LiteLLM python sdk usage - Streaming"
 from litellm import completion
 import os

 os.environ['XAI_API_KEY'] = ""
 response = completion(
-    model="xai/grok-2-latest",
+    model="xai/grok-3-mini-beta",
    messages=[
        {
            "role": "user",
@ -75,7 +77,8 @@ for chunk in response:
 ```

 ## Sample Usage - Vision
-```python
+
+```python showLineNumbers title="LiteLLM python sdk usage - Vision"
 import os 
 from litellm import completion

@ -110,7 +113,7 @@ Here's how to call a XAI model with the LiteLLM Proxy Server

 1. Modify the config.yaml 

-  ```yaml
+  ```yaml showLineNumbers
  model_list:
    - model_name: my-model
      litellm_params:
@ -131,7 +134,7 @@ Here's how to call a XAI model with the LiteLLM Proxy Server

  <TabItem value="openai" label="OpenAI Python v1.0.0+">

-  ```python
+  ```python showLineNumbers
  import openai
  client = openai.OpenAI(
      api_key="sk-1234",             # pass litellm proxy key, if you're using virtual keys
--- a/docs/my-website/docs/reasoning_content.md
+++ b/docs/my-website/docs/reasoning_content.md
@ -15,10 +15,11 @@ Supported Providers:
 - Bedrock (Anthropic + Deepseek) (`bedrock/`)
 - Vertex AI (Anthropic) (`vertexai/`)
 - OpenRouter (`openrouter/`)
+- XAI (`xai/`)

 LiteLLM will standardize the `reasoning_content` in the response and `thinking_blocks` in the assistant message.

-```python
+```python title="Example response from litellm"
 "message": {
    ...
    "reasoning_content": "The capital of France is Paris.",
@ -37,7 +38,7 @@ LiteLLM will standardize the `reasoning_content` in the response and `thinking_b
 <Tabs>
 <TabItem value="sdk" label="SDK">

-```python
+```python showLineNumbers
 from litellm import completion
 import os 

@ -111,7 +112,7 @@ Here's how to use `thinking` blocks by Anthropic with tool calling.
 <Tabs>
 <TabItem value="sdk" label="SDK">

-```python
+```python showLineNumbers
 litellm._turn_on_debug()
 litellm.modify_params = True
 model = "anthropic/claude-3-7-sonnet-20250219" # works across Anthropic, Bedrock, Vertex AI
@ -210,7 +211,7 @@ if tool_calls:

 1. Setup config.yaml

-```yaml
+```yaml showLineNumbers
 model_list:
  - model_name: claude-3-7-sonnet-thinking
    litellm_params:
@ -224,7 +225,7 @@ model_list:

 2. Run proxy

-```bash
+```bash showLineNumbers
 litellm --config config.yaml

 # RUNNING on http://0.0.0.0:4000
@ -332,7 +333,7 @@ curl http://0.0.0.0:4000/v1/chat/completions \

 Set `drop_params=True` to drop the 'thinking' blocks when swapping from Anthropic to Deepseek models. Suggest improvements to this approach [here](https://github.com/BerriAI/litellm/discussions/8927).

-```python
+```python showLineNumbers
 litellm.drop_params = True # 👈 EITHER GLOBALLY or per request

 # or per request
@ -373,7 +374,7 @@ You can also pass the `thinking` parameter to Anthropic models.
 <Tabs>
 <TabItem value="sdk" label="SDK">

-```python
+```python showLineNumbers
 response = litellm.completion(
  model="anthropic/claude-3-7-sonnet-20250219",
  messages=[{"role": "user", "content": "What is the capital of France?"}],
@ -395,5 +396,92 @@ curl http://0.0.0.0:4000/v1/chat/completions \
  }'
 ```

+</TabItem>
+</Tabs>
+
+## Checking if a model supports reasoning
+
+<Tabs>
+<TabItem label="LiteLLM Python SDK" value="Python">
+
+Use `litellm.supports_reasoning(model="")` -> returns `True` if model supports reasoning and `False` if not.
+
+```python showLineNumbers title="litellm.supports_reasoning() usage"
+import litellm 
+
+# Example models that support reasoning
+assert litellm.supports_reasoning(model="anthropic/claude-3-7-sonnet-20250219") == True
+assert litellm.supports_reasoning(model="deepseek/deepseek-chat") == True 
+
+# Example models that do not support reasoning
+assert litellm.supports_reasoning(model="openai/gpt-3.5-turbo") == False 
+```
+</TabItem>
+
+<TabItem label="LiteLLM Proxy Server" value="proxy">
+
+1. Define models that support reasoning in your `config.yaml`. You can optionally add `supports_reasoning: True` to the `model_info` if LiteLLM does not automatically detect it for your custom model.
+
+```yaml showLineNumbers title="litellm proxy config.yaml"
+model_list:
+  - model_name: claude-3-sonnet-reasoning
+    litellm_params:
+      model: anthropic/claude-3-7-sonnet-20250219
+      api_key: os.environ/ANTHROPIC_API_KEY
+  - model_name: deepseek-reasoning
+    litellm_params:
+      model: deepseek/deepseek-chat
+      api_key: os.environ/DEEPSEEK_API_KEY
+  # Example for a custom model where detection might be needed
+  - model_name: my-custom-reasoning-model 
+    litellm_params:
+      model: openai/my-custom-model # Assuming it's OpenAI compatible
+      api_base: http://localhost:8000
+      api_key: fake-key
+    model_info:
+      supports_reasoning: True # Explicitly mark as supporting reasoning
+```
+
+2. Run the proxy server:
+
+```bash showLineNumbers title="litellm --config config.yaml"
+litellm --config config.yaml
+```
+
+3. Call `/model_group/info` to check if your model supports `reasoning`
+
+```shell showLineNumbers title="curl /model_group/info"
+curl -X 'GET' \
+  'http://localhost:4000/model_group/info' \
+  -H 'accept: application/json' \
+  -H 'x-api-key: sk-1234'
+```
+
+Expected Response 
+
+```json showLineNumbers title="response from /model_group/info"
+{
+  "data": [
+    {
+      "model_group": "claude-3-sonnet-reasoning",
+      "providers": ["anthropic"],
+      "mode": "chat",
+      "supports_reasoning": true,
+    },
+    {
+      "model_group": "deepseek-reasoning",
+      "providers": ["deepseek"],
+      "supports_reasoning": true,
+    },
+    {
+      "model_group": "my-custom-reasoning-model",
+      "providers": ["openai"],
+      "supports_reasoning": true,
+    }
+  ]
+}
+````
+
+
 </TabItem>
 </Tabs>
--- a/docs/my-website/package-lock.json
+++ b/docs/my-website/package-lock.json
@ -2148,9 +2148,10 @@
      }
    },
    "node_modules/@babel/runtime": {
-      "version": "7.26.0",
-      "resolved": "https://registry.npmjs.org/@babel/runtime/-/runtime-7.26.0.tgz",
-      "integrity": "sha512-FDSOghenHTiToteC/QRlv2q3DhPZ/oOXTBoirfWNx1Cx3TMVcGWQtMMmQcSvb/JjpNeGzx8Pq/b4fKEJuWm1sw==",
+      "version": "7.27.0",
+      "resolved": "https://registry.npmjs.org/@babel/runtime/-/runtime-7.27.0.tgz",
+      "integrity": "sha512-VtPOkrdPHZsKc/clNqyi9WUA8TINkZ4cGk63UUE3u4pmB2k+ZMQRDuIOagv8UVd6j7k0T3+RRIb7beKTebNbcw==",
+      "license": "MIT",
      "dependencies": {
        "regenerator-runtime": "^0.14.0"
      },
--- a/docs/my-website/release_notes/v1.57.8-stable/index.md
+++ b/docs/my-website/release_notes/v1.57.8-stable/index.md
@ -38,7 +38,7 @@ hide_table_of_contents: false
 2. OpenAI Moderations - `omni-moderation-latest` support. [Start Here](https://docs.litellm.ai/docs/moderation)
 3. Azure O1 - fake streaming support. This ensures if a `stream=true` is passed, the response is streamed. [Start Here](https://docs.litellm.ai/docs/providers/azure)
 4. Anthropic - non-whitespace char stop sequence handling - [PR](https://github.com/BerriAI/litellm/pull/7484)
-5. Azure OpenAI - support entrata id username + password based auth. [Start Here](https://docs.litellm.ai/docs/providers/azure#entrata-id---use-tenant_id-client_id-client_secret)
+5. Azure OpenAI - support Entra id username + password based auth. [Start Here](https://docs.litellm.ai/docs/providers/azure#entrata-id---use-tenant_id-client_id-client_secret)
 6. LM Studio - embedding route support. [Start Here](https://docs.litellm.ai/docs/providers/lm-studio)
 7. WatsonX - ZenAPIKeyAuth support. [Start Here](https://docs.litellm.ai/docs/providers/watsonx)
    
--- a/litellm/init.py
+++ b/litellm/init.py
@ -65,8 +65,8 @@ from litellm.proxy._types import (
    KeyManagementSystem,
    KeyManagementSettings,
    LiteLLM_UpperboundKeyGenerateParams,
-    NewTeamRequest,
 )
+from litellm.types.proxy.management_endpoints.ui_sso import DefaultTeamSSOParams
 from litellm.types.utils import StandardKeyGenerationConfig, LlmProviders
 from litellm.integrations.custom_logger import CustomLogger
 from litellm.litellm_core_utils.logging_callback_manager import LoggingCallbackManager
@ -277,7 +277,7 @@ default_key_generate_params: Optional[Dict] = None
 upperbound_key_generate_params: Optional[LiteLLM_UpperboundKeyGenerateParams] = None
 key_generation_settings: Optional[StandardKeyGenerationConfig] = None
 default_internal_user_params: Optional[Dict] = None
-default_team_params: Optional[Union[NewTeamRequest, Dict]] = None
+default_team_params: Optional[Union[DefaultTeamSSOParams, Dict]] = None
 default_team_settings: Optional[List] = None
 max_user_budget: Optional[float] = None
 default_max_internal_user_budget: Optional[float] = None
@ -772,6 +772,7 @@ from .utils import (
    supports_audio_input,
    supports_audio_output,
    supports_system_messages,
+    supports_reasoning,
    get_litellm_params,
    acreate,
    get_max_tokens,
--- a/litellm/llms/databricks/common_utils.py
+++ b/litellm/llms/databricks/common_utils.py
@ -68,7 +68,7 @@ class DatabricksBase:
        headers: Optional[dict],
    ) -> Tuple[str, dict]:
        if api_key is None and not headers:  # handle empty headers
-            if custom_endpoint is not None:
+            if custom_endpoint is True:
                raise DatabricksException(
                    status_code=400,
                    message="Missing API Key - A call is being made to LLM Provider but no key is set either in the environment variables ({LLM_PROVIDER}_API_KEY) or via params",
--- a/litellm/llms/litellm_proxy/chat/transformation.py
+++ b/litellm/llms/litellm_proxy/chat/transformation.py
@ -15,6 +15,21 @@ class LiteLLMProxyChatConfig(OpenAIGPTConfig):
        list.append("thinking")
        return list

+    def _map_openai_params(
+        self,
+        non_default_params: dict,
+        optional_params: dict,
+        model: str,
+        drop_params: bool,
+    ) -> dict:
+        supported_openai_params = self.get_supported_openai_params(model)
+        for param, value in non_default_params.items():
+            if param == "thinking":
+                optional_params.setdefault("extra_body", {})["thinking"] = value
+            elif param in supported_openai_params:
+                optional_params[param] = value
+        return optional_params
+
    def _get_openai_compatible_provider_info(
        self, api_base: Optional[str], api_key: Optional[str]
    ) -> Tuple[Optional[str], Optional[str]]:
--- a/litellm/llms/xai/chat/transformation.py
+++ b/litellm/llms/xai/chat/transformation.py
@ -1,5 +1,7 @@
 from typing import List, Optional, Tuple

+import litellm
+from litellm._logging import verbose_logger
 from litellm.litellm_core_utils.prompt_templates.common_utils import (
    strip_name_from_messages,
 )
@ -12,6 +14,10 @@ XAI_API_BASE = "https://api.x.ai/v1"


 class XAIChatConfig(OpenAIGPTConfig):
+    @property
+    def custom_llm_provider(self) -> Optional[str]:
+        return "xai"
+
    def _get_openai_compatible_provider_info(
        self, api_base: Optional[str], api_key: Optional[str]
    ) -> Tuple[Optional[str], Optional[str]]:
@ -20,7 +26,7 @@ class XAIChatConfig(OpenAIGPTConfig):
        return api_base, dynamic_api_key

    def get_supported_openai_params(self, model: str) -> list:
-        return [
+        base_openai_params = [
            "frequency_penalty",
            "logit_bias",
            "logprobs",
@ -39,6 +45,15 @@ class XAIChatConfig(OpenAIGPTConfig):
            "top_p",
            "user",
        ]
+        try:
+            if litellm.supports_reasoning(
+                model=model, custom_llm_provider=self.custom_llm_provider
+            ):
+                base_openai_params.append("reasoning_effort")
+        except Exception as e:
+            verbose_logger.debug(f"Error checking if model supports reasoning: {e}")
+
+        return base_openai_params

    def map_openai_params(
        self,
--- a/litellm/model_prices_and_context_window_backup.json
+++ b/litellm/model_prices_and_context_window_backup.json
@ -15,6 +15,7 @@
        "supports_prompt_caching": true,
        "supports_response_schema": true,
        "supports_system_messages": true,
+        "supports_reasoning": true,
        "supports_web_search": true,
        "search_context_cost_per_query": {
            "search_context_size_low": 0.0000,
@ -379,6 +380,7 @@
        "supports_response_schema": true,
        "supports_tool_choice": true,
        "supports_native_streaming": false,
+        "supports_reasoning": true,
        "supported_modalities": ["text", "image"],
        "supported_output_modalities": ["text"],
        "supported_endpoints": ["/v1/responses", "/v1/batch"]
@ -401,6 +403,7 @@
        "supports_response_schema": true,
        "supports_tool_choice": true,
        "supports_native_streaming": false,
+        "supports_reasoning": true,
        "supported_modalities": ["text", "image"],
        "supported_output_modalities": ["text"],
        "supported_endpoints": ["/v1/responses", "/v1/batch"]
@ -420,6 +423,7 @@
        "supports_prompt_caching": true,
        "supports_system_messages": true,
        "supports_response_schema": true,
+        "supports_reasoning": true,
        "supports_tool_choice": true
    },
    "o1-mini": {
@ -448,6 +452,7 @@
        "supports_vision": false,
        "supports_prompt_caching": true,
        "supports_response_schema": true,
+        "supports_reasoning": true,
        "supports_tool_choice": true
    },
    "o3-mini-2025-01-31": {
@ -464,6 +469,7 @@
        "supports_vision": false,
        "supports_prompt_caching": true,
        "supports_response_schema": true,
+        "supports_reasoning": true,
        "supports_tool_choice": true
    },
    "o1-mini-2024-09-12": {
@ -476,6 +482,7 @@
        "litellm_provider": "openai",
        "mode": "chat",
        "supports_vision": true,
+        "supports_reasoning": true,
        "supports_prompt_caching": true
    },
    "o1-preview": {
@ -488,6 +495,7 @@
        "litellm_provider": "openai",
        "mode": "chat",
        "supports_vision": true,
+        "supports_reasoning": true,
        "supports_prompt_caching": true
    },
    "o1-preview-2024-09-12": {
@ -500,6 +508,7 @@
        "litellm_provider": "openai",
        "mode": "chat",
        "supports_vision": true,
+        "supports_reasoning": true,
        "supports_prompt_caching": true
    },
    "o1-2024-12-17": {
@ -517,6 +526,7 @@
        "supports_prompt_caching": true,
        "supports_system_messages": true,
        "supports_response_schema": true,
+        "supports_reasoning": true,
        "supports_tool_choice": true
    },
    "chatgpt-4o-latest": {
@ -1416,6 +1426,7 @@
        "cache_read_input_token_cost": 0.00000055,
        "litellm_provider": "azure",
        "mode": "chat",
+        "supports_reasoning": true,
        "supports_vision": false,
        "supports_prompt_caching": true,
        "supports_tool_choice": true
@ -1432,6 +1443,7 @@
        "litellm_provider": "azure",
        "mode": "chat",
        "supports_vision": false,
+        "supports_reasoning": true,
        "supports_prompt_caching": true,
        "supports_tool_choice": true
    },
@ -1447,6 +1459,7 @@
        "litellm_provider": "azure",
        "mode": "chat",
        "supports_vision": false,
+        "supports_reasoning": true,
        "supports_prompt_caching": true,
        "supports_tool_choice": true
    },
@ -1477,6 +1490,7 @@
        "mode": "chat",
        "supports_vision": false,
        "supports_prompt_caching": true,
+        "supports_reasoning": true,
        "supports_response_schema": true,
        "supports_tool_choice": true
    },
@ -1492,6 +1506,7 @@
        "supports_function_calling": true,
        "supports_parallel_function_calling": true,
        "supports_vision": false,
+        "supports_reasoning": true,
        "supports_prompt_caching": true
    },
    "azure/o1-mini-2024-09-12": {
@ -1506,6 +1521,7 @@
        "supports_function_calling": true,
        "supports_parallel_function_calling": true,
        "supports_vision": false,
+        "supports_reasoning": true,
        "supports_prompt_caching": true
    },
    "azure/us/o1-mini-2024-09-12": {
@ -1552,6 +1568,7 @@
        "supports_function_calling": true,
        "supports_parallel_function_calling": true,
        "supports_vision": true,
+        "supports_reasoning": true,
        "supports_prompt_caching": true,
        "supports_tool_choice": true
    },
@ -1567,6 +1584,7 @@
        "supports_function_calling": true,
        "supports_parallel_function_calling": true,
        "supports_vision": true,
+        "supports_reasoning": true,
        "supports_prompt_caching": true,
        "supports_tool_choice": true
    },
@ -1612,6 +1630,7 @@
        "supports_function_calling": true,
        "supports_parallel_function_calling": true,
        "supports_vision": false,
+        "supports_reasoning": true,
        "supports_prompt_caching": true
    },
    "azure/o1-preview-2024-09-12": {
@ -1626,6 +1645,7 @@
        "supports_function_calling": true,
        "supports_parallel_function_calling": true,
        "supports_vision": false,
+        "supports_reasoning": true,
        "supports_prompt_caching": true
    },
    "azure/us/o1-preview-2024-09-12": {
@ -2284,6 +2304,7 @@
        "litellm_provider": "azure_ai",
        "mode": "chat",
        "supports_tool_choice": true,
+        "supports_reasoning": true,
        "source": "https://techcommunity.microsoft.com/blog/machinelearningblog/deepseek-r1-improved-performance-higher-limits-and-transparent-pricing/4386367"
    },
    "azure_ai/deepseek-v3": {
@ -2984,6 +3005,7 @@
        "supports_function_calling": true, 
        "supports_assistant_prefill": true,
        "supports_tool_choice": true,
+        "supports_reasoning": true,
        "supports_prompt_caching": true
    },
    "deepseek/deepseek-chat": {
@ -3097,6 +3119,87 @@
        "supports_vision": true,
        "supports_tool_choice": true
    },
+    "xai/grok-3-beta": {
+        "max_tokens": 131072,
+        "max_input_tokens": 131072,
+        "max_output_tokens": 131072,
+        "input_cost_per_token": 0.000003,
+        "output_cost_per_token": 0.000015,
+        "litellm_provider": "xai",
+        "mode": "chat",
+        "supports_function_calling": true,
+        "supports_tool_choice": true,
+        "supports_response_schema": false,
+        "source": "https://x.ai/api#pricing"
+    },
+    "xai/grok-3-fast-beta": {
+        "max_tokens": 131072,
+        "max_input_tokens": 131072,
+        "max_output_tokens": 131072,
+        "input_cost_per_token": 0.000005,
+        "output_cost_per_token": 0.000025,
+        "litellm_provider": "xai",
+        "mode": "chat",
+        "supports_function_calling": true,
+        "supports_tool_choice": true,
+        "supports_response_schema": false,
+        "source": "https://x.ai/api#pricing"
+    },
+    "xai/grok-3-fast-latest": {
+        "max_tokens": 131072,
+        "max_input_tokens": 131072,
+        "max_output_tokens": 131072,
+        "input_cost_per_token": 0.000005,
+        "output_cost_per_token": 0.000025,
+        "litellm_provider": "xai",
+        "mode": "chat",
+        "supports_function_calling": true,
+        "supports_tool_choice": true,
+        "supports_response_schema": false,
+        "source": "https://x.ai/api#pricing"
+    },
+    "xai/grok-3-mini-beta": {
+        "max_tokens": 131072,
+        "max_input_tokens": 131072,
+        "max_output_tokens": 131072,
+        "input_cost_per_token": 0.0000003,
+        "output_cost_per_token": 0.0000005,
+        "litellm_provider": "xai",
+        "mode": "chat",
+        "supports_function_calling": true,
+        "supports_tool_choice": true,
+        "supports_reasoning": true,
+        "supports_response_schema": false,
+        "source": "https://x.ai/api#pricing"
+    },
+    "xai/grok-3-mini-fast-beta": {
+        "max_tokens": 131072,
+        "max_input_tokens": 131072,
+        "max_output_tokens": 131072,
+        "input_cost_per_token": 0.0000006,
+        "output_cost_per_token": 0.000004,
+        "litellm_provider": "xai",
+        "mode": "chat",
+        "supports_function_calling": true,
+        "supports_tool_choice": true,
+        "supports_reasoning": true,
+        "supports_response_schema": false,
+        "source": "https://x.ai/api#pricing"
+    },
+    "xai/grok-3-mini-fast-latest": {
+        "max_tokens": 131072,
+        "max_input_tokens": 131072,
+        "max_output_tokens": 131072,
+        "input_cost_per_token": 0.0000006,
+        "output_cost_per_token": 0.000004,
+        "litellm_provider": "xai",
+        "mode": "chat",
+        "supports_reasoning": true,
+        "supports_function_calling": true,
+        "supports_tool_choice": true,
+        "supports_response_schema": false,
+        "source": "https://x.ai/api#pricing"
+    },
    "xai/grok-vision-beta": {
        "max_tokens": 8192,
        "max_input_tokens": 8192,
@ -3167,6 +3270,7 @@
        "mode": "chat",
        "supports_system_messages": false,
        "supports_function_calling": false, 
+        "supports_reasoning": true,
        "supports_response_schema": false,
        "supports_tool_choice": true
    },
@ -3678,7 +3782,8 @@
        "supports_prompt_caching": true,
        "supports_response_schema": true,
        "deprecation_date": "2025-06-01",
-        "supports_tool_choice": true
+        "supports_tool_choice": true,
+        "supports_reasoning": true
    },
    "claude-3-7-sonnet-20250219": {
        "max_tokens": 128000,
@ -3698,7 +3803,8 @@
        "supports_prompt_caching": true,
        "supports_response_schema": true,
        "deprecation_date": "2026-02-01",
-        "supports_tool_choice": true
+        "supports_tool_choice": true,
+        "supports_reasoning": true
    },
    "claude-3-5-sonnet-20241022": {
        "max_tokens": 8192,
@ -5276,6 +5382,7 @@
        "supports_prompt_caching": true,
        "supports_response_schema": true,
        "deprecation_date": "2025-06-01",
+        "supports_reasoning": true,
        "supports_tool_choice": true
    },
    "vertex_ai/claude-3-haiku": {
@ -6593,6 +6700,7 @@
        "mode": "chat",
        "supports_function_calling": true, 
        "supports_assistant_prefill": true,
+        "supports_reasoning": true,
        "supports_tool_choice": true,
        "supports_prompt_caching": true
    },
@ -6768,6 +6876,7 @@
        "mode": "chat",
        "supports_function_calling": true,
        "supports_vision": true,
+        "supports_reasoning": true,
        "tool_use_system_prompt_tokens": 159,
        "supports_assistant_prefill": true,
        "supports_tool_choice": true
@ -6783,6 +6892,7 @@
        "mode": "chat",
        "supports_function_calling": true,
        "supports_vision": true,
+        "supports_reasoning": true,
        "tool_use_system_prompt_tokens": 159,
        "supports_tool_choice": true
    },
@ -6950,6 +7060,7 @@
        "litellm_provider": "openrouter",
        "mode": "chat",
        "supports_function_calling": true,
+        "supports_reasoning": true,
        "supports_parallel_function_calling": true,
        "supports_vision": false,
        "supports_tool_choice": true
@ -6963,6 +7074,7 @@
        "litellm_provider": "openrouter",
        "mode": "chat",
        "supports_function_calling": true,
+        "supports_reasoning": true,
        "supports_parallel_function_calling": true,
        "supports_vision": false,
        "supports_tool_choice": true
@ -7780,6 +7892,7 @@
        "supports_assistant_prefill": true,
        "supports_prompt_caching": true, 
        "supports_response_schema": true,
+        "supports_reasoning": true,
        "supports_tool_choice": true
    },
    "anthropic.claude-3-5-sonnet-20241022-v2:0": {
@ -7897,7 +8010,8 @@
        "supports_assistant_prefill": true,
        "supports_prompt_caching": true, 
        "supports_response_schema": true,
-        "supports_tool_choice": true
+        "supports_tool_choice": true,
+        "supports_reasoning": true
    },
    "us.anthropic.claude-3-haiku-20240307-v1:0": {
        "max_tokens": 4096,
@ -8656,6 +8770,7 @@
        "output_cost_per_token": 0.0000054,
        "litellm_provider": "bedrock_converse",
        "mode": "chat",
+        "supports_reasoning": true,
        "supports_function_calling": false, 
        "supports_tool_choice": false

@ -10482,7 +10597,8 @@
        "metadata": {"notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Claude 3.7 conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation."},
        "supports_assistant_prefill": true,
        "supports_function_calling": true,
-        "supports_tool_choice": true
+        "supports_tool_choice": true,
+        "supports_reasoning": true
    },
    "databricks/databricks-meta-llama-3-1-405b-instruct": {
        "max_tokens": 128000,
@ -10740,6 +10856,7 @@
        "max_input_tokens": 32768,
        "max_output_tokens": 8192,
        "litellm_provider": "snowflake",
+        "supports_reasoning": true,
        "mode": "chat"
    },
    "snowflake/snowflake-arctic": {
--- a/litellm/proxy/_types.py
+++ b/litellm/proxy/_types.py
@ -192,6 +192,28 @@ class LiteLLM_UpperboundKeyGenerateParams(LiteLLMPydanticObjectBase):
    rpm_limit: Optional[int] = None


+class KeyManagementRoutes(str, enum.Enum):
+    """
+    Enum for key management routes
+    """
+
+    # write routes
+    KEY_GENERATE = "/key/generate"
+    KEY_UPDATE = "/key/update"
+    KEY_DELETE = "/key/delete"
+    KEY_REGENERATE = "/key/regenerate"
+    KEY_REGENERATE_WITH_PATH_PARAM = "/key/{key_id}/regenerate"
+    KEY_BLOCK = "/key/block"
+    KEY_UNBLOCK = "/key/unblock"
+
+    # info and health routes
+    KEY_INFO = "/key/info"
+    KEY_HEALTH = "/key/health"
+
+    # list routes
+    KEY_LIST = "/key/list"
+
+
 class LiteLLMRoutes(enum.Enum):
    openai_route_names = [
        "chat_completion",
@ -322,14 +344,19 @@ class LiteLLMRoutes(enum.Enum):
    # NOTE: ROUTES ONLY FOR MASTER KEY - only the Master Key should be able to Reset Spend
    master_key_only_routes = ["/global/spend/reset"]

-    management_routes = [  # key
-        "/key/generate",
-        "/key/{token_id}/regenerate",
-        "/key/update",
-        "/key/delete",
-        "/key/info",
-        "/key/health",
-        "/key/list",
+    key_management_routes = [
+        KeyManagementRoutes.KEY_GENERATE,
+        KeyManagementRoutes.KEY_UPDATE,
+        KeyManagementRoutes.KEY_DELETE,
+        KeyManagementRoutes.KEY_INFO,
+        KeyManagementRoutes.KEY_REGENERATE,
+        KeyManagementRoutes.KEY_REGENERATE_WITH_PATH_PARAM,
+        KeyManagementRoutes.KEY_LIST,
+        KeyManagementRoutes.KEY_BLOCK,
+        KeyManagementRoutes.KEY_UNBLOCK,
+    ]
+
+    management_routes = [
        # user
        "/user/new",
        "/user/update",
@ -349,7 +376,7 @@ class LiteLLMRoutes(enum.Enum):
        "/model/update",
        "/model/delete",
        "/model/info",
-    ]
+    ] + key_management_routes

    spend_tracking_routes = [
        # spend
@ -619,9 +646,9 @@ class GenerateRequestBase(LiteLLMPydanticObjectBase):
    allowed_cache_controls: Optional[list] = []
    config: Optional[dict] = {}
    permissions: Optional[dict] = {}
-    model_max_budget: Optional[
-        dict
-    ] = {}  # {"gpt-4": 5.0, "gpt-3.5-turbo": 5.0}, defaults to {}
+    model_max_budget: Optional[dict] = (
+        {}
+    )  # {"gpt-4": 5.0, "gpt-3.5-turbo": 5.0}, defaults to {}

    model_config = ConfigDict(protected_namespaces=())
    model_rpm_limit: Optional[dict] = None
@ -877,12 +904,12 @@ class NewCustomerRequest(BudgetNewRequest):
    alias: Optional[str] = None  # human-friendly alias
    blocked: bool = False  # allow/disallow requests for this end-user
    budget_id: Optional[str] = None  # give either a budget_id or max_budget
-    allowed_model_region: Optional[
-        AllowedModelRegion
-    ] = None  # require all user requests to use models in this specific region
-    default_model: Optional[
-        str
-    ] = None  # if no equivalent model in allowed region - default all requests to this model
+    allowed_model_region: Optional[AllowedModelRegion] = (
+        None  # require all user requests to use models in this specific region
+    )
+    default_model: Optional[str] = (
+        None  # if no equivalent model in allowed region - default all requests to this model
+    )

    @model_validator(mode="before")
    @classmethod
@ -904,12 +931,12 @@ class UpdateCustomerRequest(LiteLLMPydanticObjectBase):
    blocked: bool = False  # allow/disallow requests for this end-user
    max_budget: Optional[float] = None
    budget_id: Optional[str] = None  # give either a budget_id or max_budget
-    allowed_model_region: Optional[
-        AllowedModelRegion
-    ] = None  # require all user requests to use models in this specific region
-    default_model: Optional[
-        str
-    ] = None  # if no equivalent model in allowed region - default all requests to this model
+    allowed_model_region: Optional[AllowedModelRegion] = (
+        None  # require all user requests to use models in this specific region
+    )
+    default_model: Optional[str] = (
+        None  # if no equivalent model in allowed region - default all requests to this model
+    )


 class DeleteCustomerRequest(LiteLLMPydanticObjectBase):
@ -1044,9 +1071,9 @@ class BlockKeyRequest(LiteLLMPydanticObjectBase):

 class AddTeamCallback(LiteLLMPydanticObjectBase):
    callback_name: str
-    callback_type: Optional[
-        Literal["success", "failure", "success_and_failure"]
-    ] = "success_and_failure"
+    callback_type: Optional[Literal["success", "failure", "success_and_failure"]] = (
+        "success_and_failure"
+    )
    callback_vars: Dict[str, str]

    @model_validator(mode="before")
@ -1111,6 +1138,7 @@ class LiteLLM_TeamTable(TeamBase):
    budget_duration: Optional[str] = None
    budget_reset_at: Optional[datetime] = None
    model_id: Optional[int] = None
+    team_member_permissions: Optional[List[str]] = None
    litellm_model_table: Optional[LiteLLM_ModelTable] = None
    created_at: Optional[datetime] = None

@ -1303,9 +1331,9 @@ class ConfigList(LiteLLMPydanticObjectBase):
    stored_in_db: Optional[bool]
    field_default_value: Any
    premium_field: bool = False
-    nested_fields: Optional[
-        List[FieldDetail]
-    ] = None  # For nested dictionary or Pydantic fields
+    nested_fields: Optional[List[FieldDetail]] = (
+        None  # For nested dictionary or Pydantic fields
+    )


 class ConfigGeneralSettings(LiteLLMPydanticObjectBase):
@ -1571,9 +1599,9 @@ class LiteLLM_OrganizationMembershipTable(LiteLLMPydanticObjectBase):
    budget_id: Optional[str] = None
    created_at: datetime
    updated_at: datetime
-    user: Optional[
-        Any
-    ] = None  # You might want to replace 'Any' with a more specific type if available
+    user: Optional[Any] = (
+        None  # You might want to replace 'Any' with a more specific type if available
+    )
    litellm_budget_table: Optional[LiteLLM_BudgetTable] = None

    model_config = ConfigDict(protected_namespaces=())
@ -2157,6 +2185,11 @@ class ProxyErrorTypes(str, enum.Enum):
    Cache ping error
    """

+    team_member_permission_error = "team_member_permission_error"
+    """
+    Team member permission error
+    """
+
    @classmethod
    def get_model_access_error_type_for_object(
        cls, object_type: Literal["key", "user", "team"]
@ -2314,9 +2347,9 @@ class TeamModelDeleteRequest(BaseModel):
 # Organization Member Requests
 class OrganizationMemberAddRequest(OrgMemberAddRequest):
    organization_id: str
-    max_budget_in_organization: Optional[
-        float
-    ] = None  # Users max budget within the organization
+    max_budget_in_organization: Optional[float] = (
+        None  # Users max budget within the organization
+    )


 class OrganizationMemberDeleteRequest(MemberDeleteRequest):
@ -2505,9 +2538,9 @@ class ProviderBudgetResponse(LiteLLMPydanticObjectBase):
    Maps provider names to their budget configs.
    """

-    providers: Dict[
-        str, ProviderBudgetResponseObject
-    ] = {}  # Dictionary mapping provider names to their budget configurations
+    providers: Dict[str, ProviderBudgetResponseObject] = (
+        {}
+    )  # Dictionary mapping provider names to their budget configurations


 class ProxyStateVariables(TypedDict):
@ -2635,9 +2668,9 @@ class LiteLLM_JWTAuth(LiteLLMPydanticObjectBase):
    enforce_rbac: bool = False
    roles_jwt_field: Optional[str] = None  # v2 on role mappings
    role_mappings: Optional[List[RoleMapping]] = None
-    object_id_jwt_field: Optional[
-        str
-    ] = None  # can be either user / team, inferred from the role mapping
+    object_id_jwt_field: Optional[str] = (
+        None  # can be either user / team, inferred from the role mapping
+    )
    scope_mappings: Optional[List[ScopeMapping]] = None
    enforce_scope_based_access: bool = False
    enforce_team_based_model_access: bool = False
--- a/litellm/proxy/hooks/managed_files.py
+++ b/litellm/proxy/hooks/managed_files.py
@ -1,9 +1,9 @@
 # What is this?
 ## This hook is used to check for LiteLLM managed files in the request body, and replace them with model-specific file id

-
 import base64
 import json
+import asyncio
 import uuid
 from abc import ABC, abstractmethod
 from typing import TYPE_CHECKING, Any, Dict, List, Literal, Optional, Union, cast
@ -415,6 +415,7 @@ class _PROXY_LiteLLMManagedFiles(CustomLogger):
            [file_id], litellm_parent_otel_span
        )
        specific_model_file_id_mapping = model_file_id_mapping.get(file_id)
+
        if specific_model_file_id_mapping:
            exception_dict = {}
            for model_id, file_id in specific_model_file_id_mapping.items():
@ -427,3 +428,4 @@ class _PROXY_LiteLLMManagedFiles(CustomLogger):
            )
        else:
            raise Exception(f"LiteLLM Managed File object with id={file_id} not found")
+
--- a/litellm/proxy/management_endpoints/team_endpoints.py
+++ b/litellm/proxy/management_endpoints/team_endpoints.py
@ -1,7 +1,7 @@
 """
 TEAM MANAGEMENT

-All /team management endpoints 
+All /team management endpoints

 /team/new
 /team/info
@ -62,6 +62,9 @@ from litellm.proxy.management_endpoints.common_utils import (
    _is_user_team_admin,
    _set_object_metadata_field,
 )
+from litellm.proxy.management_helpers.team_member_permission_checks import (
+    TeamMemberPermissionChecks,
+)
 from litellm.proxy.management_helpers.utils import (
    add_new_member,
    management_endpoint_wrapper,
@ -72,6 +75,10 @@ from litellm.proxy.utils import (
    handle_exception_on_proxy,
 )
 from litellm.router import Router
+from litellm.types.proxy.management_endpoints.team_endpoints import (
+    GetTeamMemberPermissionsResponse,
+    UpdateTeamMemberPermissionsRequest,
+)

 router = APIRouter()

@ -506,12 +513,12 @@ async def update_team(
            updated_kv["model_id"] = _model_id

    updated_kv = prisma_client.jsonify_team_object(db_data=updated_kv)
-    team_row: Optional[
-        LiteLLM_TeamTable
-    ] = await prisma_client.db.litellm_teamtable.update(
-        where={"team_id": data.team_id},
-        data=updated_kv,
-        include={"litellm_model_table": True},  # type: ignore
+    team_row: Optional[LiteLLM_TeamTable] = (
+        await prisma_client.db.litellm_teamtable.update(
+            where={"team_id": data.team_id},
+            data=updated_kv,
+            include={"litellm_model_table": True},  # type: ignore
+        )
    )

    if team_row is None or team_row.team_id is None:
@ -1137,10 +1144,10 @@ async def delete_team(
    team_rows: List[LiteLLM_TeamTable] = []
    for team_id in data.team_ids:
        try:
-            team_row_base: Optional[
-                BaseModel
-            ] = await prisma_client.db.litellm_teamtable.find_unique(
-                where={"team_id": team_id}
+            team_row_base: Optional[BaseModel] = (
+                await prisma_client.db.litellm_teamtable.find_unique(
+                    where={"team_id": team_id}
+                )
            )
            if team_row_base is None:
                raise Exception
@ -1298,10 +1305,10 @@ async def team_info(
            )

        try:
-            team_info: Optional[
-                BaseModel
-            ] = await prisma_client.db.litellm_teamtable.find_unique(
-                where={"team_id": team_id}
+            team_info: Optional[BaseModel] = (
+                await prisma_client.db.litellm_teamtable.find_unique(
+                    where={"team_id": team_id}
+                )
            )
            if team_info is None:
                raise Exception
@ -1926,3 +1933,89 @@ async def team_model_delete(
    )

    return updated_team
+
+
+@router.get(
+    "/team/permissions_list",
+    tags=["team management"],
+    dependencies=[Depends(user_api_key_auth)],
+)
+@management_endpoint_wrapper
+async def team_member_permissions(
+    team_id: str = fastapi.Query(
+        default=None, description="Team ID in the request parameters"
+    ),
+    user_api_key_dict: UserAPIKeyAuth = Depends(user_api_key_auth),
+) -> GetTeamMemberPermissionsResponse:
+    """
+    Get the team member permissions for a team
+    """
+    from litellm.proxy.proxy_server import prisma_client
+
+    if prisma_client is None:
+        raise HTTPException(status_code=500, detail={"error": "No db connected"})
+
+    team_row = await prisma_client.db.litellm_teamtable.find_unique(
+        where={"team_id": team_id}
+    )
+
+    if team_row is None:
+        raise HTTPException(
+            status_code=404,
+            detail={"error": f"Team not found, passed team_id={team_id}"},
+        )
+
+    team_obj = LiteLLM_TeamTable(**team_row.model_dump())
+    if team_obj.team_member_permissions is None:
+        team_obj.team_member_permissions = (
+            TeamMemberPermissionChecks.default_team_member_permissions()
+        )
+
+    return GetTeamMemberPermissionsResponse(
+        team_id=team_id,
+        team_member_permissions=team_obj.team_member_permissions,
+        all_available_permissions=TeamMemberPermissionChecks.get_all_available_team_member_permissions(),
+    )
+
+
+@router.post(
+    "/team/permissions_update",
+    tags=["team management"],
+    dependencies=[Depends(user_api_key_auth)],
+)
+async def update_team_member_permissions(
+    data: UpdateTeamMemberPermissionsRequest,
+    http_request: Request,
+    user_api_key_dict: UserAPIKeyAuth = Depends(user_api_key_auth),
+) -> LiteLLM_TeamTable:
+    """
+    Update the team member permissions for a team
+    """
+    from litellm.proxy.proxy_server import prisma_client
+
+    if prisma_client is None:
+        raise HTTPException(status_code=500, detail={"error": "No db connected"})
+
+    team_row = await prisma_client.db.litellm_teamtable.find_unique(
+        where={"team_id": data.team_id}
+    )
+
+    if team_row is None:
+        raise HTTPException(
+            status_code=404,
+            detail={"error": f"Team not found, passed team_id={data.team_id}"},
+        )
+
+    if user_api_key_dict.user_role != LitellmUserRoles.PROXY_ADMIN.value:
+        raise HTTPException(
+            status_code=403,
+            detail={"error": "Only proxy admin can update team member permissions"},
+        )
+
+    # Update the team member permissions
+    updated_team = await prisma_client.db.litellm_teamtable.update(
+        where={"team_id": data.team_id},
+        data={"team_member_permissions": data.team_member_permissions},
+    )
+
+    return updated_team
--- a/litellm/proxy/management_endpoints/ui_sso.py
+++ b/litellm/proxy/management_endpoints/ui_sso.py
@ -941,7 +941,7 @@ class SSOAuthenticationHandler:

    @staticmethod
    def _cast_and_deepcopy_litellm_default_team_params(
-        default_team_params: Union[NewTeamRequest, Dict],
+        default_team_params: Union[DefaultTeamSSOParams, Dict],
        team_request: NewTeamRequest,
        litellm_team_id: str,
        litellm_team_name: Optional[str] = None,
@ -949,23 +949,20 @@ class SSOAuthenticationHandler:
        """
        Casts and deepcopies the litellm.default_team_params to a NewTeamRequest object

-        - Ensures we create a new NewTeamRequest object
-        - Handle the case where litellm.default_team_params is a dict or a NewTeamRequest object
-        - Adds the litellm_team_id and litellm_team_name to the NewTeamRequest object
+        - Ensures we create a new DefaultTeamSSOParams object
+        - Handle the case where litellm.default_team_params is a dict or a DefaultTeamSSOParams object
+        - Adds the litellm_team_id and litellm_team_name to the DefaultTeamSSOParams object
        """
        if isinstance(default_team_params, dict):
            _team_request = deepcopy(default_team_params)
            _team_request["team_id"] = litellm_team_id
            _team_request["team_alias"] = litellm_team_name
            team_request = NewTeamRequest(**_team_request)
-        elif isinstance(litellm.default_team_params, NewTeamRequest):
-            team_request = litellm.default_team_params.model_copy(
-                deep=True,
-                update={
-                    "team_id": litellm_team_id,
-                    "team_alias": litellm_team_name,
-                },
-            )
+        elif isinstance(litellm.default_team_params, DefaultTeamSSOParams):
+            _default_team_params = deepcopy(litellm.default_team_params)
+            _new_team_request = team_request.model_dump()
+            _new_team_request.update(_default_team_params)
+            team_request = NewTeamRequest(**_new_team_request)
        return team_request


--- a/litellm/proxy/management_helpers/team_member_permission_checks.py
+++ b/litellm/proxy/management_helpers/team_member_permission_checks.py
@ -0,0 +1,181 @@
+from typing import List, Optional
+
+from litellm.caching import DualCache
+from litellm.proxy._types import (
+    KeyManagementRoutes,
+    LiteLLM_TeamTableCachedObj,
+    LiteLLM_VerificationToken,
+    LiteLLMRoutes,
+    LitellmUserRoles,
+    Member,
+    ProxyErrorTypes,
+    ProxyException,
+    Span,
+    UserAPIKeyAuth,
+)
+from litellm.proxy.auth.auth_checks import get_team_object
+from litellm.proxy.auth.route_checks import RouteChecks
+from litellm.proxy.utils import PrismaClient
+
+DEFAULT_TEAM_MEMBER_PERMISSIONS = [
+    KeyManagementRoutes.KEY_INFO,
+    KeyManagementRoutes.KEY_HEALTH,
+]
+
+
+class TeamMemberPermissionChecks:
+    @staticmethod
+    def get_permissions_for_team_member(
+        team_member_object: Member,
+        team_table: LiteLLM_TeamTableCachedObj,
+    ) -> List[KeyManagementRoutes]:
+        """
+        Returns the permissions for a team member
+        """
+        if team_table.team_member_permissions and isinstance(
+            team_table.team_member_permissions, list
+        ):
+            return [
+                KeyManagementRoutes(permission)
+                for permission in team_table.team_member_permissions
+            ]
+
+        return DEFAULT_TEAM_MEMBER_PERMISSIONS
+
+    @staticmethod
+    def _get_list_of_route_enum_as_str(
+        route_enum: List[KeyManagementRoutes],
+    ) -> List[str]:
+        """
+        Returns a list of the route enum as a list of strings
+        """
+        return [route.value for route in route_enum]
+
+    @staticmethod
+    async def can_team_member_execute_key_management_endpoint(
+        user_api_key_dict: UserAPIKeyAuth,
+        route: KeyManagementRoutes,
+        prisma_client: PrismaClient,
+        user_api_key_cache: DualCache,
+        parent_otel_span: Optional[Span],
+        existing_key_row: LiteLLM_VerificationToken,
+    ):
+        """
+        Main handler for checking if a team member can update a key
+        """
+        from litellm.proxy.management_endpoints.key_management_endpoints import (
+            _get_user_in_team,
+        )
+
+        # 1. Don't execute these checks if the user role is proxy admin
+        if user_api_key_dict.user_role == LitellmUserRoles.PROXY_ADMIN.value:
+            return
+
+        # 2. Check if the operation is being done on a team key
+        if existing_key_row.team_id is None:
+            return
+
+        # 3. Get Team Object from DB
+        team_table = await get_team_object(
+            team_id=existing_key_row.team_id,
+            prisma_client=prisma_client,
+            user_api_key_cache=user_api_key_cache,
+            parent_otel_span=user_api_key_dict.parent_otel_span,
+            check_db_only=True,
+        )
+
+        # 4. Extract `Member` object from `team_table`
+        key_assigned_user_in_team = _get_user_in_team(
+            team_table=team_table, user_id=user_api_key_dict.user_id
+        )
+
+        # 5. Check if the team member has permissions for the endpoint
+        TeamMemberPermissionChecks.does_team_member_have_permissions_for_endpoint(
+            team_member_object=key_assigned_user_in_team,
+            team_table=team_table,
+            route=route,
+        )
+
+    @staticmethod
+    def does_team_member_have_permissions_for_endpoint(
+        team_member_object: Optional[Member],
+        team_table: LiteLLM_TeamTableCachedObj,
+        route: str,
+    ) -> Optional[bool]:
+        """
+        Raises an exception if the team member does not have permissions for calling the endpoint for a team
+        """
+
+        # permission checks only run for non-admin users
+        # Non-Admin user trying to access information about a team's key
+        if team_member_object is None:
+            return False
+        if team_member_object.role == "admin":
+            return True
+
+        _team_member_permissions = (
+            TeamMemberPermissionChecks.get_permissions_for_team_member(
+                team_member_object=team_member_object,
+                team_table=team_table,
+            )
+        )
+        team_member_permissions = (
+            TeamMemberPermissionChecks._get_list_of_route_enum_as_str(
+                _team_member_permissions
+            )
+        )
+
+        if not RouteChecks.check_route_access(
+            route=route, allowed_routes=team_member_permissions
+        ):
+            raise ProxyException(
+                message=f"Team member does not have permissions for endpoint: {route}. You only have access to the following endpoints: {team_member_permissions}",
+                type=ProxyErrorTypes.team_member_permission_error,
+                param=route,
+                code=401,
+            )
+
+        return True
+
+    @staticmethod
+    async def user_belongs_to_keys_team(
+        user_api_key_dict: UserAPIKeyAuth,
+        existing_key_row: LiteLLM_VerificationToken,
+    ) -> bool:
+        """
+        Returns True if the user belongs to the team that the key is assigned to
+        """
+        from litellm.proxy.management_endpoints.key_management_endpoints import (
+            _get_user_in_team,
+        )
+        from litellm.proxy.proxy_server import prisma_client, user_api_key_cache
+
+        if existing_key_row.team_id is None:
+            return False
+        team_table = await get_team_object(
+            team_id=existing_key_row.team_id,
+            prisma_client=prisma_client,
+            user_api_key_cache=user_api_key_cache,
+            parent_otel_span=user_api_key_dict.parent_otel_span,
+            check_db_only=True,
+        )
+
+        # 4. Extract `Member` object from `team_table`
+        team_member_object = _get_user_in_team(
+            team_table=team_table, user_id=user_api_key_dict.user_id
+        )
+        return team_member_object is not None
+
+    @staticmethod
+    def get_all_available_team_member_permissions() -> List[str]:
+        """
+        Returns all available team member permissions
+        """
+        all_available_permissions = []
+        for route in LiteLLMRoutes.key_management_routes.value:
+            all_available_permissions.append(route.value)
+        return all_available_permissions
+
+    @staticmethod
+    def default_team_member_permissions() -> List[str]:
+        return [route.value for route in DEFAULT_TEAM_MEMBER_PERMISSIONS]
--- a/litellm/proxy/openai_files_endpoints/files_endpoints.py
+++ b/litellm/proxy/openai_files_endpoints/files_endpoints.py
@ -189,6 +189,51 @@ async def route_create_file(
    return response


+async def route_create_file(
+    llm_router: Optional[Router],
+    _create_file_request: CreateFileRequest,
+    purpose: OpenAIFilesPurpose,
+    proxy_logging_obj: ProxyLogging,
+    user_api_key_dict: UserAPIKeyAuth,
+    target_model_names_list: List[str],
+    is_router_model: bool,
+    router_model: Optional[str],
+    custom_llm_provider: str,
+) -> OpenAIFileObject:
+    if (
+        litellm.enable_loadbalancing_on_batch_endpoints is True
+        and is_router_model
+        and router_model is not None
+    ):
+        response = await _deprecated_loadbalanced_create_file(
+            llm_router=llm_router,
+            router_model=router_model,
+            _create_file_request=_create_file_request,
+        )
+    elif target_model_names_list:
+        response = await create_file_for_each_model(
+            llm_router=llm_router,
+            _create_file_request=_create_file_request,
+            target_model_names_list=target_model_names_list,
+            purpose=purpose,
+            proxy_logging_obj=proxy_logging_obj,
+            user_api_key_dict=user_api_key_dict,
+        )
+    else:
+        # get configs for custom_llm_provider
+        llm_provider_config = get_files_provider_config(
+            custom_llm_provider=custom_llm_provider
+        )
+        if llm_provider_config is not None:
+            # add llm_provider_config to data
+            _create_file_request.update(llm_provider_config)
+        _create_file_request.pop("custom_llm_provider", None)  # type: ignore
+        # for now use custom_llm_provider=="openai" -> this will change as LiteLLM adds more providers for acreate_batch
+        response = await litellm.acreate_file(**_create_file_request, custom_llm_provider=custom_llm_provider)  # type: ignore
+
+    return response
+
+
@router.post(
    "/{provider}/v1/files",
    dependencies=[Depends(user_api_key_auth)],
--- a/litellm/proxy/ui_crud_endpoints/proxy_setting_endpoints.py
+++ b/litellm/proxy/ui_crud_endpoints/proxy_setting_endpoints.py
@ -1,5 +1,5 @@
 #### CRUD ENDPOINTS for UI Settings #####
-from typing import List
+from typing import Any, List, Union

 from fastapi import APIRouter, Depends, HTTPException

@ -7,6 +7,7 @@ import litellm
 from litellm._logging import verbose_proxy_logger
 from litellm.proxy._types import *
 from litellm.proxy.auth.user_api_key_auth import user_api_key_auth
+from litellm.types.proxy.management_endpoints.ui_sso import DefaultTeamSSOParams

 router = APIRouter()

@ -111,34 +112,31 @@ async def delete_allowed_ip(ip_address: IPAddress):
    return {"message": f"IP {ip_address.ip} deleted successfully", "status": "success"}


-@router.get(
-    "/get/internal_user_settings",
-    tags=["SSO Settings"],
-    dependencies=[Depends(user_api_key_auth)],
-)
-async def get_sso_settings():
+async def _get_settings_with_schema(
+    settings_key: str,
+    settings_class: Any,
+    config: dict,
+) -> dict:
    """
-    Get all SSO settings from the litellm_settings configuration.
-    Returns a structured object with values and descriptions for UI display.
+    Common utility function to get settings with schema information.
+
+    Args:
+        settings_key: The key in litellm_settings to get
+        settings_class: The Pydantic class to use for schema
+        config: The config dictionary
    """
    from pydantic import TypeAdapter

-    from litellm.proxy.proxy_server import proxy_config
-
-    # Load existing config
-    config = await proxy_config.get_config()
    litellm_settings = config.get("litellm_settings", {}) or {}
-    default_internal_user_params = (
-        litellm_settings.get("default_internal_user_params", {}) or {}
-    )
+    settings_data = litellm_settings.get(settings_key, {}) or {}

-    # Create the settings object first
-    sso_settings = DefaultInternalUserParams(**(default_internal_user_params))
-    # Get the schema for UISSOSettings
-    schema = TypeAdapter(DefaultInternalUserParams).json_schema(by_alias=True)
+    # Create the settings object
+    settings = settings_class(**(settings_data))
+    # Get the schema
+    schema = TypeAdapter(settings_class).json_schema(by_alias=True)

    # Convert to dict for response
-    settings_dict = sso_settings.model_dump()
+    settings_dict = settings.model_dump()

    # Add descriptions to the response
    result = {
@ -166,6 +164,89 @@ async def get_sso_settings():
    return result


+@router.get(
+    "/get/internal_user_settings",
+    tags=["SSO Settings"],
+    dependencies=[Depends(user_api_key_auth)],
+)
+async def get_sso_settings():
+    """
+    Get all SSO settings from the litellm_settings configuration.
+    Returns a structured object with values and descriptions for UI display.
+    """
+    from litellm.proxy.proxy_server import proxy_config
+
+    # Load existing config
+    config = await proxy_config.get_config()
+
+    return await _get_settings_with_schema(
+        settings_key="default_internal_user_params",
+        settings_class=DefaultInternalUserParams,
+        config=config,
+    )
+
+
+@router.get(
+    "/get/default_team_settings",
+    tags=["SSO Settings"],
+    dependencies=[Depends(user_api_key_auth)],
+)
+async def get_default_team_settings():
+    """
+    Get all SSO settings from the litellm_settings configuration.
+    Returns a structured object with values and descriptions for UI display.
+    """
+    from litellm.proxy.proxy_server import proxy_config
+
+    # Load existing config
+    config = await proxy_config.get_config()
+
+    return await _get_settings_with_schema(
+        settings_key="default_team_params",
+        settings_class=DefaultTeamSSOParams,
+        config=config,
+    )
+
+
+async def _update_litellm_setting(
+    settings: Union[DefaultInternalUserParams, DefaultTeamSSOParams],
+    settings_key: str,
+    in_memory_var: Any,
+    success_message: str,
+):
+    """
+    Common utility function to update `litellm_settings` in both memory and config.
+
+    Args:
+        settings: The settings object to update
+        settings_key: The key in litellm_settings to update
+        in_memory_var: The in-memory variable to update
+        success_message: Message to return on success
+    """
+    from litellm.proxy.proxy_server import proxy_config
+
+    # Update the in-memory settings
+    in_memory_var = settings.model_dump(exclude_none=True)
+
+    # Load existing config
+    config = await proxy_config.get_config()
+
+    # Update config with new settings
+    if "litellm_settings" not in config:
+        config["litellm_settings"] = {}
+
+    config["litellm_settings"][settings_key] = settings.model_dump(exclude_none=True)
+
+    # Save the updated config
+    await proxy_config.save_config(new_config=config)
+
+    return {
+        "message": success_message,
+        "status": "success",
+        "settings": in_memory_var,
+    }
+
+
@router.patch(
    "/update/internal_user_settings",
    tags=["SSO Settings"],
@ -176,27 +257,27 @@ async def update_internal_user_settings(settings: DefaultInternalUserParams):
    Update the default internal user parameters for SSO users.
    These settings will be applied to new users who sign in via SSO.
    """
-    from litellm.proxy.proxy_server import proxy_config
-
-    # Update the in-memory settings
-    litellm.default_internal_user_params = settings.model_dump(exclude_none=True)
-
-    # Load existing config
-    config = await proxy_config.get_config()
-
-    # Update config with new settings
-    if "litellm_settings" not in config:
-        config["litellm_settings"] = {}
-
-    config["litellm_settings"]["default_internal_user_params"] = settings.model_dump(
-        exclude_none=True
+    return await _update_litellm_setting(
+        settings=settings,
+        settings_key="default_internal_user_params",
+        in_memory_var=litellm.default_internal_user_params,
+        success_message="Internal user settings updated successfully",
    )

-    # Save the updated config
-    await proxy_config.save_config(new_config=config)

-    return {
-        "message": "Internal user settings updated successfully",
-        "status": "success",
-        "settings": litellm.default_internal_user_params,
-    }
+@router.patch(
+    "/update/default_team_settings",
+    tags=["SSO Settings"],
+    dependencies=[Depends(user_api_key_auth)],
+)
+async def update_default_team_settings(settings: DefaultTeamSSOParams):
+    """
+    Update the default team parameters for SSO users.
+    These settings will be applied to new teams created from SSO.
+    """
+    return await _update_litellm_setting(
+        settings=settings,
+        settings_key="default_team_params",
+        in_memory_var=litellm.default_team_params,
+        success_message="Default team settings updated successfully",
+    )
--- a/litellm/router.py
+++ b/litellm/router.py
@ -339,9 +339,9 @@ class Router:
        )  # names of models under litellm_params. ex. azure/chatgpt-v-2
        self.deployment_latency_map = {}
        ### CACHING ###
-        cache_type: Literal[
-            "local", "redis", "redis-semantic", "s3", "disk"
-        ] = "local"  # default to an in-memory cache
+        cache_type: Literal["local", "redis", "redis-semantic", "s3", "disk"] = (
+            "local"  # default to an in-memory cache
+        )
        redis_cache = None
        cache_config: Dict[str, Any] = {}

@ -562,9 +562,9 @@ class Router:
                )
            )

-        self.model_group_retry_policy: Optional[
-            Dict[str, RetryPolicy]
-        ] = model_group_retry_policy
+        self.model_group_retry_policy: Optional[Dict[str, RetryPolicy]] = (
+            model_group_retry_policy
+        )

        self.allowed_fails_policy: Optional[AllowedFailsPolicy] = None
        if allowed_fails_policy is not None:
@ -619,7 +619,7 @@ class Router:

    @staticmethod
    def _create_redis_cache(
-        cache_config: Dict[str, Any]
+        cache_config: Dict[str, Any],
    ) -> Union[RedisCache, RedisClusterCache]:
        """
        Initializes either a RedisCache or RedisClusterCache based on the cache_config.
@ -1105,9 +1105,9 @@ class Router:
        """
        Adds default litellm params to kwargs, if set.
        """
-        self.default_litellm_params[
-            metadata_variable_name
-        ] = self.default_litellm_params.pop("metadata", {})
+        self.default_litellm_params[metadata_variable_name] = (
+            self.default_litellm_params.pop("metadata", {})
+        )
        for k, v in self.default_litellm_params.items():
            if (
                k not in kwargs and v is not None
@ -3243,11 +3243,11 @@ class Router:

                if isinstance(e, litellm.ContextWindowExceededError):
                    if context_window_fallbacks is not None:
-                        fallback_model_group: Optional[
-                            List[str]
-                        ] = self._get_fallback_model_group_from_fallbacks(
-                            fallbacks=context_window_fallbacks,
-                            model_group=model_group,
+                        fallback_model_group: Optional[List[str]] = (
+                            self._get_fallback_model_group_from_fallbacks(
+                                fallbacks=context_window_fallbacks,
+                                model_group=model_group,
+                            )
                        )
                        if fallback_model_group is None:
                            raise original_exception
@ -3279,11 +3279,11 @@ class Router:
                        e.message += "\n{}".format(error_message)
                elif isinstance(e, litellm.ContentPolicyViolationError):
                    if content_policy_fallbacks is not None:
-                        fallback_model_group: Optional[
-                            List[str]
-                        ] = self._get_fallback_model_group_from_fallbacks(
-                            fallbacks=content_policy_fallbacks,
-                            model_group=model_group,
+                        fallback_model_group: Optional[List[str]] = (
+                            self._get_fallback_model_group_from_fallbacks(
+                                fallbacks=content_policy_fallbacks,
+                                model_group=model_group,
+                            )
                        )
                        if fallback_model_group is None:
                            raise original_exception
@ -5046,6 +5046,11 @@ class Router:
                    and model_info["supports_web_search"] is True  # type: ignore
                ):
                    model_group_info.supports_web_search = True
+                if (
+                    model_info.get("supports_reasoning", None) is not None
+                    and model_info["supports_reasoning"] is True  # type: ignore
+                ):
+                    model_group_info.supports_reasoning = True
                if (
                    model_info.get("supported_openai_params", None) is not None
                    and model_info["supported_openai_params"] is not None
--- a/litellm/types/proxy/management_endpoints/team_endpoints.py
+++ b/litellm/types/proxy/management_endpoints/team_endpoints.py
@ -0,0 +1,35 @@
+from typing import List, Optional
+
+from pydantic import BaseModel
+
+
+class GetTeamMemberPermissionsRequest(BaseModel):
+    """Request to get the team member permissions for a team"""
+
+    team_id: str
+
+
+class GetTeamMemberPermissionsResponse(BaseModel):
+    """Response to get the team member permissions for a team"""
+
+    team_id: str
+    """
+    The team id that the permissions are for
+    """
+
+    team_member_permissions: Optional[List[str]] = []
+    """
+    The team member permissions currently set for the team
+    """
+
+    all_available_permissions: List[str]
+    """
+    All available team member permissions
+    """
+
+
+class UpdateTeamMemberPermissionsRequest(BaseModel):
+    """Request to update the team member permissions for a team"""
+
+    team_id: str
+    team_member_permissions: List[str]
--- a/litellm/types/proxy/management_endpoints/ui_sso.py
+++ b/litellm/types/proxy/management_endpoints/ui_sso.py
@ -1,4 +1,8 @@
-from typing import List, Optional, TypedDict
+from typing import List, Literal, Optional, TypedDict
+
+from pydantic import Field
+
+from litellm.proxy._types import LiteLLMPydanticObjectBase, LitellmUserRoles


 class MicrosoftGraphAPIUserGroupDirectoryObject(TypedDict, total=False):
@ -25,3 +29,30 @@ class MicrosoftServicePrincipalTeam(TypedDict, total=False):

    principalDisplayName: Optional[str]
    principalId: Optional[str]
+
+
+class DefaultTeamSSOParams(LiteLLMPydanticObjectBase):
+    """
+    Default parameters to apply when a new team is automatically created by LiteLLM via SSO Groups
+    """
+
+    models: List[str] = Field(
+        default=[],
+        description="Default list of models that new automatically created teams can access",
+    )
+    max_budget: Optional[float] = Field(
+        default=None,
+        description="Default maximum budget (in USD) for new automatically created teams",
+    )
+    budget_duration: Optional[str] = Field(
+        default=None,
+        description="Default budget duration for new automatically created teams (e.g. 'daily', 'weekly', 'monthly')",
+    )
+    tpm_limit: Optional[int] = Field(
+        default=None,
+        description="Default tpm limit for new automatically created teams",
+    )
+    rpm_limit: Optional[int] = Field(
+        default=None,
+        description="Default rpm limit for new automatically created teams",
+    )
--- a/litellm/types/router.py
+++ b/litellm/types/router.py
@ -96,16 +96,18 @@ class ModelInfo(BaseModel):
    id: Optional[
        str
    ]  # Allow id to be optional on input, but it will always be present as a str in the model instance
-    db_model: bool = False  # used for proxy - to separate models which are stored in the db vs. config.
+    db_model: bool = (
+        False  # used for proxy - to separate models which are stored in the db vs. config.
+    )
    updated_at: Optional[datetime.datetime] = None
    updated_by: Optional[str] = None

    created_at: Optional[datetime.datetime] = None
    created_by: Optional[str] = None

-    base_model: Optional[
-        str
-    ] = None  # specify if the base model is azure/gpt-3.5-turbo etc for accurate cost tracking
+    base_model: Optional[str] = (
+        None  # specify if the base model is azure/gpt-3.5-turbo etc for accurate cost tracking
+    )
    tier: Optional[Literal["free", "paid"]] = None

    """
@ -178,12 +180,12 @@ class GenericLiteLLMParams(CredentialLiteLLMParams, CustomPricingLiteLLMParams):
    custom_llm_provider: Optional[str] = None
    tpm: Optional[int] = None
    rpm: Optional[int] = None
-    timeout: Optional[
-        Union[float, str, httpx.Timeout]
-    ] = None  # if str, pass in as os.environ/
-    stream_timeout: Optional[
-        Union[float, str]
-    ] = None  # timeout when making stream=True calls, if str, pass in as os.environ/
+    timeout: Optional[Union[float, str, httpx.Timeout]] = (
+        None  # if str, pass in as os.environ/
+    )
+    stream_timeout: Optional[Union[float, str]] = (
+        None  # timeout when making stream=True calls, if str, pass in as os.environ/
+    )
    max_retries: Optional[int] = None
    organization: Optional[str] = None  # for openai orgs
    configurable_clientside_auth_params: CONFIGURABLE_CLIENTSIDE_AUTH_PARAMS = None
@ -253,9 +255,9 @@ class GenericLiteLLMParams(CredentialLiteLLMParams, CustomPricingLiteLLMParams):
        if max_retries is not None and isinstance(max_retries, str):
            max_retries = int(max_retries)  # cast to int
        # We need to keep max_retries in args since it's a parameter of GenericLiteLLMParams
-        args[
-            "max_retries"
-        ] = max_retries  # Put max_retries back in args after popping it
+        args["max_retries"] = (
+            max_retries  # Put max_retries back in args after popping it
+        )
        super().__init__(**args, **params)

    def __contains__(self, key):
@ -562,6 +564,7 @@ class ModelGroupInfo(BaseModel):
    supports_parallel_function_calling: bool = Field(default=False)
    supports_vision: bool = Field(default=False)
    supports_web_search: bool = Field(default=False)
+    supports_reasoning: bool = Field(default=False)
    supports_function_calling: bool = Field(default=False)
    supported_openai_params: Optional[List[str]] = Field(default=[])
    configurable_clientside_auth_params: CONFIGURABLE_CLIENTSIDE_AUTH_PARAMS = None
--- a/litellm/types/utils.py
+++ b/litellm/types/utils.py
@ -102,6 +102,7 @@ class ProviderSpecificModelInfo(TypedDict, total=False):
    supports_native_streaming: Optional[bool]
    supports_parallel_function_calling: Optional[bool]
    supports_web_search: Optional[bool]
+    supports_reasoning: Optional[bool]


 class SearchContextCostPerQuery(TypedDict, total=False):
--- a/litellm/utils.py
+++ b/litellm/utils.py
@ -484,7 +484,7 @@ def load_credentials_from_list(kwargs: dict):


 def get_dynamic_callbacks(
-    dynamic_callbacks: Optional[List[Union[str, Callable, CustomLogger]]]
+    dynamic_callbacks: Optional[List[Union[str, Callable, CustomLogger]]],
 ) -> List:
    returned_callbacks = litellm.callbacks.copy()
    if dynamic_callbacks:
@ -516,9 +516,9 @@ def function_setup(  # noqa: PLR0915
        function_id: Optional[str] = kwargs["id"] if "id" in kwargs else None

        ## DYNAMIC CALLBACKS ##
-        dynamic_callbacks: Optional[
-            List[Union[str, Callable, CustomLogger]]
-        ] = kwargs.pop("callbacks", None)
+        dynamic_callbacks: Optional[List[Union[str, Callable, CustomLogger]]] = (
+            kwargs.pop("callbacks", None)
+        )
        all_callbacks = get_dynamic_callbacks(dynamic_callbacks=dynamic_callbacks)

        if len(all_callbacks) > 0:
@ -1202,9 +1202,9 @@ def client(original_function):  # noqa: PLR0915
                        exception=e,
                        retry_policy=kwargs.get("retry_policy"),
                    )
-                    kwargs[
-                        "retry_policy"
-                    ] = reset_retry_policy()  # prevent infinite loops
+                    kwargs["retry_policy"] = (
+                        reset_retry_policy()
+                    )  # prevent infinite loops
                litellm.num_retries = (
                    None  # set retries to None to prevent infinite loops
                )
@ -2229,6 +2229,15 @@ def supports_vision(model: str, custom_llm_provider: Optional[str] = None) -> bo
    )


+def supports_reasoning(model: str, custom_llm_provider: Optional[str] = None) -> bool:
+    """
+    Check if the given model supports reasoning and return a boolean value.
+    """
+    return _supports_factory(
+        model=model, custom_llm_provider=custom_llm_provider, key="supports_reasoning"
+    )
+
+
 def supports_embedding_image_input(
    model: str, custom_llm_provider: Optional[str] = None
 ) -> bool:
@ -3004,16 +3013,16 @@ def get_optional_params(  # noqa: PLR0915
                    True  # so that main.py adds the function call to the prompt
                )
                if "tools" in non_default_params:
-                    optional_params[
-                        "functions_unsupported_model"
-                    ] = non_default_params.pop("tools")
+                    optional_params["functions_unsupported_model"] = (
+                        non_default_params.pop("tools")
+                    )
                    non_default_params.pop(
                        "tool_choice", None
                    )  # causes ollama requests to hang
                elif "functions" in non_default_params:
-                    optional_params[
-                        "functions_unsupported_model"
-                    ] = non_default_params.pop("functions")
+                    optional_params["functions_unsupported_model"] = (
+                        non_default_params.pop("functions")
+                    )
            elif (
                litellm.add_function_to_prompt
            ):  # if user opts to add it to prompt instead
@ -3036,10 +3045,10 @@ def get_optional_params(  # noqa: PLR0915

    if "response_format" in non_default_params:
        if provider_config is not None:
-            non_default_params[
-                "response_format"
-            ] = provider_config.get_json_schema_from_pydantic_object(
-                response_format=non_default_params["response_format"]
+            non_default_params["response_format"] = (
+                provider_config.get_json_schema_from_pydantic_object(
+                    response_format=non_default_params["response_format"]
+                )
            )
        else:
            non_default_params["response_format"] = type_to_response_format_param(
@ -4055,9 +4064,9 @@ def _count_characters(text: str) -> int:


 def get_response_string(response_obj: Union[ModelResponse, ModelResponseStream]) -> str:
-    _choices: Union[
-        List[Union[Choices, StreamingChoices]], List[StreamingChoices]
-    ] = response_obj.choices
+    _choices: Union[List[Union[Choices, StreamingChoices]], List[StreamingChoices]] = (
+        response_obj.choices
+    )

    response_str = ""
    for choice in _choices:
@ -4597,6 +4606,7 @@ def _get_model_info_helper(  # noqa: PLR0915
                    "supports_native_streaming", None
                ),
                supports_web_search=_model_info.get("supports_web_search", False),
+                supports_reasoning=_model_info.get("supports_reasoning", False),
                search_context_cost_per_query=_model_info.get(
                    "search_context_cost_per_query", None
                ),
@ -4669,6 +4679,7 @@ def get_model_info(model: str, custom_llm_provider: Optional[str] = None) -> Mod
            supports_audio_output: Optional[bool]
            supports_pdf_input: Optional[bool]
            supports_web_search: Optional[bool]
+            supports_reasoning: Optional[bool]
    Raises:
        Exception: If the model is not mapped yet.

@ -6188,7 +6199,7 @@ def validate_chat_completion_user_messages(messages: List[AllMessageValues]):


 def validate_chat_completion_tool_choice(
-    tool_choice: Optional[Union[dict, str]]
+    tool_choice: Optional[Union[dict, str]],
 ) -> Optional[Union[dict, str]]:
    """
    Confirm the tool choice is passed in the OpenAI format.
--- a/model_prices_and_context_window.json
+++ b/model_prices_and_context_window.json
@ -15,6 +15,7 @@
        "supports_prompt_caching": true,
        "supports_response_schema": true,
        "supports_system_messages": true,
+        "supports_reasoning": true,
        "supports_web_search": true,
        "search_context_cost_per_query": {
            "search_context_size_low": 0.0000,
@ -379,6 +380,7 @@
        "supports_response_schema": true,
        "supports_tool_choice": true,
        "supports_native_streaming": false,
+        "supports_reasoning": true,
        "supported_modalities": ["text", "image"],
        "supported_output_modalities": ["text"],
        "supported_endpoints": ["/v1/responses", "/v1/batch"]
@ -401,6 +403,7 @@
        "supports_response_schema": true,
        "supports_tool_choice": true,
        "supports_native_streaming": false,
+        "supports_reasoning": true,
        "supported_modalities": ["text", "image"],
        "supported_output_modalities": ["text"],
        "supported_endpoints": ["/v1/responses", "/v1/batch"]
@ -420,6 +423,7 @@
        "supports_prompt_caching": true,
        "supports_system_messages": true,
        "supports_response_schema": true,
+        "supports_reasoning": true,
        "supports_tool_choice": true
    },
    "o1-mini": {
@ -448,6 +452,7 @@
        "supports_vision": false,
        "supports_prompt_caching": true,
        "supports_response_schema": true,
+        "supports_reasoning": true,
        "supports_tool_choice": true
    },
    "o3-mini-2025-01-31": {
@ -464,6 +469,7 @@
        "supports_vision": false,
        "supports_prompt_caching": true,
        "supports_response_schema": true,
+        "supports_reasoning": true,
        "supports_tool_choice": true
    },
    "o1-mini-2024-09-12": {
@ -476,6 +482,7 @@
        "litellm_provider": "openai",
        "mode": "chat",
        "supports_vision": true,
+        "supports_reasoning": true,
        "supports_prompt_caching": true
    },
    "o1-preview": {
@ -488,6 +495,7 @@
        "litellm_provider": "openai",
        "mode": "chat",
        "supports_vision": true,
+        "supports_reasoning": true,
        "supports_prompt_caching": true
    },
    "o1-preview-2024-09-12": {
@ -500,6 +508,7 @@
        "litellm_provider": "openai",
        "mode": "chat",
        "supports_vision": true,
+        "supports_reasoning": true,
        "supports_prompt_caching": true
    },
    "o1-2024-12-17": {
@ -517,6 +526,7 @@
        "supports_prompt_caching": true,
        "supports_system_messages": true,
        "supports_response_schema": true,
+        "supports_reasoning": true,
        "supports_tool_choice": true
    },
    "chatgpt-4o-latest": {
@ -1416,6 +1426,7 @@
        "cache_read_input_token_cost": 0.00000055,
        "litellm_provider": "azure",
        "mode": "chat",
+        "supports_reasoning": true,
        "supports_vision": false,
        "supports_prompt_caching": true,
        "supports_tool_choice": true
@ -1432,6 +1443,7 @@
        "litellm_provider": "azure",
        "mode": "chat",
        "supports_vision": false,
+        "supports_reasoning": true,
        "supports_prompt_caching": true,
        "supports_tool_choice": true
    },
@ -1447,6 +1459,7 @@
        "litellm_provider": "azure",
        "mode": "chat",
        "supports_vision": false,
+        "supports_reasoning": true,
        "supports_prompt_caching": true,
        "supports_tool_choice": true
    },
@ -1477,6 +1490,7 @@
        "mode": "chat",
        "supports_vision": false,
        "supports_prompt_caching": true,
+        "supports_reasoning": true,
        "supports_response_schema": true,
        "supports_tool_choice": true
    },
@ -1492,6 +1506,7 @@
        "supports_function_calling": true,
        "supports_parallel_function_calling": true,
        "supports_vision": false,
+        "supports_reasoning": true,
        "supports_prompt_caching": true
    },
    "azure/o1-mini-2024-09-12": {
@ -1506,6 +1521,7 @@
        "supports_function_calling": true,
        "supports_parallel_function_calling": true,
        "supports_vision": false,
+        "supports_reasoning": true,
        "supports_prompt_caching": true
    },
    "azure/us/o1-mini-2024-09-12": {
@ -1552,6 +1568,7 @@
        "supports_function_calling": true,
        "supports_parallel_function_calling": true,
        "supports_vision": true,
+        "supports_reasoning": true,
        "supports_prompt_caching": true,
        "supports_tool_choice": true
    },
@ -1567,6 +1584,7 @@
        "supports_function_calling": true,
        "supports_parallel_function_calling": true,
        "supports_vision": true,
+        "supports_reasoning": true,
        "supports_prompt_caching": true,
        "supports_tool_choice": true
    },
@ -1612,6 +1630,7 @@
        "supports_function_calling": true,
        "supports_parallel_function_calling": true,
        "supports_vision": false,
+        "supports_reasoning": true,
        "supports_prompt_caching": true
    },
    "azure/o1-preview-2024-09-12": {
@ -1626,6 +1645,7 @@
        "supports_function_calling": true,
        "supports_parallel_function_calling": true,
        "supports_vision": false,
+        "supports_reasoning": true,
        "supports_prompt_caching": true
    },
    "azure/us/o1-preview-2024-09-12": {
@ -2284,6 +2304,7 @@
        "litellm_provider": "azure_ai",
        "mode": "chat",
        "supports_tool_choice": true,
+        "supports_reasoning": true,
        "source": "https://techcommunity.microsoft.com/blog/machinelearningblog/deepseek-r1-improved-performance-higher-limits-and-transparent-pricing/4386367"
    },
    "azure_ai/deepseek-v3": {
@ -2984,6 +3005,7 @@
        "supports_function_calling": true, 
        "supports_assistant_prefill": true,
        "supports_tool_choice": true,
+        "supports_reasoning": true,
        "supports_prompt_caching": true
    },
    "deepseek/deepseek-chat": {
@ -3097,6 +3119,87 @@
        "supports_vision": true,
        "supports_tool_choice": true
    },
+    "xai/grok-3-beta": {
+        "max_tokens": 131072,
+        "max_input_tokens": 131072,
+        "max_output_tokens": 131072,
+        "input_cost_per_token": 0.000003,
+        "output_cost_per_token": 0.000015,
+        "litellm_provider": "xai",
+        "mode": "chat",
+        "supports_function_calling": true,
+        "supports_tool_choice": true,
+        "supports_response_schema": false,
+        "source": "https://x.ai/api#pricing"
+    },
+    "xai/grok-3-fast-beta": {
+        "max_tokens": 131072,
+        "max_input_tokens": 131072,
+        "max_output_tokens": 131072,
+        "input_cost_per_token": 0.000005,
+        "output_cost_per_token": 0.000025,
+        "litellm_provider": "xai",
+        "mode": "chat",
+        "supports_function_calling": true,
+        "supports_tool_choice": true,
+        "supports_response_schema": false,
+        "source": "https://x.ai/api#pricing"
+    },
+    "xai/grok-3-fast-latest": {
+        "max_tokens": 131072,
+        "max_input_tokens": 131072,
+        "max_output_tokens": 131072,
+        "input_cost_per_token": 0.000005,
+        "output_cost_per_token": 0.000025,
+        "litellm_provider": "xai",
+        "mode": "chat",
+        "supports_function_calling": true,
+        "supports_tool_choice": true,
+        "supports_response_schema": false,
+        "source": "https://x.ai/api#pricing"
+    },
+    "xai/grok-3-mini-beta": {
+        "max_tokens": 131072,
+        "max_input_tokens": 131072,
+        "max_output_tokens": 131072,
+        "input_cost_per_token": 0.0000003,
+        "output_cost_per_token": 0.0000005,
+        "litellm_provider": "xai",
+        "mode": "chat",
+        "supports_function_calling": true,
+        "supports_tool_choice": true,
+        "supports_reasoning": true,
+        "supports_response_schema": false,
+        "source": "https://x.ai/api#pricing"
+    },
+    "xai/grok-3-mini-fast-beta": {
+        "max_tokens": 131072,
+        "max_input_tokens": 131072,
+        "max_output_tokens": 131072,
+        "input_cost_per_token": 0.0000006,
+        "output_cost_per_token": 0.000004,
+        "litellm_provider": "xai",
+        "mode": "chat",
+        "supports_function_calling": true,
+        "supports_tool_choice": true,
+        "supports_reasoning": true,
+        "supports_response_schema": false,
+        "source": "https://x.ai/api#pricing"
+    },
+    "xai/grok-3-mini-fast-latest": {
+        "max_tokens": 131072,
+        "max_input_tokens": 131072,
+        "max_output_tokens": 131072,
+        "input_cost_per_token": 0.0000006,
+        "output_cost_per_token": 0.000004,
+        "litellm_provider": "xai",
+        "mode": "chat",
+        "supports_reasoning": true,
+        "supports_function_calling": true,
+        "supports_tool_choice": true,
+        "supports_response_schema": false,
+        "source": "https://x.ai/api#pricing"
+    },
    "xai/grok-vision-beta": {
        "max_tokens": 8192,
        "max_input_tokens": 8192,
@ -3167,6 +3270,7 @@
        "mode": "chat",
        "supports_system_messages": false,
        "supports_function_calling": false, 
+        "supports_reasoning": true,
        "supports_response_schema": false,
        "supports_tool_choice": true
    },
@ -3678,7 +3782,8 @@
        "supports_prompt_caching": true,
        "supports_response_schema": true,
        "deprecation_date": "2025-06-01",
-        "supports_tool_choice": true
+        "supports_tool_choice": true,
+        "supports_reasoning": true
    },
    "claude-3-7-sonnet-20250219": {
        "max_tokens": 128000,
@ -3698,7 +3803,8 @@
        "supports_prompt_caching": true,
        "supports_response_schema": true,
        "deprecation_date": "2026-02-01",
-        "supports_tool_choice": true
+        "supports_tool_choice": true,
+        "supports_reasoning": true
    },
    "claude-3-5-sonnet-20241022": {
        "max_tokens": 8192,
@ -5276,6 +5382,7 @@
        "supports_prompt_caching": true,
        "supports_response_schema": true,
        "deprecation_date": "2025-06-01",
+        "supports_reasoning": true,
        "supports_tool_choice": true
    },
    "vertex_ai/claude-3-haiku": {
@ -6593,6 +6700,7 @@
        "mode": "chat",
        "supports_function_calling": true, 
        "supports_assistant_prefill": true,
+        "supports_reasoning": true,
        "supports_tool_choice": true,
        "supports_prompt_caching": true
    },
@ -6768,6 +6876,7 @@
        "mode": "chat",
        "supports_function_calling": true,
        "supports_vision": true,
+        "supports_reasoning": true,
        "tool_use_system_prompt_tokens": 159,
        "supports_assistant_prefill": true,
        "supports_tool_choice": true
@ -6783,6 +6892,7 @@
        "mode": "chat",
        "supports_function_calling": true,
        "supports_vision": true,
+        "supports_reasoning": true,
        "tool_use_system_prompt_tokens": 159,
        "supports_tool_choice": true
    },
@ -6950,6 +7060,7 @@
        "litellm_provider": "openrouter",
        "mode": "chat",
        "supports_function_calling": true,
+        "supports_reasoning": true,
        "supports_parallel_function_calling": true,
        "supports_vision": false,
        "supports_tool_choice": true
@ -6963,6 +7074,7 @@
        "litellm_provider": "openrouter",
        "mode": "chat",
        "supports_function_calling": true,
+        "supports_reasoning": true,
        "supports_parallel_function_calling": true,
        "supports_vision": false,
        "supports_tool_choice": true
@ -7780,6 +7892,7 @@
        "supports_assistant_prefill": true,
        "supports_prompt_caching": true, 
        "supports_response_schema": true,
+        "supports_reasoning": true,
        "supports_tool_choice": true
    },
    "anthropic.claude-3-5-sonnet-20241022-v2:0": {
@ -7897,7 +8010,8 @@
        "supports_assistant_prefill": true,
        "supports_prompt_caching": true, 
        "supports_response_schema": true,
-        "supports_tool_choice": true
+        "supports_tool_choice": true,
+        "supports_reasoning": true
    },
    "us.anthropic.claude-3-haiku-20240307-v1:0": {
        "max_tokens": 4096,
@ -8656,6 +8770,7 @@
        "output_cost_per_token": 0.0000054,
        "litellm_provider": "bedrock_converse",
        "mode": "chat",
+        "supports_reasoning": true,
        "supports_function_calling": false, 
        "supports_tool_choice": false

@ -10482,7 +10597,8 @@
        "metadata": {"notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Claude 3.7 conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation."},
        "supports_assistant_prefill": true,
        "supports_function_calling": true,
-        "supports_tool_choice": true
+        "supports_tool_choice": true,
+        "supports_reasoning": true
    },
    "databricks/databricks-meta-llama-3-1-405b-instruct": {
        "max_tokens": 128000,
@ -10740,6 +10856,7 @@
        "max_input_tokens": 32768,
        "max_output_tokens": 8192,
        "litellm_provider": "snowflake",
+        "supports_reasoning": true,
        "mode": "chat"
    },
    "snowflake/snowflake-arctic": {
--- a/pyproject.toml
+++ b/pyproject.toml
@ -1,6 +1,6 @@
 [tool.poetry]
 name = "litellm"
-version = "1.65.7"
+version = "1.65.8"
 description = "Library to easily interface with LLM API providers"
 authors = ["BerriAI"]
 license = "MIT"
@ -118,7 +118,7 @@ requires = ["poetry-core", "wheel"]
 build-backend = "poetry.core.masonry.api"

 [tool.commitizen]
-version = "1.65.7"
+version = "1.65.8"
 version_files = [
    "pyproject.toml:^version"
 ]
--- a/tests/litellm/llms/databricks/test_databricks_common_utils.py
+++ b/tests/litellm/llms/databricks/test_databricks_common_utils.py
@ -0,0 +1,32 @@
+import json
+import os
+import sys
+
+import pytest
+from fastapi.testclient import TestClient
+
+sys.path.insert(
+    0, os.path.abspath("../../../..")
+)  # Adds the parent directory to the system path
+from unittest.mock import MagicMock, patch
+
+from litellm.llms.databricks.common_utils import DatabricksBase
+
+
+def test_databricks_validate_environment():
+    databricks_base = DatabricksBase()
+
+    with patch.object(
+        databricks_base, "_get_databricks_credentials"
+    ) as mock_get_credentials:
+        try:
+            databricks_base.databricks_validate_environment(
+                api_key=None,
+                api_base="my_api_base",
+                endpoint_type="chat_completions",
+                custom_endpoint=False,
+                headers=None,
+            )
+        except Exception:
+            pass
+        mock_get_credentials.assert_called_once()
--- a/tests/litellm/proxy/management_endpoints/test_team_endpoints.py
+++ b/tests/litellm/proxy/management_endpoints/test_team_endpoints.py
@ -0,0 +1,161 @@
+import asyncio
+import json
+import os
+import sys
+import uuid
+from typing import Optional, cast
+from unittest.mock import AsyncMock, MagicMock, patch
+
+import pytest
+from fastapi import HTTPException
+from fastapi.testclient import TestClient
+
+sys.path.insert(
+    0, os.path.abspath("../../../")
+)  # Adds the parent directory to the system path
+from litellm.proxy._types import UserAPIKeyAuth  # Import UserAPIKeyAuth
+from litellm.proxy._types import LiteLLM_TeamTable, LitellmUserRoles
+from litellm.proxy.management_endpoints.team_endpoints import (
+    user_api_key_auth,  # Assuming this dependency is needed
+)
+from litellm.proxy.management_endpoints.team_endpoints import (
+    GetTeamMemberPermissionsResponse,
+    UpdateTeamMemberPermissionsRequest,
+    router,
+)
+from litellm.proxy.management_helpers.team_member_permission_checks import (
+    TeamMemberPermissionChecks,
+)
+from litellm.proxy.proxy_server import app
+
+# Setup TestClient
+client = TestClient(app)
+
+# Mock prisma_client
+mock_prisma_client = MagicMock()
+
+
+# Fixture to provide the mock prisma client
+@pytest.fixture(autouse=True)
+def mock_db_client():
+    with patch(
+        "litellm.proxy.proxy_server.prisma_client", mock_prisma_client
+    ):  # Mock in both places if necessary
+        yield mock_prisma_client
+    mock_prisma_client.reset_mock()
+
+
+# Fixture to provide a mock admin user auth object
+@pytest.fixture
+def mock_admin_auth():
+    mock_auth = UserAPIKeyAuth(user_role=LitellmUserRoles.PROXY_ADMIN)
+    return mock_auth
+
+
+# Test for /team/permissions_list endpoint (GET)
+@pytest.mark.asyncio
+async def test_get_team_permissions_list_success(mock_db_client, mock_admin_auth):
+    """
+    Test successful retrieval of team member permissions.
+    """
+    test_team_id = "test-team-123"
+    mock_team_data = {
+        "team_id": test_team_id,
+        "team_alias": "Test Team",
+        "team_member_permissions": ["/key/generate", "/key/update"],
+        "spend": 0.0,
+    }
+    mock_team_row = MagicMock()
+    mock_team_row.model_dump.return_value = mock_team_data
+    mock_db_client.db.litellm_teamtable.find_unique = AsyncMock(
+        return_value=mock_team_row
+    )
+
+    # Override the dependency for this test
+    app.dependency_overrides[user_api_key_auth] = lambda: mock_admin_auth
+
+    response = client.get(f"/team/permissions_list?team_id={test_team_id}")
+
+    assert response.status_code == 200
+    response_data = response.json()
+    assert response_data["team_id"] == test_team_id
+    assert (
+        response_data["team_member_permissions"]
+        == mock_team_data["team_member_permissions"]
+    )
+    assert (
+        response_data["all_available_permissions"]
+        == TeamMemberPermissionChecks.get_all_available_team_member_permissions()
+    )
+    mock_db_client.db.litellm_teamtable.find_unique.assert_awaited_once_with(
+        where={"team_id": test_team_id}
+    )
+
+    # Clean up dependency override
+    app.dependency_overrides = {}
+
+
+# Test for /team/permissions_update endpoint (POST)
+@pytest.mark.asyncio
+async def test_update_team_permissions_success(mock_db_client, mock_admin_auth):
+    """
+    Test successful update of team member permissions by an admin.
+    """
+    test_team_id = "test-team-456"
+    update_payload = {
+        "team_id": test_team_id,
+        "team_member_permissions": ["/key/generate", "/key/update"],
+    }
+
+    mock_existing_team_data = {
+        "team_id": test_team_id,
+        "team_alias": "Existing Team",
+        "team_member_permissions": ["/key/list"],
+        "spend": 0.0,
+        "models": [],
+    }
+    mock_updated_team_data = {
+        **mock_existing_team_data,
+        "team_member_permissions": update_payload["team_member_permissions"],
+    }
+
+    mock_existing_team_row = MagicMock(spec=LiteLLM_TeamTable)
+    mock_existing_team_row.model_dump.return_value = mock_existing_team_data
+    # Set attributes directly if model_dump isn't enough for LiteLLM_TeamTable usage
+    for key, value in mock_existing_team_data.items():
+        setattr(mock_existing_team_row, key, value)
+
+    mock_updated_team_row = MagicMock(spec=LiteLLM_TeamTable)
+    mock_updated_team_row.model_dump.return_value = mock_updated_team_data
+    # Set attributes directly if model_dump isn't enough for LiteLLM_TeamTable usage
+    for key, value in mock_updated_team_data.items():
+        setattr(mock_updated_team_row, key, value)
+
+    mock_db_client.db.litellm_teamtable.find_unique = AsyncMock(
+        return_value=mock_existing_team_row
+    )
+    mock_db_client.db.litellm_teamtable.update = AsyncMock(
+        return_value=mock_updated_team_row
+    )
+
+    # Override the dependency for this test
+    app.dependency_overrides[user_api_key_auth] = lambda: mock_admin_auth
+
+    response = client.post("/team/permissions_update", json=update_payload)
+
+    assert response.status_code == 200
+    response_data = response.json()
+
+    # Use model_dump for comparison if the endpoint returns the Prisma model directly
+    assert response_data == mock_updated_team_row.model_dump()
+
+    mock_db_client.db.litellm_teamtable.find_unique.assert_awaited_once_with(
+        where={"team_id": test_team_id}
+    )
+    mock_db_client.db.litellm_teamtable.update.assert_awaited_once_with(
+        where={"team_id": test_team_id},
+        data={"team_member_permissions": update_payload["team_member_permissions"]},
+    )
+
+    # Clean up dependency override
+    app.dependency_overrides = {}
--- a/tests/litellm/proxy/management_endpoints/test_ui_sso.py
+++ b/tests/litellm/proxy/management_endpoints/test_ui_sso.py
@ -19,6 +19,7 @@ from litellm.proxy._types import NewTeamRequest
 from litellm.proxy.auth.handle_jwt import JWTHandler
 from litellm.proxy.management_endpoints.types import CustomOpenID
 from litellm.proxy.management_endpoints.ui_sso import (
+    DefaultTeamSSOParams,
    GoogleSSOHandler,
    MicrosoftSSOHandler,
    SSOAuthenticationHandler,
@ -421,8 +422,10 @@ def test_get_group_ids_from_graph_api_response():
@pytest.mark.parametrize(
    "team_params",
    [
-        # Test case 1: Using NewTeamRequest
-        NewTeamRequest(max_budget=10, budget_duration="1d", models=["special-gpt-5"]),
+        # Test case 1: Using DefaultTeamSSOParams
+        DefaultTeamSSOParams(
+            max_budget=10, budget_duration="1d", models=["special-gpt-5"]
+        ),
        # Test case 2: Using Dict
        {"max_budget": 10, "budget_duration": "1d", "models": ["special-gpt-5"]},
    ],
--- a/tests/litellm/proxy/spend_tracking/test_spend_management_endpoints.py
+++ b/tests/litellm/proxy/spend_tracking/test_spend_management_endpoints.py
@ -457,7 +457,7 @@ class TestSpendLogsPayload:
                    "model": "gpt-4o",
                    "user": "",
                    "team_id": "",
-                    "metadata": '{"applied_guardrails": [], "batch_models": null, "mcp_tool_call_metadata": null, "usage_object": {"completion_tokens": 20, "prompt_tokens": 10, "total_tokens": 30, "completion_tokens_details": null, "prompt_tokens_details": null}, "model_map_information": {"model_map_key": "gpt-4o", "model_map_value": {"key": "gpt-4o", "max_tokens": 16384, "max_input_tokens": 128000, "max_output_tokens": 16384, "input_cost_per_token": 2.5e-06, "cache_creation_input_token_cost": null, "cache_read_input_token_cost": 1.25e-06, "input_cost_per_character": null, "input_cost_per_token_above_128k_tokens": null, "input_cost_per_token_above_200k_tokens": null, "input_cost_per_query": null, "input_cost_per_second": null, "input_cost_per_audio_token": null, "input_cost_per_token_batches": 1.25e-06, "output_cost_per_token_batches": 5e-06, "output_cost_per_token": 1e-05, "output_cost_per_audio_token": null, "output_cost_per_character": null, "output_cost_per_token_above_128k_tokens": null, "output_cost_per_character_above_128k_tokens": null, "output_cost_per_token_above_200k_tokens": null, "output_cost_per_second": null, "output_cost_per_image": null, "output_vector_size": null, "litellm_provider": "openai", "mode": "chat", "supports_system_messages": true, "supports_response_schema": true, "supports_vision": true, "supports_function_calling": true, "supports_tool_choice": true, "supports_assistant_prefill": false, "supports_prompt_caching": true, "supports_audio_input": false, "supports_audio_output": false, "supports_pdf_input": false, "supports_embedding_image_input": false, "supports_native_streaming": null, "supports_web_search": true, "search_context_cost_per_query": {"search_context_size_low": 0.03, "search_context_size_medium": 0.035, "search_context_size_high": 0.05}, "tpm": null, "rpm": null, "supported_openai_params": ["frequency_penalty", "logit_bias", "logprobs", "top_logprobs", "max_tokens", "max_completion_tokens", "modalities", "prediction", "n", "presence_penalty", "seed", "stop", "stream", "stream_options", "temperature", "top_p", "tools", "tool_choice", "function_call", "functions", "max_retries", "extra_headers", "parallel_tool_calls", "audio", "response_format", "user"]}}, "additional_usage_values": {"completion_tokens_details": null, "prompt_tokens_details": null}}',
+                    "metadata": '{"applied_guardrails": [], "batch_models": null, "mcp_tool_call_metadata": null, "usage_object": {"completion_tokens": 20, "prompt_tokens": 10, "total_tokens": 30, "completion_tokens_details": null, "prompt_tokens_details": null}, "model_map_information": {"model_map_key": "gpt-4o", "model_map_value": {"key": "gpt-4o", "max_tokens": 16384, "max_input_tokens": 128000, "max_output_tokens": 16384, "input_cost_per_token": 2.5e-06, "cache_creation_input_token_cost": null, "cache_read_input_token_cost": 1.25e-06, "input_cost_per_character": null, "input_cost_per_token_above_128k_tokens": null, "input_cost_per_token_above_200k_tokens": null, "input_cost_per_query": null, "input_cost_per_second": null, "input_cost_per_audio_token": null, "input_cost_per_token_batches": 1.25e-06, "output_cost_per_token_batches": 5e-06, "output_cost_per_token": 1e-05, "output_cost_per_audio_token": null, "output_cost_per_character": null, "output_cost_per_token_above_128k_tokens": null, "output_cost_per_character_above_128k_tokens": null, "output_cost_per_token_above_200k_tokens": null, "output_cost_per_second": null, "output_cost_per_image": null, "output_vector_size": null, "litellm_provider": "openai", "mode": "chat", "supports_system_messages": true, "supports_response_schema": true, "supports_vision": true, "supports_function_calling": true, "supports_tool_choice": true, "supports_assistant_prefill": false, "supports_prompt_caching": true, "supports_audio_input": false, "supports_audio_output": false, "supports_pdf_input": false, "supports_embedding_image_input": false, "supports_native_streaming": null, "supports_web_search": true, "supports_reasoning": false, "search_context_cost_per_query": {"search_context_size_low": 0.03, "search_context_size_medium": 0.035, "search_context_size_high": 0.05}, "tpm": null, "rpm": null, "supported_openai_params": ["frequency_penalty", "logit_bias", "logprobs", "top_logprobs", "max_tokens", "max_completion_tokens", "modalities", "prediction", "n", "presence_penalty", "seed", "stop", "stream", "stream_options", "temperature", "top_p", "tools", "tool_choice", "function_call", "functions", "max_retries", "extra_headers", "parallel_tool_calls", "audio", "response_format", "user"]}}, "additional_usage_values": {"completion_tokens_details": null, "prompt_tokens_details": null}}',
                    "cache_key": "Cache OFF",
                    "spend": 0.00022500000000000002,
                    "total_tokens": 30,
@ -555,7 +555,7 @@ class TestSpendLogsPayload:
                    "model": "claude-3-7-sonnet-20250219",
                    "user": "",
                    "team_id": "",
-                    "metadata": '{"applied_guardrails": [], "batch_models": null, "mcp_tool_call_metadata": null, "usage_object": {"completion_tokens": 503, "prompt_tokens": 2095, "total_tokens": 2598, "completion_tokens_details": null, "prompt_tokens_details": {"audio_tokens": null, "cached_tokens": 0}, "cache_creation_input_tokens": 0, "cache_read_input_tokens": 0}, "model_map_information": {"model_map_key": "claude-3-7-sonnet-20250219", "model_map_value": {"key": "claude-3-7-sonnet-20250219", "max_tokens": 128000, "max_input_tokens": 200000, "max_output_tokens": 128000, "input_cost_per_token": 3e-06, "cache_creation_input_token_cost": 3.75e-06, "cache_read_input_token_cost": 3e-07, "input_cost_per_character": null, "input_cost_per_token_above_128k_tokens": null, "input_cost_per_token_above_200k_tokens": null, "input_cost_per_query": null, "input_cost_per_second": null, "input_cost_per_audio_token": null, "input_cost_per_token_batches": null, "output_cost_per_token_batches": null, "output_cost_per_token": 1.5e-05, "output_cost_per_audio_token": null, "output_cost_per_character": null, "output_cost_per_token_above_128k_tokens": null, "output_cost_per_character_above_128k_tokens": null, "output_cost_per_token_above_200k_tokens": null, "output_cost_per_second": null, "output_cost_per_image": null, "output_vector_size": null, "litellm_provider": "anthropic", "mode": "chat", "supports_system_messages": null, "supports_response_schema": true, "supports_vision": true, "supports_function_calling": true, "supports_tool_choice": true, "supports_assistant_prefill": true, "supports_prompt_caching": true, "supports_audio_input": false, "supports_audio_output": false, "supports_pdf_input": true, "supports_embedding_image_input": false, "supports_native_streaming": null, "supports_web_search": false, "search_context_cost_per_query": null, "tpm": null, "rpm": null, "supported_openai_params": ["stream", "stop", "temperature", "top_p", "max_tokens", "max_completion_tokens", "tools", "tool_choice", "extra_headers", "parallel_tool_calls", "response_format", "user", "reasoning_effort", "thinking"]}}, "additional_usage_values": {"completion_tokens_details": null, "prompt_tokens_details": {"audio_tokens": null, "cached_tokens": 0, "text_tokens": null, "image_tokens": null}, "cache_creation_input_tokens": 0, "cache_read_input_tokens": 0}}',
+                    "metadata": '{"applied_guardrails": [], "batch_models": null, "mcp_tool_call_metadata": null, "usage_object": {"completion_tokens": 503, "prompt_tokens": 2095, "total_tokens": 2598, "completion_tokens_details": null, "prompt_tokens_details": {"audio_tokens": null, "cached_tokens": 0}, "cache_creation_input_tokens": 0, "cache_read_input_tokens": 0}, "model_map_information": {"model_map_key": "claude-3-7-sonnet-20250219", "model_map_value": {"key": "claude-3-7-sonnet-20250219", "max_tokens": 128000, "max_input_tokens": 200000, "max_output_tokens": 128000, "input_cost_per_token": 3e-06, "cache_creation_input_token_cost": 3.75e-06, "cache_read_input_token_cost": 3e-07, "input_cost_per_character": null, "input_cost_per_token_above_128k_tokens": null, "input_cost_per_token_above_200k_tokens": null, "input_cost_per_query": null, "input_cost_per_second": null, "input_cost_per_audio_token": null, "input_cost_per_token_batches": null, "output_cost_per_token_batches": null, "output_cost_per_token": 1.5e-05, "output_cost_per_audio_token": null, "output_cost_per_character": null, "output_cost_per_token_above_128k_tokens": null, "output_cost_per_character_above_128k_tokens": null, "output_cost_per_token_above_200k_tokens": null, "output_cost_per_second": null, "output_cost_per_image": null, "output_vector_size": null, "litellm_provider": "anthropic", "mode": "chat", "supports_system_messages": null, "supports_response_schema": true, "supports_vision": true, "supports_function_calling": true, "supports_tool_choice": true, "supports_assistant_prefill": true, "supports_prompt_caching": true, "supports_audio_input": false, "supports_audio_output": false, "supports_pdf_input": true, "supports_embedding_image_input": false, "supports_native_streaming": null, "supports_web_search": false, "supports_reasoning": true, "search_context_cost_per_query": null, "tpm": null, "rpm": null, "supported_openai_params": ["stream", "stop", "temperature", "top_p", "max_tokens", "max_completion_tokens", "tools", "tool_choice", "extra_headers", "parallel_tool_calls", "response_format", "user", "reasoning_effort", "thinking"]}}, "additional_usage_values": {"completion_tokens_details": null, "prompt_tokens_details": {"audio_tokens": null, "cached_tokens": 0, "text_tokens": null, "image_tokens": null}, "cache_creation_input_tokens": 0, "cache_read_input_tokens": 0}}',
                    "cache_key": "Cache OFF",
                    "spend": 0.01383,
                    "total_tokens": 2598,
@ -651,7 +651,7 @@ class TestSpendLogsPayload:
                    "model": "claude-3-7-sonnet-20250219",
                    "user": "",
                    "team_id": "",
-                    "metadata": '{"applied_guardrails": [], "batch_models": null, "mcp_tool_call_metadata": null, "usage_object": {"completion_tokens": 503, "prompt_tokens": 2095, "total_tokens": 2598, "completion_tokens_details": null, "prompt_tokens_details": {"audio_tokens": null, "cached_tokens": 0}, "cache_creation_input_tokens": 0, "cache_read_input_tokens": 0}, "model_map_information": {"model_map_key": "claude-3-7-sonnet-20250219", "model_map_value": {"key": "claude-3-7-sonnet-20250219", "max_tokens": 128000, "max_input_tokens": 200000, "max_output_tokens": 128000, "input_cost_per_token": 3e-06, "cache_creation_input_token_cost": 3.75e-06, "cache_read_input_token_cost": 3e-07, "input_cost_per_character": null, "input_cost_per_token_above_128k_tokens": null, "input_cost_per_token_above_200k_tokens": null, "input_cost_per_query": null, "input_cost_per_second": null, "input_cost_per_audio_token": null, "input_cost_per_token_batches": null, "output_cost_per_token_batches": null, "output_cost_per_token": 1.5e-05, "output_cost_per_audio_token": null, "output_cost_per_character": null, "output_cost_per_token_above_128k_tokens": null, "output_cost_per_character_above_128k_tokens": null, "output_cost_per_token_above_200k_tokens": null, "output_cost_per_second": null, "output_cost_per_image": null, "output_vector_size": null, "litellm_provider": "anthropic", "mode": "chat", "supports_system_messages": null, "supports_response_schema": true, "supports_vision": true, "supports_function_calling": true, "supports_tool_choice": true, "supports_assistant_prefill": true, "supports_prompt_caching": true, "supports_audio_input": false, "supports_audio_output": false, "supports_pdf_input": true, "supports_embedding_image_input": false, "supports_native_streaming": null, "supports_web_search": false, "search_context_cost_per_query": null, "tpm": null, "rpm": null, "supported_openai_params": ["stream", "stop", "temperature", "top_p", "max_tokens", "max_completion_tokens", "tools", "tool_choice", "extra_headers", "parallel_tool_calls", "response_format", "user", "reasoning_effort", "thinking"]}}, "additional_usage_values": {"completion_tokens_details": null, "prompt_tokens_details": {"audio_tokens": null, "cached_tokens": 0, "text_tokens": null, "image_tokens": null}, "cache_creation_input_tokens": 0, "cache_read_input_tokens": 0}}',
+                    "metadata": '{"applied_guardrails": [], "batch_models": null, "mcp_tool_call_metadata": null, "usage_object": {"completion_tokens": 503, "prompt_tokens": 2095, "total_tokens": 2598, "completion_tokens_details": null, "prompt_tokens_details": {"audio_tokens": null, "cached_tokens": 0}, "cache_creation_input_tokens": 0, "cache_read_input_tokens": 0}, "model_map_information": {"model_map_key": "claude-3-7-sonnet-20250219", "model_map_value": {"key": "claude-3-7-sonnet-20250219", "max_tokens": 128000, "max_input_tokens": 200000, "max_output_tokens": 128000, "input_cost_per_token": 3e-06, "cache_creation_input_token_cost": 3.75e-06, "cache_read_input_token_cost": 3e-07, "input_cost_per_character": null, "input_cost_per_token_above_128k_tokens": null, "input_cost_per_token_above_200k_tokens": null, "input_cost_per_query": null, "input_cost_per_second": null, "input_cost_per_audio_token": null, "input_cost_per_token_batches": null, "output_cost_per_token_batches": null, "output_cost_per_token": 1.5e-05, "output_cost_per_audio_token": null, "output_cost_per_character": null, "output_cost_per_token_above_128k_tokens": null, "output_cost_per_character_above_128k_tokens": null, "output_cost_per_token_above_200k_tokens": null, "output_cost_per_second": null, "output_cost_per_image": null, "output_vector_size": null, "litellm_provider": "anthropic", "mode": "chat", "supports_system_messages": null, "supports_response_schema": true, "supports_vision": true, "supports_function_calling": true, "supports_tool_choice": true, "supports_assistant_prefill": true, "supports_prompt_caching": true, "supports_audio_input": false, "supports_audio_output": false, "supports_pdf_input": true, "supports_embedding_image_input": false, "supports_native_streaming": null, "supports_web_search": false, "supports_reasoning": true, "search_context_cost_per_query": null, "tpm": null, "rpm": null, "supported_openai_params": ["stream", "stop", "temperature", "top_p", "max_tokens", "max_completion_tokens", "tools", "tool_choice", "extra_headers", "parallel_tool_calls", "response_format", "user", "reasoning_effort", "thinking"]}}, "additional_usage_values": {"completion_tokens_details": null, "prompt_tokens_details": {"audio_tokens": null, "cached_tokens": 0, "text_tokens": null, "image_tokens": null}, "cache_creation_input_tokens": 0, "cache_read_input_tokens": 0}}',
                    "cache_key": "Cache OFF",
                    "spend": 0.01383,
                    "total_tokens": 2598,
--- a/tests/litellm/proxy/ui_crud_endpoints/test_proxy_setting_endpoints.py
+++ b/tests/litellm/proxy/ui_crud_endpoints/test_proxy_setting_endpoints.py
@ -11,6 +11,7 @@ sys.path.insert(

 from litellm.proxy._types import DefaultInternalUserParams, LitellmUserRoles
 from litellm.proxy.proxy_server import app
+from litellm.types.proxy.management_endpoints.ui_sso import DefaultTeamSSOParams

 client = TestClient(app)

@ -25,7 +26,14 @@ def mock_proxy_config(monkeypatch):
                "max_budget": 100.0,
                "budget_duration": "30d",
                "models": ["gpt-3.5-turbo", "gpt-4"],
-            }
+            },
+            "default_team_params": {
+                "models": ["gpt-3.5-turbo"],
+                "max_budget": 50.0,
+                "budget_duration": "14d",
+                "tpm_limit": 100,
+                "rpm_limit": 10,
+            },
        }
    }

@ -138,3 +146,76 @@ class TestProxySettingEndpoints:

        # Verify save_config was called exactly once
        assert mock_proxy_config["save_call_count"]() == 1
+
+    def test_get_default_team_settings(self, mock_proxy_config, mock_auth):
+        """Test getting the default team settings"""
+        response = client.get("/get/default_team_settings")
+
+        assert response.status_code == 200
+        data = response.json()
+
+        # Check structure of response
+        assert "values" in data
+        assert "schema" in data
+
+        # Check values match our mock config
+        values = data["values"]
+        mock_params = mock_proxy_config["config"]["litellm_settings"][
+            "default_team_params"
+        ]
+        assert values["models"] == mock_params["models"]
+        assert values["max_budget"] == mock_params["max_budget"]
+        assert values["budget_duration"] == mock_params["budget_duration"]
+        assert values["tpm_limit"] == mock_params["tpm_limit"]
+        assert values["rpm_limit"] == mock_params["rpm_limit"]
+
+        # Check schema contains descriptions
+        assert "properties" in data["schema"]
+        assert "models" in data["schema"]["properties"]
+        assert "description" in data["schema"]["properties"]["models"]
+
+    def test_update_default_team_settings(
+        self, mock_proxy_config, mock_auth, monkeypatch
+    ):
+        """Test updating the default team settings"""
+        # Mock litellm.default_team_params
+        import litellm
+
+        monkeypatch.setattr(litellm, "default_team_params", {})
+
+        # New settings to update
+        new_settings = {
+            "models": ["gpt-4", "claude-3"],
+            "max_budget": 150.0,
+            "budget_duration": "30d",
+            "tpm_limit": 200,
+            "rpm_limit": 20,
+        }
+
+        response = client.patch("/update/default_team_settings", json=new_settings)
+
+        assert response.status_code == 200
+        data = response.json()
+
+        # Check response structure
+        assert data["status"] == "success"
+        assert "settings" in data
+
+        # Verify settings were updated
+        settings = data["settings"]
+        assert settings["models"] == new_settings["models"]
+        assert settings["max_budget"] == new_settings["max_budget"]
+        assert settings["budget_duration"] == new_settings["budget_duration"]
+        assert settings["tpm_limit"] == new_settings["tpm_limit"]
+        assert settings["rpm_limit"] == new_settings["rpm_limit"]
+
+        # Verify the config was updated
+        updated_config = mock_proxy_config["config"]["litellm_settings"][
+            "default_team_params"
+        ]
+        assert updated_config["models"] == new_settings["models"]
+        assert updated_config["max_budget"] == new_settings["max_budget"]
+        assert updated_config["tpm_limit"] == new_settings["tpm_limit"]
+
+        # Verify save_config was called exactly once
+        assert mock_proxy_config["save_call_count"]() == 1
--- a/tests/litellm_utils_tests/test_utils.py
+++ b/tests/litellm_utils_tests/test_utils.py
@ -514,6 +514,26 @@ def test_supports_web_search(model, expected_bool):
        pytest.fail(f"Error occurred: {e}")


+@pytest.mark.parametrize(
+    "model, expected_bool",
+    [
+        ("openai/o3-mini", True),
+        ("o3-mini", True),
+        ("xai/grok-3-mini-beta", True),
+        ("xai/grok-3-mini-fast-beta", True),
+        ("xai/grok-2", False),
+        ("gpt-3.5-turbo", False),
+    ],
+)
+def test_supports_reasoning(model, expected_bool):
+    os.environ["LITELLM_LOCAL_MODEL_COST_MAP"] = "True"
+    litellm.model_cost = litellm.get_model_cost_map(url="")
+    try:
+        assert litellm.supports_reasoning(model=model) == expected_bool
+    except Exception as e:
+        pytest.fail(f"Error occurred: {e}")
+
+
 def test_get_max_token_unit_test():
    """
    More complete testing in `test_completion_cost.py`
--- a/tests/llm_translation/base_llm_unit_tests.py
+++ b/tests/llm_translation/base_llm_unit_tests.py
@ -23,7 +23,7 @@ from litellm.utils import (
 )
 from litellm.main import stream_chunk_builder
 from typing import Union
-
+from litellm.types.utils import Usage, ModelResponse
 # test_example.py
 from abc import ABC, abstractmethod
 from openai import OpenAI
@ -1398,4 +1398,77 @@ class BaseAnthropicChatTest(ABC):
        )
        assert optional_params["thinking"] == {"type": "enabled", "budget_tokens": 4096}

-        assert "reasoning_effort" not in optional_params
+        assert "reasoning_effort" not in optional_params
+
+
+class BaseReasoningLLMTests(ABC):
+    """
+    Base class for testing reasoning llms
+
+    - test that the responses contain reasoning_content
+    - test that the usage contains reasoning_tokens
+    """
+    @abstractmethod
+    def get_base_completion_call_args(self) -> dict:
+        """Must return the base completion call args"""
+        pass
+    
+    @property
+    def completion_function(self):
+        return litellm.completion
+
+
+    def test_non_streaming_reasoning_effort(self):
+        """
+        Base test for non-streaming reasoning effort
+
+        - Assert that `reasoning_content` is not None from response message
+        - Assert that `reasoning_tokens` is greater than 0 from usage
+        """
+        litellm._turn_on_debug()
+        base_completion_call_args = self.get_base_completion_call_args()
+        response: ModelResponse = self.completion_function(**base_completion_call_args, reasoning_effort="low")
+        
+        # user gets `reasoning_content` in the response message
+        assert response.choices[0].message.reasoning_content is not None
+        assert isinstance(response.choices[0].message.reasoning_content, str)
+
+        # user get `reasoning_tokens`
+        assert response.usage.completion_tokens_details.reasoning_tokens > 0
+    
+
+    def test_streaming_reasoning_effort(self):
+        """
+        Base test for streaming reasoning effort
+
+        - Assert that `reasoning_content` is not None from streaming response
+        - Assert that `reasoning_tokens` is greater than 0 from usage
+        """
+        #litellm._turn_on_debug()
+        base_completion_call_args = self.get_base_completion_call_args()
+        response: CustomStreamWrapper = self.completion_function(
+            **base_completion_call_args,
+            reasoning_effort="low",
+            stream=True,
+            stream_options={
+                "include_usage": True
+            }
+        )
+        
+        resoning_content: str = ""
+        usage: Usage = None
+        for chunk in response:
+            print(chunk)
+            if hasattr(chunk.choices[0].delta, "reasoning_content"):
+                resoning_content += chunk.choices[0].delta.reasoning_content
+            if hasattr(chunk, "usage"):
+                usage = chunk.usage
+
+        assert resoning_content is not None
+        assert len(resoning_content) > 0
+
+        print(f"usage: {usage}")
+        assert usage.completion_tokens_details.reasoning_tokens > 0
+
+    
+    
--- a/tests/llm_translation/test_litellm_proxy_provider.py
+++ b/tests/llm_translation/test_litellm_proxy_provider.py
@ -449,3 +449,19 @@ def test_litellm_gateway_from_sdk_with_response_cost_in_additional_headers():
        )

        assert response._hidden_params["response_cost"] == 120
+
+
+def test_litellm_gateway_from_sdk_with_thinking_param():
+    try: 
+        response = litellm.completion(
+            model="litellm_proxy/anthropic.claude-3-7-sonnet-20250219-v1:0",
+            messages=[{"role": "user", "content": "Hello world"}],
+            api_base="http://0.0.0.0:4000",
+            api_key="sk-PIp1h0RekR",
+            # client=openai_client,
+            thinking={"type": "enabled", "max_budget": 100},
+        )
+        pytest.fail("Expected an error to be raised")
+    except Exception as e:
+        assert "Connection error." in str(e)
+    
--- a/tests/llm_translation/test_optional_params.py
+++ b/tests/llm_translation/test_optional_params.py
@ -1410,7 +1410,7 @@ def test_litellm_proxy_thinking_param():
        custom_llm_provider="litellm_proxy",
        thinking={"type": "enabled", "budget_tokens": 1024},
    )
-    assert optional_params["thinking"] == {"type": "enabled", "budget_tokens": 1024}
+    assert optional_params["extra_body"]["thinking"] == {"type": "enabled", "budget_tokens": 1024}

 def test_gemini_modalities_param():
    optional_params = get_optional_params(
--- a/tests/llm_translation/test_xai.py
+++ b/tests/llm_translation/test_xai.py
@ -18,6 +18,7 @@ from litellm import Choices, Message, ModelResponse, EmbeddingResponse, Usage
 from litellm import completion
 from unittest.mock import patch
 from litellm.llms.xai.chat.transformation import XAIChatConfig, XAI_API_BASE
+from base_llm_unit_tests import BaseReasoningLLMTests


 def test_xai_chat_config_get_openai_compatible_provider_info():
@ -160,3 +161,11 @@ def test_xai_message_name_filtering():
    )
    assert response is not None
    assert response.choices[0].message.content is not None
+
+
+class TestXAIReasoningEffort(BaseReasoningLLMTests):
+    def get_base_completion_call_args(self):
+        return {
+            "model": "xai/grok-3-mini-beta",
+            "messages": [{"role": "user", "content": "Hello"}],
+        }
--- a/tests/local_testing/test_embedding.py
+++ b/tests/local_testing/test_embedding.py
@ -1075,9 +1075,14 @@ def test_embedding_response_ratelimit_headers(model):
    hidden_params = response._hidden_params
    additional_headers = hidden_params.get("additional_headers", {})

-    print(additional_headers)
-    assert "x-ratelimit-remaining-requests" in additional_headers
-    assert int(additional_headers["x-ratelimit-remaining-requests"]) > 0
+    print("additional_headers", additional_headers)
+
+    # Azure is flaky with returning x-ratelimit-remaining-requests, we need to verify the upstream api returns this header
+    # if upstream api returns this header, we need to verify the header is transformed by litellm
+    if "llm_provider-x-ratelimit-limit-requests" in additional_headers or "x-ratelimit-limit-requests" in additional_headers:
+        assert "x-ratelimit-remaining-requests" in additional_headers
+        assert int(additional_headers["x-ratelimit-remaining-requests"]) > 0
+    
    assert "x-ratelimit-remaining-tokens" in additional_headers
    assert int(additional_headers["x-ratelimit-remaining-tokens"]) > 0

--- a/tests/local_testing/test_get_model_info.py
+++ b/tests/local_testing/test_get_model_info.py
@ -510,6 +510,7 @@ def test_aaamodel_prices_and_context_window_json_is_valid():
                "supports_video_input": {"type": "boolean"},
                "supports_vision": {"type": "boolean"},
                "supports_web_search": {"type": "boolean"},
+                "supports_reasoning": {"type": "boolean"},
                "tool_use_system_prompt_tokens": {"type": "number"},
                "tpm": {"type": "number"},
                "supported_endpoints": {
--- a/tests/logging_callback_tests/gcs_pub_sub_body/spend_logs_payload.json
+++ b/tests/logging_callback_tests/gcs_pub_sub_body/spend_logs_payload.json
@ -9,7 +9,7 @@
    "model": "gpt-4o",
    "user": "",
    "team_id": "",
-    "metadata": "{\"applied_guardrails\": [], \"batch_models\": null, \"mcp_tool_call_metadata\": null, \"usage_object\": {\"completion_tokens\": 20, \"prompt_tokens\": 10, \"total_tokens\": 30, \"completion_tokens_details\": null, \"prompt_tokens_details\": null}, \"model_map_information\": {\"model_map_key\": \"gpt-4o\", \"model_map_value\": {\"key\": \"gpt-4o\", \"max_tokens\": 16384, \"max_input_tokens\": 128000, \"max_output_tokens\": 16384, \"input_cost_per_token\": 2.5e-06, \"cache_creation_input_token_cost\": null, \"cache_read_input_token_cost\": 1.25e-06, \"input_cost_per_character\": null, \"input_cost_per_token_above_128k_tokens\": null, \"input_cost_per_token_above_200k_tokens\": null, \"input_cost_per_query\": null, \"input_cost_per_second\": null, \"input_cost_per_audio_token\": null, \"input_cost_per_token_batches\": 1.25e-06, \"output_cost_per_token_batches\": 5e-06, \"output_cost_per_token\": 1e-05, \"output_cost_per_audio_token\": null, \"output_cost_per_character\": null, \"output_cost_per_token_above_128k_tokens\": null, \"output_cost_per_character_above_128k_tokens\": null, \"output_cost_per_token_above_200k_tokens\": null, \"output_cost_per_second\": null, \"output_cost_per_image\": null, \"output_vector_size\": null, \"litellm_provider\": \"openai\", \"mode\": \"chat\", \"supports_system_messages\": true, \"supports_response_schema\": true, \"supports_vision\": true, \"supports_function_calling\": true, \"supports_tool_choice\": true, \"supports_assistant_prefill\": false, \"supports_prompt_caching\": true, \"supports_audio_input\": false, \"supports_audio_output\": false, \"supports_pdf_input\": false, \"supports_embedding_image_input\": false, \"supports_native_streaming\": null, \"supports_web_search\": true, \"search_context_cost_per_query\": {\"search_context_size_low\": 0.03, \"search_context_size_medium\": 0.035, \"search_context_size_high\": 0.05}, \"tpm\": null, \"rpm\": null, \"supported_openai_params\": [\"frequency_penalty\", \"logit_bias\", \"logprobs\", \"top_logprobs\", \"max_tokens\", \"max_completion_tokens\", \"modalities\", \"prediction\", \"n\", \"presence_penalty\", \"seed\", \"stop\", \"stream\", \"stream_options\", \"temperature\", \"top_p\", \"tools\", \"tool_choice\", \"function_call\", \"functions\", \"max_retries\", \"extra_headers\", \"parallel_tool_calls\", \"audio\", \"response_format\", \"user\"]}}, \"additional_usage_values\": {\"completion_tokens_details\": null, \"prompt_tokens_details\": null}}",
+    "metadata": "{\"applied_guardrails\": [], \"batch_models\": null, \"mcp_tool_call_metadata\": null, \"usage_object\": {\"completion_tokens\": 20, \"prompt_tokens\": 10, \"total_tokens\": 30, \"completion_tokens_details\": null, \"prompt_tokens_details\": null}, \"model_map_information\": {\"model_map_key\": \"gpt-4o\", \"model_map_value\": {\"key\": \"gpt-4o\", \"max_tokens\": 16384, \"max_input_tokens\": 128000, \"max_output_tokens\": 16384, \"input_cost_per_token\": 2.5e-06, \"cache_creation_input_token_cost\": null, \"cache_read_input_token_cost\": 1.25e-06, \"input_cost_per_character\": null, \"input_cost_per_token_above_128k_tokens\": null, \"input_cost_per_token_above_200k_tokens\": null, \"input_cost_per_query\": null, \"input_cost_per_second\": null, \"input_cost_per_audio_token\": null, \"input_cost_per_token_batches\": 1.25e-06, \"output_cost_per_token_batches\": 5e-06, \"output_cost_per_token\": 1e-05, \"output_cost_per_audio_token\": null, \"output_cost_per_character\": null, \"output_cost_per_token_above_128k_tokens\": null, \"output_cost_per_character_above_128k_tokens\": null, \"output_cost_per_token_above_200k_tokens\": null, \"output_cost_per_second\": null, \"output_cost_per_image\": null, \"output_vector_size\": null, \"litellm_provider\": \"openai\", \"mode\": \"chat\", \"supports_system_messages\": true, \"supports_response_schema\": true, \"supports_vision\": true, \"supports_function_calling\": true, \"supports_tool_choice\": true, \"supports_assistant_prefill\": false, \"supports_prompt_caching\": true, \"supports_audio_input\": false, \"supports_audio_output\": false, \"supports_pdf_input\": false, \"supports_embedding_image_input\": false, \"supports_native_streaming\": null, \"supports_web_search\": true, \"supports_reasoning\": false, \"search_context_cost_per_query\": {\"search_context_size_low\": 0.03, \"search_context_size_medium\": 0.035, \"search_context_size_high\": 0.05}, \"tpm\": null, \"rpm\": null, \"supported_openai_params\": [\"frequency_penalty\", \"logit_bias\", \"logprobs\", \"top_logprobs\", \"max_tokens\", \"max_completion_tokens\", \"modalities\", \"prediction\", \"n\", \"presence_penalty\", \"seed\", \"stop\", \"stream\", \"stream_options\", \"temperature\", \"top_p\", \"tools\", \"tool_choice\", \"function_call\", \"functions\", \"max_retries\", \"extra_headers\", \"parallel_tool_calls\", \"audio\", \"response_format\", \"user\"]}}, \"additional_usage_values\": {\"completion_tokens_details\": null, \"prompt_tokens_details\": null}}",
    "cache_key": "Cache OFF",
    "spend": 0.00022500000000000002,
    "total_tokens": 30,
--- a/ui/litellm-dashboard/package-lock.json
+++ b/ui/litellm-dashboard/package-lock.json
@ -22,7 +22,7 @@
        "jwt-decode": "^4.0.0",
        "moment": "^2.30.1",
        "next": "^14.2.26",
-        "openai": "^4.28.0",
+        "openai": "^4.93.0",
        "papaparse": "^5.5.2",
        "react": "^18",
        "react-copy-to-clipboard": "^5.1.0",
@ -1617,11 +1617,6 @@
      "resolved": "https://registry.npmjs.org/balanced-match/-/balanced-match-1.0.2.tgz",
      "integrity": "sha512-3oSeUO0TMV67hN1AmbXsK4yaqU7tjiHlbxRDZOpH0KW9+CeX4bRAaX0Anxt0tx2MrpRpWwQaPwIlISEJhYU5Pw=="
    },
-    "node_modules/base-64": {
-      "version": "0.1.0",
-      "resolved": "https://registry.npmjs.org/base-64/-/base-64-0.1.0.tgz",
-      "integrity": "sha512-Y5gU45svrR5tI2Vt/X9GPd3L0HNIKzGu202EjxrXMpuc2V2CiKgemAbUUsqYmZJvPtCXoUKjNZwBJzsNScUbXA=="
-    },
    "node_modules/binary-extensions": {
      "version": "2.2.0",
      "resolved": "https://registry.npmjs.org/binary-extensions/-/binary-extensions-2.2.0.tgz",
@ -1810,14 +1805,6 @@
        "url": "https://github.com/sponsors/wooorm"
      }
    },
-    "node_modules/charenc": {
-      "version": "0.0.2",
-      "resolved": "https://registry.npmjs.org/charenc/-/charenc-0.0.2.tgz",
-      "integrity": "sha512-yrLQ/yVUFXkzg7EDQsPieE/53+0RlaWTs+wBrvW36cyilJ2SaDWfl4Yj7MtLTXleV9uEKefbAGUPv2/iWSooRA==",
-      "engines": {
-        "node": "*"
-      }
-    },
    "node_modules/chokidar": {
      "version": "3.5.3",
      "resolved": "https://registry.npmjs.org/chokidar/-/chokidar-3.5.3.tgz",
@ -1949,14 +1936,6 @@
        "node": ">= 8"
      }
    },
-    "node_modules/crypt": {
-      "version": "0.0.2",
-      "resolved": "https://registry.npmjs.org/crypt/-/crypt-0.0.2.tgz",
-      "integrity": "sha512-mCxBlsHFYh9C+HVpiEacem8FEBnMXgU9gy4zmNC+SXAZNB/1idgp/aulFJ4FgCi7GPEVbfyng092GqL2k2rmow==",
-      "engines": {
-        "node": "*"
-      }
-    },
    "node_modules/cssesc": {
      "version": "3.0.0",
      "resolved": "https://registry.npmjs.org/cssesc/-/cssesc-3.0.0.tgz",
@ -2212,15 +2191,6 @@
      "resolved": "https://registry.npmjs.org/didyoumean/-/didyoumean-1.2.2.tgz",
      "integrity": "sha512-gxtyfqMg7GKyhQmb056K7M3xszy/myH8w+B4RT+QXBQsvAOdc3XymqDDPHx1BgPgsdAA5SIifona89YtRATDzw=="
    },
-    "node_modules/digest-fetch": {
-      "version": "1.3.0",
-      "resolved": "https://registry.npmjs.org/digest-fetch/-/digest-fetch-1.3.0.tgz",
-      "integrity": "sha512-CGJuv6iKNM7QyZlM2T3sPAdZWd/p9zQiRNS9G+9COUCwzWFTs0Xp8NF5iePx7wtvhDykReiRRrSeNb4oMmB8lA==",
-      "dependencies": {
-        "base-64": "^0.1.0",
-        "md5": "^2.3.0"
-      }
-    },
    "node_modules/dir-glob": {
      "version": "3.0.1",
      "resolved": "https://registry.npmjs.org/dir-glob/-/dir-glob-3.0.1.tgz",
@ -3694,11 +3664,6 @@
        "url": "https://github.com/sponsors/ljharb"
      }
    },
-    "node_modules/is-buffer": {
-      "version": "1.1.6",
-      "resolved": "https://registry.npmjs.org/is-buffer/-/is-buffer-1.1.6.tgz",
-      "integrity": "sha512-NcdALwpXkTm5Zvvbk7owOUSvVvBKDgKP5/ewfXEznmQFfs4ZRmanOeKBTjRVjka3QFoN6XJ+9F3USqfHqTaU5w=="
-    },
    "node_modules/is-callable": {
      "version": "1.2.7",
      "resolved": "https://registry.npmjs.org/is-callable/-/is-callable-1.2.7.tgz",
@ -4311,16 +4276,6 @@
        "node": "14 || >=16.14"
      }
    },
-    "node_modules/md5": {
-      "version": "2.3.0",
-      "resolved": "https://registry.npmjs.org/md5/-/md5-2.3.0.tgz",
-      "integrity": "sha512-T1GITYmFaKuO91vxyoQMFETst+O71VUPEU3ze5GNzDm0OWdP8v1ziTaAEPUr/3kLsY3Sftgz242A1SetQiDL7g==",
-      "dependencies": {
-        "charenc": "0.0.2",
-        "crypt": "0.0.2",
-        "is-buffer": "~1.1.6"
-      }
-    },
    "node_modules/mdast-util-from-markdown": {
      "version": "2.0.0",
      "resolved": "https://registry.npmjs.org/mdast-util-from-markdown/-/mdast-util-from-markdown-2.0.0.tgz",
@ -5282,22 +5237,32 @@
      }
    },
    "node_modules/openai": {
-      "version": "4.28.0",
-      "resolved": "https://registry.npmjs.org/openai/-/openai-4.28.0.tgz",
-      "integrity": "sha512-JM8fhcpmpGN0vrUwGquYIzdcEQHtFuom6sRCbbCM6CfzZXNuRk33G7KfeRAIfnaCxSpzrP5iHtwJzIm6biUZ2Q==",
+      "version": "4.93.0",
+      "resolved": "https://registry.npmjs.org/openai/-/openai-4.93.0.tgz",
+      "integrity": "sha512-2kONcISbThKLfm7T9paVzg+QCE1FOZtNMMUfXyXckUAoXRRS/mTP89JSDHPMp8uM5s0bz28RISbvQjArD6mgUQ==",
      "dependencies": {
        "@types/node": "^18.11.18",
        "@types/node-fetch": "^2.6.4",
        "abort-controller": "^3.0.0",
        "agentkeepalive": "^4.2.1",
-        "digest-fetch": "^1.3.0",
        "form-data-encoder": "1.7.2",
        "formdata-node": "^4.3.2",
-        "node-fetch": "^2.6.7",
-        "web-streams-polyfill": "^3.2.1"
+        "node-fetch": "^2.6.7"
      },
      "bin": {
        "openai": "bin/cli"
+      },
+      "peerDependencies": {
+        "ws": "^8.18.0",
+        "zod": "^3.23.8"
+      },
+      "peerDependenciesMeta": {
+        "ws": {
+          "optional": true
+        },
+        "zod": {
+          "optional": true
+        }
      }
    },
    "node_modules/openai/node_modules/@types/node": {
@ -7701,14 +7666,6 @@
        "d3-timer": "^3.0.1"
      }
    },
-    "node_modules/web-streams-polyfill": {
-      "version": "3.3.2",
-      "resolved": "https://registry.npmjs.org/web-streams-polyfill/-/web-streams-polyfill-3.3.2.tgz",
-      "integrity": "sha512-3pRGuxRF5gpuZc0W+EpwQRmCD7gRqcDOMt688KmdlDAgAyaB1XlN0zq2njfDNm44XVdIouE7pZ6GzbdyH47uIQ==",
-      "engines": {
-        "node": ">= 8"
-      }
-    },
    "node_modules/webidl-conversions": {
      "version": "3.0.1",
      "resolved": "https://registry.npmjs.org/webidl-conversions/-/webidl-conversions-3.0.1.tgz",
--- a/ui/litellm-dashboard/package.json
+++ b/ui/litellm-dashboard/package.json
@ -23,7 +23,7 @@
    "jwt-decode": "^4.0.0",
    "moment": "^2.30.1",
    "next": "^14.2.26",
-    "openai": "^4.28.0",
+    "openai": "^4.93.0",
    "papaparse": "^5.5.2",
    "react": "^18",
    "react-copy-to-clipboard": "^5.1.0",
--- a/ui/litellm-dashboard/src/components/TeamSSOSettings.tsx
+++ b/ui/litellm-dashboard/src/components/TeamSSOSettings.tsx
@ -0,0 +1,307 @@
+import React, { useState, useEffect } from "react";
+import { Card, Title, Text, Divider, Button, TextInput } from "@tremor/react";
+import { Typography, Spin, message, Switch, Select, Form } from "antd";
+import { getDefaultTeamSettings, updateDefaultTeamSettings, modelAvailableCall } from "./networking";
+import BudgetDurationDropdown, { getBudgetDurationLabel } from "./common_components/budget_duration_dropdown";
+import { getModelDisplayName } from "./key_team_helpers/fetch_available_models_team_key";
+
+interface TeamSSOSettingsProps {
+  accessToken: string | null;
+  userID: string;
+  userRole: string;
+}
+
+const TeamSSOSettings: React.FC<TeamSSOSettingsProps> = ({ accessToken, userID, userRole }) => {
+  const [loading, setLoading] = useState<boolean>(true);
+  const [settings, setSettings] = useState<any>(null);
+  const [isEditing, setIsEditing] = useState<boolean>(false);
+  const [editedValues, setEditedValues] = useState<any>({});
+  const [saving, setSaving] = useState<boolean>(false);
+  const [availableModels, setAvailableModels] = useState<string[]>([]);
+  const { Paragraph } = Typography;
+  const { Option } = Select;
+
+  useEffect(() => {
+    const fetchTeamSSOSettings = async () => {
+      if (!accessToken) {
+        setLoading(false);
+        return;
+      }
+
+      try {
+        const data = await getDefaultTeamSettings(accessToken);
+        setSettings(data);
+        setEditedValues(data.values || {});
+        
+        // Fetch available models
+        if (accessToken) {
+          try {
+            const modelResponse = await modelAvailableCall(accessToken, userID, userRole);
+            if (modelResponse && modelResponse.data) {
+              const modelNames = modelResponse.data.map((model: { id: string }) => model.id);
+              setAvailableModels(modelNames);
+            }
+          } catch (error) {
+            console.error("Error fetching available models:", error);
+          }
+        }
+      } catch (error) {
+        console.error("Error fetching team SSO settings:", error);
+        message.error("Failed to fetch team settings");
+      } finally {
+        setLoading(false);
+      }
+    };
+
+    fetchTeamSSOSettings();
+  }, [accessToken]);
+
+  const handleSaveSettings = async () => {
+    if (!accessToken) return;
+    
+    setSaving(true);
+    try {
+      const updatedSettings = await updateDefaultTeamSettings(accessToken, editedValues);
+      setSettings({...settings, values: updatedSettings.settings});
+      setIsEditing(false);
+      message.success("Default team settings updated successfully");
+    } catch (error) {
+      console.error("Error updating team settings:", error);
+      message.error("Failed to update team settings");
+    } finally {
+      setSaving(false);
+    }
+  };
+
+  const handleTextInputChange = (key: string, value: any) => {
+    setEditedValues((prev: Record<string, any>) => ({
+      ...prev,
+      [key]: value
+    }));
+  };
+
+  const renderEditableField = (key: string, property: any, value: any) => {
+    const type = property.type;
+    
+    if (key === "budget_duration") {
+      return (
+        <BudgetDurationDropdown
+          value={editedValues[key] || null}
+          onChange={(value) => handleTextInputChange(key, value)}
+          className="mt-2"
+        />
+      );
+    } else if (type === "boolean") {
+      return (
+        <div className="mt-2">
+          <Switch 
+            checked={!!editedValues[key]} 
+            onChange={(checked) => handleTextInputChange(key, checked)}
+          />
+        </div>
+      );
+    } else if (type === "array" && property.items?.enum) {
+      return (
+        <Select
+          mode="multiple"
+          style={{ width: '100%' }}
+          value={editedValues[key] || []}
+          onChange={(value) => handleTextInputChange(key, value)}
+          className="mt-2"
+        >
+          {property.items.enum.map((option: string) => (
+            <Option key={option} value={option}>{option}</Option>
+          ))}
+        </Select>
+      );
+    } else if (key === "models") {
+      return (
+        <Select
+          mode="multiple"
+          style={{ width: '100%' }}
+          value={editedValues[key] || []}
+          onChange={(value) => handleTextInputChange(key, value)}
+          className="mt-2"
+        >
+          {availableModels.map((model: string) => (
+            <Option key={model} value={model}>
+              {getModelDisplayName(model)}
+            </Option>
+          ))}
+        </Select>
+      );
+    } else if (type === "string" && property.enum) {
+      return (
+        <Select
+          style={{ width: '100%' }}
+          value={editedValues[key] || ""}
+          onChange={(value) => handleTextInputChange(key, value)}
+          className="mt-2"
+        >
+          {property.enum.map((option: string) => (
+            <Option key={option} value={option}>{option}</Option>
+          ))}
+        </Select>
+      );
+    } else {
+      return (
+        <TextInput 
+          value={editedValues[key] !== undefined ? String(editedValues[key]) : ""} 
+          onChange={(e) => handleTextInputChange(key, e.target.value)}
+          placeholder={property.description || ""}
+          className="mt-2"
+        />
+      );
+    }
+  };
+
+  const renderValue = (key: string, value: any): JSX.Element => {
+    if (value === null || value === undefined) return <span className="text-gray-400">Not set</span>;
+    
+    if (key === "budget_duration") {
+      return <span>{getBudgetDurationLabel(value)}</span>;
+    }
+    
+    if (typeof value === "boolean") {
+      return <span>{value ? "Enabled" : "Disabled"}</span>;
+    }
+    
+    if (key === "models" && Array.isArray(value)) {
+      if (value.length === 0) return <span className="text-gray-400">None</span>;
+      
+      return (
+        <div className="flex flex-wrap gap-2 mt-1">
+          {value.map((model, index) => (
+            <span key={index} className="px-2 py-1 bg-blue-100 rounded text-xs">
+              {getModelDisplayName(model)}
+            </span>
+          ))}
+        </div>
+      );
+    }
+    
+    if (typeof value === "object") {
+      if (Array.isArray(value)) {
+        if (value.length === 0) return <span className="text-gray-400">None</span>;
+        
+        return (
+          <div className="flex flex-wrap gap-2 mt-1">
+            {value.map((item, index) => (
+              <span key={index} className="px-2 py-1 bg-blue-100 rounded text-xs">
+                {typeof item === "object" ? JSON.stringify(item) : String(item)}
+              </span>
+            ))}
+          </div>
+        );
+      }
+      
+      return (
+        <pre className="bg-gray-100 p-2 rounded text-xs overflow-auto mt-1">
+          {JSON.stringify(value, null, 2)}
+        </pre>
+      );
+    }
+    
+    return <span>{String(value)}</span>;
+  };
+
+  if (loading) {
+    return (
+      <div className="flex justify-center items-center h-64">
+        <Spin size="large" />
+      </div>
+    );
+  }
+
+  if (!settings) {
+    return (
+      <Card>
+        <Text>No team settings available or you do not have permission to view them.</Text>
+      </Card>
+    );
+  }
+
+  // Dynamically render settings based on the schema
+  const renderSettings = () => {
+    const { values, schema } = settings;
+    
+    if (!schema || !schema.properties) {
+      return <Text>No schema information available</Text>;
+    }
+
+    return Object.entries(schema.properties).map(([key, property]: [string, any]) => {
+      const value = values[key];
+      const displayName = key.replace(/_/g, ' ').replace(/\b\w/g, l => l.toUpperCase());
+      
+      return (
+        <div key={key} className="mb-6 pb-6 border-b border-gray-200 last:border-0">
+          <Text className="font-medium text-lg">{displayName}</Text>
+          <Paragraph className="text-sm text-gray-500 mt-1">
+            {property.description || "No description available"}
+          </Paragraph>
+          
+          {isEditing ? (
+            <div className="mt-2">
+              {renderEditableField(key, property, value)}
+            </div>
+          ) : (
+            <div className="mt-1 p-2 bg-gray-50 rounded">
+              {renderValue(key, value)}
+            </div>
+          )}
+        </div>
+      );
+    });
+  };
+
+  return (
+    <Card>
+      <div className="flex justify-between items-center mb-4">
+        <Title className="text-xl">Default Team Settings</Title>
+        {!loading && settings && (
+          isEditing ? (
+            <div className="flex gap-2">
+              <Button 
+                variant="secondary"
+                onClick={() => {
+                  setIsEditing(false);
+                  setEditedValues(settings.values || {});
+                }}
+                disabled={saving}
+              >
+                Cancel
+              </Button>
+              <Button 
+                onClick={handleSaveSettings}
+                loading={saving}
+              >
+                Save Changes
+              </Button>
+            </div>
+          ) : (
+            <Button 
+              onClick={() => setIsEditing(true)}
+            >
+              Edit Settings
+            </Button>
+          )
+        )}
+      </div>
+      
+      <Text>
+        These settings will be applied by default when creating new teams.
+      </Text>
+      
+      {settings?.schema?.description && (
+        <Paragraph className="mb-4 mt-2">{settings.schema.description}</Paragraph>
+      )}
+      <Divider />
+      
+      <div className="mt-4 space-y-4">
+        {renderSettings()}
+      </div>
+    </Card>
+  );
+};
+
+export default TeamSSOSettings; 
--- a/ui/litellm-dashboard/src/components/chat_ui.tsx
+++ b/ui/litellm-dashboard/src/components/chat_ui.tsx
@ -23,7 +23,7 @@ import {
  Divider,
 } from "@tremor/react";

-import { message, Select, Spin, Typography, Tooltip } from "antd";
+import { message, Select, Spin, Typography, Tooltip, Input } from "antd";
 import { makeOpenAIChatCompletionRequest } from "./chat_ui/llm_calls/chat_completion";
 import { makeOpenAIImageGenerationRequest } from "./chat_ui/llm_calls/image_generation";
 import { fetchAvailableModels, ModelGroup  } from "./chat_ui/llm_calls/fetch_models";
@ -33,6 +33,9 @@ import { coy } from 'react-syntax-highlighter/dist/esm/styles/prism';
 import EndpointSelector from "./chat_ui/EndpointSelector";
 import TagSelector from "./tag_management/TagSelector";
 import { determineEndpointType } from "./chat_ui/EndpointUtils";
+import { MessageType } from "./chat_ui/types";
+import ReasoningContent from "./chat_ui/ReasoningContent";
+import ResponseMetrics, { TokenUsage } from "./chat_ui/ResponseMetrics";
 import { 
  SendOutlined, 
  ApiOutlined, 
@ -45,6 +48,8 @@ import {
  TagsOutlined
 } from "@ant-design/icons";

+const { TextArea } = Input;
+
 interface ChatUIProps {
  accessToken: string | null;
  token: string | null;
@ -65,7 +70,7 @@ const ChatUI: React.FC<ChatUIProps> = ({
  );
  const [apiKey, setApiKey] = useState("");
  const [inputMessage, setInputMessage] = useState("");
-  const [chatHistory, setChatHistory] = useState<{ role: string; content: string; model?: string; isImage?: boolean }[]>([]);
+  const [chatHistory, setChatHistory] = useState<MessageType[]>([]);
  const [selectedModel, setSelectedModel] = useState<string | undefined>(
    undefined
  );
@ -138,7 +143,11 @@ const ChatUI: React.FC<ChatUIProps> = ({
      if (lastMessage && lastMessage.role === role && !lastMessage.isImage) {
        return [
          ...prevHistory.slice(0, prevHistory.length - 1),
-          { role, content: lastMessage.content + chunk, model },
+          { 
+            ...lastMessage,
+            content: lastMessage.content + chunk, 
+            model 
+          },
        ];
      } else {
        return [...prevHistory, { role, content: chunk, model }];
@ -146,6 +155,97 @@ const ChatUI: React.FC<ChatUIProps> = ({
    });
  };

+  const updateReasoningContent = (chunk: string) => {
+    setChatHistory((prevHistory) => {
+      const lastMessage = prevHistory[prevHistory.length - 1];
+      
+      if (lastMessage && lastMessage.role === "assistant" && !lastMessage.isImage) {
+        return [
+          ...prevHistory.slice(0, prevHistory.length - 1),
+          { 
+            ...lastMessage,
+            reasoningContent: (lastMessage.reasoningContent || "") + chunk 
+          },
+        ];
+      } else {
+        // If there's no assistant message yet, we'll create one with empty content
+        // but with reasoning content
+        if (prevHistory.length > 0 && prevHistory[prevHistory.length - 1].role === "user") {
+          return [
+            ...prevHistory,
+            { 
+              role: "assistant", 
+              content: "", 
+              reasoningContent: chunk 
+            }
+          ];
+        }
+        
+        return prevHistory;
+      }
+    });
+  };
+
+  const updateTimingData = (timeToFirstToken: number) => {
+    console.log("updateTimingData called with:", timeToFirstToken);
+    setChatHistory((prevHistory) => {
+      const lastMessage = prevHistory[prevHistory.length - 1];
+      console.log("Current last message:", lastMessage);
+      
+      if (lastMessage && lastMessage.role === "assistant") {
+        console.log("Updating assistant message with timeToFirstToken:", timeToFirstToken);
+        const updatedHistory = [
+          ...prevHistory.slice(0, prevHistory.length - 1),
+          { 
+            ...lastMessage,
+            timeToFirstToken
+          },
+        ];
+        console.log("Updated chat history:", updatedHistory);
+        return updatedHistory;
+      } 
+      // If the last message is a user message and no assistant message exists yet,
+      // create a new assistant message with empty content
+      else if (lastMessage && lastMessage.role === "user") {
+        console.log("Creating new assistant message with timeToFirstToken:", timeToFirstToken);
+        return [
+          ...prevHistory,
+          { 
+            role: "assistant", 
+            content: "", 
+            timeToFirstToken 
+          }
+        ];
+      }
+      
+      console.log("No appropriate message found to update timing");
+      return prevHistory;
+    });
+  };
+
+  const updateUsageData = (usage: TokenUsage) => {
+    console.log("Received usage data:", usage);
+    setChatHistory((prevHistory) => {
+      const lastMessage = prevHistory[prevHistory.length - 1];
+      
+      if (lastMessage && lastMessage.role === "assistant") {
+        console.log("Updating message with usage data:", usage);
+        const updatedMessage = { 
+          ...lastMessage,
+          usage
+        };
+        console.log("Updated message:", updatedMessage);
+        
+        return [
+          ...prevHistory.slice(0, prevHistory.length - 1),
+          updatedMessage
+        ];
+      }
+      
+      return prevHistory;
+    });
+  };
+
  const updateImageUI = (imageUrl: string, model: string) => {
    setChatHistory((prevHistory) => [
      ...prevHistory,
@ -153,10 +253,12 @@ const ChatUI: React.FC<ChatUIProps> = ({
    ]);
  };

-  const handleKeyDown = (event: React.KeyboardEvent<HTMLInputElement>) => {
-    if (event.key === 'Enter') {
+  const handleKeyDown = (event: React.KeyboardEvent<HTMLTextAreaElement>) => {
+    if (event.key === 'Enter' && !event.shiftKey) {
+      event.preventDefault(); // Prevent default to avoid newline
      handleSendMessage();
    }
+    // If Shift+Enter is pressed, the default behavior (inserting a newline) will occur
  };

  const handleCancelRequest = () => {
@ -206,7 +308,10 @@ const ChatUI: React.FC<ChatUIProps> = ({
            selectedModel,
            effectiveApiKey,
            selectedTags,
-            signal
+            signal,
+            updateReasoningContent,
+            updateTimingData,
+            updateUsageData
          );
        } else if (endpointType === EndpointType.IMAGE) {
          // For image generation
@ -410,7 +515,16 @@ const ChatUI: React.FC<ChatUIProps> = ({
                      </span>
                    )}
                  </div>
-                  <div className="whitespace-pre-wrap break-words max-w-full message-content">
+                  {message.reasoningContent && (
+                    <ReasoningContent reasoningContent={message.reasoningContent} />
+                  )}
+                  <div className="whitespace-pre-wrap break-words max-w-full message-content" 
+                       style={{ 
+                         wordWrap: 'break-word', 
+                         overflowWrap: 'break-word',
+                         wordBreak: 'break-word',
+                         hyphens: 'auto'
+                       }}>
                    {message.isImage ? (
                      <img 
                        src={message.content} 
@ -432,21 +546,33 @@ const ChatUI: React.FC<ChatUIProps> = ({
                                language={match[1]}
                                PreTag="div"
                                className="rounded-md my-2"
+                                wrapLines={true}
+                                wrapLongLines={true}
                                {...props}
                              >
                                {String(children).replace(/\n$/, '')}
                              </SyntaxHighlighter>
                            ) : (
-                              <code className={`${className} px-1.5 py-0.5 rounded bg-gray-100 text-sm font-mono`} {...props}>
+                              <code className={`${className} px-1.5 py-0.5 rounded bg-gray-100 text-sm font-mono`} style={{ wordBreak: 'break-word' }} {...props}>
                                {children}
                              </code>
                            );
-                          }
+                          },
+                          pre: ({ node, ...props }) => (
+                            <pre style={{ overflowX: 'auto', maxWidth: '100%' }} {...props} />
+                          )
                        }}
                      >
                        {message.content}
                      </ReactMarkdown>
                    )}
+                                        
+                    {message.role === "assistant" && (message.timeToFirstToken || message.usage) && (
+                      <ResponseMetrics 
+                        timeToFirstToken={message.timeToFirstToken}
+                        usage={message.usage}
+                      />
+                    )}
                  </div>
                </div>
              </div>
@ -461,18 +587,19 @@ const ChatUI: React.FC<ChatUIProps> = ({
          
          <div className="p-4 border-t border-gray-200 bg-white">
            <div className="flex items-center">
-              <TextInput
-                type="text"
+              <TextArea
                value={inputMessage}
                onChange={(e) => setInputMessage(e.target.value)}
                onKeyDown={handleKeyDown}
                placeholder={
                  endpointType === EndpointType.CHAT 
-                    ? "Type your message..." 
+                    ? "Type your message... (Shift+Enter for new line)" 
                    : "Describe the image you want to generate..."
                }
                disabled={isLoading}
                className="flex-1"
+                autoSize={{ minRows: 1, maxRows: 6 }}
+                style={{ resize: 'none', paddingRight: '10px', paddingLeft: '10px' }}
              />
              {isLoading ? (
                <Button
--- a/ui/litellm-dashboard/src/components/chat_ui/ReasoningContent.tsx
+++ b/ui/litellm-dashboard/src/components/chat_ui/ReasoningContent.tsx
@ -0,0 +1,64 @@
+import React, { useState } from "react";
+import { Button, Collapse } from "antd";
+import ReactMarkdown from "react-markdown";
+import { Prism as SyntaxHighlighter } from "react-syntax-highlighter";
+import { coy } from 'react-syntax-highlighter/dist/esm/styles/prism';
+import { DownOutlined, RightOutlined, BulbOutlined } from "@ant-design/icons";
+
+interface ReasoningContentProps {
+  reasoningContent: string;
+}
+
+const ReasoningContent: React.FC<ReasoningContentProps> = ({ reasoningContent }) => {
+  const [isExpanded, setIsExpanded] = useState(true);
+
+  if (!reasoningContent) return null;
+
+  return (
+    <div className="reasoning-content mt-1 mb-2">
+      <Button 
+        type="text" 
+        className="flex items-center text-xs text-gray-500 hover:text-gray-700"
+        onClick={() => setIsExpanded(!isExpanded)}
+        icon={<BulbOutlined />}
+      >
+        {isExpanded ? "Hide reasoning" : "Show reasoning"}
+        {isExpanded ? <DownOutlined className="ml-1" /> : <RightOutlined className="ml-1" />}
+      </Button>
+      
+      {isExpanded && (
+        <div className="mt-2 p-3 bg-gray-50 border border-gray-200 rounded-md text-sm text-gray-700">
+          <ReactMarkdown
+            components={{
+              code({node, inline, className, children, ...props}: React.ComponentPropsWithoutRef<'code'> & {
+                inline?: boolean;
+                node?: any;
+              }) {
+                const match = /language-(\w+)/.exec(className || '');
+                return !inline && match ? (
+                  <SyntaxHighlighter
+                    style={coy as any}
+                    language={match[1]}
+                    PreTag="div"
+                    className="rounded-md my-2"
+                    {...props}
+                  >
+                    {String(children).replace(/\n$/, '')}
+                  </SyntaxHighlighter>
+                ) : (
+                  <code className={`${className} px-1.5 py-0.5 rounded bg-gray-100 text-sm font-mono`} {...props}>
+                    {children}
+                  </code>
+                );
+              }
+            }}
+          >
+            {reasoningContent}
+          </ReactMarkdown>
+        </div>
+      )}
+    </div>
+  );
+};
+
+export default ReasoningContent; 
--- a/ui/litellm-dashboard/src/components/chat_ui/ResponseMetrics.tsx
+++ b/ui/litellm-dashboard/src/components/chat_ui/ResponseMetrics.tsx
@ -0,0 +1,80 @@
+import React from "react";
+import { Tooltip } from "antd";
+import { 
+  ClockCircleOutlined, 
+  NumberOutlined, 
+  ImportOutlined, 
+  ExportOutlined,
+  ThunderboltOutlined,
+  BulbOutlined
+} from "@ant-design/icons";
+
+export interface TokenUsage {
+  completionTokens?: number;
+  promptTokens?: number;
+  totalTokens?: number;
+  reasoningTokens?: number;
+}
+
+interface ResponseMetricsProps {
+  timeToFirstToken?: number; // in milliseconds
+  usage?: TokenUsage;
+}
+
+const ResponseMetrics: React.FC<ResponseMetricsProps> = ({ 
+  timeToFirstToken, 
+  usage 
+}) => {
+  if (!timeToFirstToken && !usage) return null;
+
+  return (
+    <div className="response-metrics mt-2 pt-2 border-t border-gray-100 text-xs text-gray-500 flex flex-wrap gap-3">
+      {timeToFirstToken !== undefined && (
+        <Tooltip title="Time to first token">
+          <div className="flex items-center">
+            <ClockCircleOutlined className="mr-1" />
+            <span>{(timeToFirstToken / 1000).toFixed(2)}s</span>
+          </div>
+        </Tooltip>
+      )}
+      
+      {usage?.promptTokens !== undefined && (
+        <Tooltip title="Prompt tokens">
+          <div className="flex items-center">
+            <ImportOutlined className="mr-1" />
+            <span>In: {usage.promptTokens}</span>
+          </div>
+        </Tooltip>
+      )}
+      
+      {usage?.completionTokens !== undefined && (
+        <Tooltip title="Completion tokens">
+          <div className="flex items-center">
+            <ExportOutlined className="mr-1" />
+            <span>Out: {usage.completionTokens}</span>
+          </div>
+        </Tooltip>
+      )}
+      
+      {usage?.reasoningTokens !== undefined && (
+        <Tooltip title="Reasoning tokens">
+          <div className="flex items-center">
+            <BulbOutlined className="mr-1" />
+            <span>Reasoning: {usage.reasoningTokens}</span>
+          </div>
+        </Tooltip>
+      )}
+      
+      {usage?.totalTokens !== undefined && (
+        <Tooltip title="Total tokens">
+          <div className="flex items-center">
+            <NumberOutlined className="mr-1" />
+            <span>Total: {usage.totalTokens}</span>
+          </div>
+        </Tooltip>
+      )}
+    </div>
+  );
+};
+
+export default ResponseMetrics; 
--- a/ui/litellm-dashboard/src/components/chat_ui/llm_calls/chat_completion.tsx
+++ b/ui/litellm-dashboard/src/components/chat_ui/llm_calls/chat_completion.tsx
@ -1,14 +1,18 @@
 import openai from "openai";
 import { ChatCompletionMessageParam } from "openai/resources/chat/completions";
 import { message } from "antd";
+import { TokenUsage } from "../ResponseMetrics";

 export async function makeOpenAIChatCompletionRequest(
    chatHistory: { role: string; content: string }[],
-    updateUI: (chunk: string, model: string) => void,
+    updateUI: (chunk: string, model?: string) => void,
    selectedModel: string,
    accessToken: string,
    tags?: string[],
-    signal?: AbortSignal
+    signal?: AbortSignal,
+    onReasoningContent?: (content: string) => void,
+    onTimingData?: (timeToFirstToken: number) => void,
+    onUsageData?: (usage: TokenUsage) => void
  ) {
    // base url should be the current base_url
    const isLocal = process.env.NODE_ENV === "development";
@ -20,23 +24,85 @@ export async function makeOpenAIChatCompletionRequest(
      ? "http://localhost:4000"
      : window.location.origin;
    const client = new openai.OpenAI({
-      apiKey: accessToken, // Replace with your OpenAI API key
-      baseURL: proxyBaseUrl, // Replace with your OpenAI API base URL
-      dangerouslyAllowBrowser: true, // using a temporary litellm proxy key
+      apiKey: accessToken,
+      baseURL: proxyBaseUrl,
+      dangerouslyAllowBrowser: true,
      defaultHeaders: tags && tags.length > 0 ? { 'x-litellm-tags': tags.join(',') } : undefined,
    });
  
    try {
+      const startTime = Date.now();
+      let firstTokenReceived = false;
+      let timeToFirstToken: number | undefined = undefined;
+      
+      // For collecting complete response text
+      let fullResponseContent = "";
+      let fullReasoningContent = "";
+
      const response = await client.chat.completions.create({
        model: selectedModel,
        stream: true,
+        stream_options: {
+          include_usage: true,
+        },
        messages: chatHistory as ChatCompletionMessageParam[],
      }, { signal });
  
      for await (const chunk of response) {
-        console.log(chunk);
-        if (chunk.choices[0].delta.content) {
-          updateUI(chunk.choices[0].delta.content, chunk.model);
+        console.log("Stream chunk:", chunk);
+        
+        // Process content and measure time to first token
+        const delta = chunk.choices[0]?.delta as any;
+        
+        // Debug what's in the delta
+        console.log("Delta content:", chunk.choices[0]?.delta?.content);
+        console.log("Delta reasoning content:", delta?.reasoning_content);
+        
+        // Measure time to first token for either content or reasoning_content
+        if (!firstTokenReceived && (chunk.choices[0]?.delta?.content || (delta && delta.reasoning_content))) {
+          firstTokenReceived = true;
+          timeToFirstToken = Date.now() - startTime;
+          console.log("First token received! Time:", timeToFirstToken, "ms");
+          if (onTimingData) {
+            console.log("Calling onTimingData with:", timeToFirstToken);
+            onTimingData(timeToFirstToken);
+          } else {
+            console.log("onTimingData callback is not defined!");
+          }
+        }
+        
+        // Process content
+        if (chunk.choices[0]?.delta?.content) {
+          const content = chunk.choices[0].delta.content;
+          updateUI(content, chunk.model);
+          fullResponseContent += content;
+        }
+        
+        // Process reasoning content if present - using type assertion
+        if (delta && delta.reasoning_content) {
+          const reasoningContent = delta.reasoning_content;
+          if (onReasoningContent) {
+            onReasoningContent(reasoningContent);
+          }
+          fullReasoningContent += reasoningContent;
+        }
+        
+        // Check for usage data using type assertion
+        const chunkWithUsage = chunk as any;
+        if (chunkWithUsage.usage && onUsageData) {
+          console.log("Usage data found:", chunkWithUsage.usage);
+          const usageData: TokenUsage = {
+            completionTokens: chunkWithUsage.usage.completion_tokens,
+            promptTokens: chunkWithUsage.usage.prompt_tokens,
+            totalTokens: chunkWithUsage.usage.total_tokens,
+          };
+          
+          // Check for reasoning tokens
+          if (chunkWithUsage.usage.completion_tokens_details?.reasoning_tokens) {
+            usageData.reasoningTokens = chunkWithUsage.usage.completion_tokens_details.reasoning_tokens;
+          }
+          
+          onUsageData(usageData);
        }
      }
    } catch (error) {
--- a/ui/litellm-dashboard/src/components/chat_ui/llm_calls/process_stream.tsx
+++ b/ui/litellm-dashboard/src/components/chat_ui/llm_calls/process_stream.tsx
@ -0,0 +1,96 @@
+import { TokenUsage } from "../ResponseMetrics";
+
+export interface StreamingResponse {
+  id: string;
+  created: number;
+  model: string;
+  object: string;
+  system_fingerprint?: string;
+  choices: StreamingChoices[];
+  provider_specific_fields?: any;
+  stream_options?: any;
+  citations?: any;
+  usage?: Usage;
+}
+
+export interface StreamingChoices {
+  finish_reason?: string | null;
+  index: number;
+  delta: Delta;
+  logprobs?: any;
+}
+
+export interface Delta {
+  content?: string;
+  reasoning_content?: string;
+  role?: string;
+  function_call?: any;
+  tool_calls?: any;
+  audio?: any;
+  refusal?: any;
+  provider_specific_fields?: any;
+}
+
+export interface Usage {
+  completion_tokens: number;
+  prompt_tokens: number;
+  total_tokens: number;
+  completion_tokens_details?: {
+    accepted_prediction_tokens?: number;
+    audio_tokens?: number;
+    reasoning_tokens?: number;
+    rejected_prediction_tokens?: number;
+    text_tokens?: number | null;
+  };
+  prompt_tokens_details?: {
+    audio_tokens?: number;
+    cached_tokens?: number;
+    text_tokens?: number;
+    image_tokens?: number;
+  };
+}
+
+export interface StreamProcessCallbacks {
+  onContent: (content: string, model?: string) => void;
+  onReasoningContent: (content: string) => void;
+  onUsage?: (usage: TokenUsage) => void;
+}
+
+export const processStreamingResponse = (
+  response: StreamingResponse, 
+  callbacks: StreamProcessCallbacks
+) => {
+  // Extract model information if available
+  const model = response.model;
+  
+  // Process regular content
+  if (response.choices && response.choices.length > 0) {
+    const choice = response.choices[0];
+    
+    if (choice.delta?.content) {
+      callbacks.onContent(choice.delta.content, model);
+    }
+    
+    // Process reasoning content if it exists
+    if (choice.delta?.reasoning_content) {
+      callbacks.onReasoningContent(choice.delta.reasoning_content);
+    }
+  }
+  
+  // Process usage information if it exists and we have a handler
+  if (response.usage && callbacks.onUsage) {
+    console.log("Processing usage data:", response.usage);
+    const usageData: TokenUsage = {
+      completionTokens: response.usage.completion_tokens,
+      promptTokens: response.usage.prompt_tokens,
+      totalTokens: response.usage.total_tokens,
+    };
+    
+    // Extract reasoning tokens if available
+    if (response.usage.completion_tokens_details?.reasoning_tokens) {
+      usageData.reasoningTokens = response.usage.completion_tokens_details.reasoning_tokens;
+    }
+    
+    callbacks.onUsage(usageData);
+  }
+}; 
--- a/ui/litellm-dashboard/src/components/chat_ui/types.ts
+++ b/ui/litellm-dashboard/src/components/chat_ui/types.ts
@ -0,0 +1,68 @@
+export interface Delta {
+  content?: string;
+  reasoning_content?: string;
+  role?: string;
+  function_call?: any;
+  tool_calls?: any;
+  audio?: any;
+  refusal?: any;
+  provider_specific_fields?: any;
+}
+
+export interface CompletionTokensDetails {
+  accepted_prediction_tokens?: number;
+  audio_tokens?: number;
+  reasoning_tokens?: number;
+  rejected_prediction_tokens?: number;
+  text_tokens?: number | null;
+}
+
+export interface PromptTokensDetails {
+  audio_tokens?: number;
+  cached_tokens?: number;
+  text_tokens?: number;
+  image_tokens?: number;
+}
+
+export interface Usage {
+  completion_tokens: number;
+  prompt_tokens: number;
+  total_tokens: number;
+  completion_tokens_details?: CompletionTokensDetails;
+  prompt_tokens_details?: PromptTokensDetails;
+}
+
+export interface StreamingChoices {
+  finish_reason?: string | null;
+  index: number;
+  delta: Delta;
+  logprobs?: any;
+}
+
+export interface StreamingResponse {
+  id: string;
+  created: number;
+  model: string;
+  object: string;
+  system_fingerprint?: string;
+  choices: StreamingChoices[];
+  provider_specific_fields?: any;
+  stream_options?: any;
+  citations?: any;
+  usage?: Usage;
+}
+
+export interface MessageType {
+  role: string;
+  content: string;
+  model?: string;
+  isImage?: boolean;
+  reasoningContent?: string;
+  timeToFirstToken?: number;
+  usage?: {
+    completionTokens?: number;
+    promptTokens?: number;
+    totalTokens?: number;
+    reasoningTokens?: number;
+  };
+} 
--- a/ui/litellm-dashboard/src/components/model_dashboard.tsx
+++ b/ui/litellm-dashboard/src/components/model_dashboard.tsx
@ -1023,6 +1023,7 @@ const ModelDashboard: React.FC<ModelDashboardProps> = ({
          is_proxy_admin={userRole === "Proxy Admin"}
          userModels={all_models_on_proxy}
          editTeam={false}
+          onUpdate={handleRefreshClick}
        />
      </div>
    );
--- a/ui/litellm-dashboard/src/components/networking.tsx
+++ b/ui/litellm-dashboard/src/components/networking.tsx
@ -4344,4 +4344,146 @@ export const tagDeleteCall = async (
    console.error("Error deleting tag:", error);
    throw error;
  }
+};
+
+export const getDefaultTeamSettings = async (accessToken: string) => {
+  try {
+    // Construct base URL
+    let url = proxyBaseUrl 
+      ? `${proxyBaseUrl}/get/default_team_settings`
+      : `/get/default_team_settings`;
+
+    console.log("Fetching default team settings from:", url);
+    
+    const response = await fetch(url, {
+      method: "GET",
+      headers: {
+        [globalLitellmHeaderName]: `Bearer ${accessToken}`,
+        "Content-Type": "application/json",
+      },
+    });
+
+    if (!response.ok) {
+      const errorData = await response.text();
+      handleError(errorData);
+      throw new Error("Network response was not ok");
+    }
+
+    const data = await response.json();
+    console.log("Fetched default team settings:", data);
+    return data;
+  } catch (error) {
+    console.error("Failed to fetch default team settings:", error);
+    throw error;
+  }
+};
+
+
+export const updateDefaultTeamSettings = async (accessToken: string, settings: Record<string, any>) => {
+  try {
+    // Construct base URL
+    let url = proxyBaseUrl 
+      ? `${proxyBaseUrl}/update/default_team_settings`
+      : `/update/default_team_settings`;
+
+    console.log("Updating default team settings:", settings);
+    
+    const response = await fetch(url, {
+      method: "PATCH",
+      headers: {
+        [globalLitellmHeaderName]: `Bearer ${accessToken}`,
+        "Content-Type": "application/json",
+      },
+      body: JSON.stringify(settings),
+    });
+
+    if (!response.ok) {
+      const errorData = await response.text();
+      handleError(errorData);
+      throw new Error("Network response was not ok");
+    }
+
+    const data = await response.json();
+    console.log("Updated default team settings:", data);
+    message.success("Default team settings updated successfully");
+    return data;
+  } catch (error) {
+    console.error("Failed to update default team settings:", error);
+    throw error;
+  }
+};
+
+
+
+export const getTeamPermissionsCall = async (
+  accessToken: string,
+  teamId: string
+) => {
+  try {
+    let url = proxyBaseUrl 
+      ? `${proxyBaseUrl}/team/permissions_list?team_id=${teamId}`
+      : `/team/permissions_list?team_id=${teamId}`;
+
+    const response = await fetch(url, {
+      method: "GET",
+      headers: {
+        "Content-Type": "application/json",
+        Authorization: `Bearer ${accessToken}`,
+      },
+    });
+
+    if (!response.ok) {
+      const errorData = await response.text();
+      handleError(errorData);
+      throw new Error("Network response was not ok");
+    }
+
+    const data = await response.json();
+    console.log("Team permissions response:", data);
+    return data;
+  } catch (error) {
+    console.error("Failed to get team permissions:", error);
+    throw error;
+  }
+};
+
+
+
+export const teamPermissionsUpdateCall = async (
+  accessToken: string,
+  teamId: string,
+  permissions: string[]
+) => {
+  try {
+    let url = proxyBaseUrl  
+      ? `${proxyBaseUrl}/team/permissions_update`
+      : `/team/permissions_update`;
+
+
+    const response = await fetch(url, {
+      method: "POST",
+      headers: {
+        "Content-Type": "application/json",
+        Authorization: `Bearer ${accessToken}`,
+      },
+      body: JSON.stringify({
+        team_id: teamId,
+        team_member_permissions: permissions,
+      }),
+    });
+
+    if (!response.ok) {
+      const errorData = await response.text();
+      handleError(errorData);
+      throw new Error("Network response was not ok");
+    }
+
+
+    const data = await response.json();
+    console.log("Team permissions response:", data);
+    return data;
+  } catch (error) {
+    console.error("Failed to update team permissions:", error);
+    throw error;
+  }
 };
--- a/ui/litellm-dashboard/src/components/team/member_permissions.tsx
+++ b/ui/litellm-dashboard/src/components/team/member_permissions.tsx
@ -0,0 +1,175 @@
+import React, { useState, useEffect } from "react";
+import {
+  Card,
+  Title,
+  Text,
+  Button as TremorButton,
+  Table,
+  TableHead,
+  TableHeaderCell,
+  TableBody,
+  TableRow,
+  TableCell,
+} from "@tremor/react";
+import { Button, message, Checkbox, Empty } from "antd";
+import { ReloadOutlined, SaveOutlined } from "@ant-design/icons";
+import { getTeamPermissionsCall, teamPermissionsUpdateCall } from "@/components/networking";
+import { getPermissionInfo } from "./permission_definitions";
+
+interface MemberPermissionsProps {
+  teamId: string;
+  accessToken: string | null;
+  canEditTeam: boolean;
+}
+
+const MemberPermissions: React.FC<MemberPermissionsProps> = ({
+  teamId,
+  accessToken,
+  canEditTeam,
+}) => {
+  const [permissions, setPermissions] = useState<string[]>([]);
+  const [selectedPermissions, setSelectedPermissions] = useState<string[]>([]);
+  const [loading, setLoading] = useState(true);
+  const [saving, setSaving] = useState(false);
+  const [hasChanges, setHasChanges] = useState(false);
+
+  const fetchPermissions = async () => {
+    try {
+      setLoading(true);
+      if (!accessToken) return;
+      const response = await getTeamPermissionsCall(accessToken, teamId);
+      const allPermissions = response.all_available_permissions || [];
+      setPermissions(allPermissions);
+      const teamPermissions = response.team_member_permissions || [];
+      setSelectedPermissions(teamPermissions);
+      setHasChanges(false);
+    } catch (error) {
+      message.error("Failed to load permissions");
+      console.error("Error fetching permissions:", error);
+    } finally {
+      setLoading(false);
+    }
+  };
+
+  useEffect(() => {
+    fetchPermissions();
+  }, [teamId, accessToken]);
+
+  const handlePermissionChange = (permission: string, checked: boolean) => {
+    const newSelectedPermissions = checked
+      ? [...selectedPermissions, permission]
+      : selectedPermissions.filter((p) => p !== permission);
+    setSelectedPermissions(newSelectedPermissions);
+    setHasChanges(true);
+  };
+
+  const handleSave = async () => {
+    try {
+      if (!accessToken) return;
+      setSaving(true);
+      await teamPermissionsUpdateCall(accessToken, teamId, selectedPermissions);
+      message.success("Permissions updated successfully");
+      setHasChanges(false);
+    } catch (error) {
+      message.error("Failed to update permissions");
+      console.error("Error updating permissions:", error);
+    } finally {
+      setSaving(false);
+    }
+  };
+
+  const handleReset = () => {
+    fetchPermissions();
+  };
+
+  if (loading) {
+    return <div className="p-6 text-center">Loading permissions...</div>;
+  }
+
+  const hasPermissions = permissions.length > 0;
+
+  return (
+    <Card className="bg-white shadow-md rounded-md p-6">
+      <div className="flex flex-col sm:flex-row justify-between items-start sm:items-center border-b pb-4 mb-6">
+        <Title className="mb-2 sm:mb-0">Member Permissions</Title>
+        {canEditTeam && hasChanges && (
+          <div className="flex gap-3">
+            <Button icon={<ReloadOutlined />} onClick={handleReset}>
+              Reset
+            </Button>
+            <TremorButton
+              onClick={handleSave}
+              loading={saving}
+              className="flex items-center gap-2"
+            >
+              <SaveOutlined /> Save Changes
+            </TremorButton>
+          </div>
+        )}
+      </div>
+
+      <Text className="mb-6 text-gray-600">
+        Control what team members can do when they are not team admins.
+      </Text>
+
+      {hasPermissions ? (
+        <Table className="mt-4">
+          <TableHead>
+            <TableRow>
+              <TableHeaderCell>Method</TableHeaderCell>
+              <TableHeaderCell>Endpoint</TableHeaderCell>
+              <TableHeaderCell>Description</TableHeaderCell>
+              <TableHeaderCell className="text-right">Access</TableHeaderCell>
+            </TableRow>
+          </TableHead>
+          <TableBody>
+            {permissions.map((permission) => {
+              const permInfo = getPermissionInfo(permission);
+              return (
+                <TableRow
+                  key={permission}
+                  className="hover:bg-gray-50 transition-colors"
+                >
+                  <TableCell>
+                    <span
+                      className={`px-2 py-1 rounded text-xs font-medium ${
+                        permInfo.method === "GET"
+                          ? "bg-blue-100 text-blue-800"
+                          : "bg-green-100 text-green-800"
+                      }`}
+                    >
+                      {permInfo.method}
+                    </span>
+                  </TableCell>
+                  <TableCell>
+                    <span className="font-mono text-sm text-gray-800">
+                      {permInfo.endpoint}
+                    </span>
+                  </TableCell>
+                  <TableCell className="text-gray-700">
+                    {permInfo.description}
+                  </TableCell>
+                  <TableCell className="text-right">
+                    <Checkbox
+                      checked={selectedPermissions.includes(permission)}
+                      onChange={(e) =>
+                        handlePermissionChange(permission, e.target.checked)
+                      }
+                      disabled={!canEditTeam}
+                    />
+                  </TableCell>
+                </TableRow>
+              );
+            })}
+          </TableBody>
+        </Table>
+      ) : (
+        <div className="py-12">
+          <Empty description="No permissions available" />
+        </div>
+      )}
+    </Card>
+  );
+};
+
+export default MemberPermissions;
--- a/ui/litellm-dashboard/src/components/team/permission_definitions.tsx
+++ b/ui/litellm-dashboard/src/components/team/permission_definitions.tsx
@ -0,0 +1,64 @@
+export interface PermissionInfo {
+  method: string;
+  endpoint: string;
+  description: string;
+  route: string;
+}
+
+/**
+ * Map of permission endpoint patterns to their descriptions
+ */
+export const PERMISSION_DESCRIPTIONS: Record<string, string> = {
+  '/key/generate': 'Member can generate a virtual key for this team',
+  '/key/update': 'Member can update a virtual key belonging to this team',
+  '/key/delete': 'Member can delete a virtual key belonging to this team',
+  '/key/info': 'Member can get info about a virtual key belonging to this team',
+  '/key/regenerate': 'Member can regenerate a virtual key belonging to this team',
+  '/key/{key_id}/regenerate': 'Member can regenerate a virtual key belonging to this team',
+  '/key/list': 'Member can list virtual keys belonging to this team',
+  '/key/block': 'Member can block a virtual key belonging to this team',
+  '/key/unblock': 'Member can unblock a virtual key belonging to this team'
+};
+
+/**
+ * Determines the HTTP method for a given permission endpoint
+ */
+export const getMethodForEndpoint = (endpoint: string): string => {
+  if (endpoint.includes('/info') || endpoint.includes('/list')) {
+    return 'GET';
+  }
+  return 'POST';
+};
+
+/**
+ * Parses a permission string into a structured PermissionInfo object
+ */
+export const getPermissionInfo = (permission: string): PermissionInfo => {
+  const method = getMethodForEndpoint(permission);
+  const endpoint = permission;
+  
+  // Find exact match or fallback to default description
+  let description = PERMISSION_DESCRIPTIONS[permission];
+  
+  // If no exact match, try to find a partial match based on patterns
+  if (!description) {
+    for (const [pattern, desc] of Object.entries(PERMISSION_DESCRIPTIONS)) {
+      if (permission.includes(pattern)) {
+        description = desc;
+        break;
+      }
+    }
+  }
+  
+  // Fallback if no match found
+  if (!description) {
+    description = `Access ${permission}`;
+  }
+  
+  return {
+    method,
+    endpoint,
+    description,
+    route: permission
+  };
+}; 
--- a/ui/litellm-dashboard/src/components/team/team_info.tsx
+++ b/ui/litellm-dashboard/src/components/team/team_info.tsx
@ -20,6 +20,8 @@ import {
  Table,
  Icon
 } from "@tremor/react";
+import TeamMembersComponent from "./team_member_view";
+import MemberPermissions from "./member_permissions";
 import { teamInfoCall, teamMemberDeleteCall, teamMemberAddCall, teamMemberUpdateCall, Member, teamUpdateCall } from "@/components/networking";
 import { Button, Form, Input, Select, message, Tooltip } from "antd";
 import { InfoCircleOutlined } from '@ant-design/icons';
@ -30,10 +32,9 @@ import { PencilAltIcon, PlusIcon, TrashIcon } from "@heroicons/react/outline";
 import MemberModal from "./edit_membership";
 import UserSearchModal from "@/components/common_components/user_search_modal";
 import { getModelDisplayName } from "../key_team_helpers/fetch_available_models_team_key";
-import { Team } from "../key_team_helpers/key_list";


-interface TeamData {
+export interface TeamData {
  team_id: string;
  team_info: {
    team_alias: string;
@ -62,15 +63,15 @@ interface TeamData {
  team_memberships: any[];
 }

-interface TeamInfoProps {
+export interface TeamInfoProps {
  teamId: string;
+  onUpdate: (data: any) => void;
  onClose: () => void;
  accessToken: string | null;
  is_team_admin: boolean;
  is_proxy_admin: boolean;
  userModels: string[];
  editTeam: boolean;
-  onUpdate?: (team: Team) => void
 }

 const TeamInfoView: React.FC<TeamInfoProps> = ({ 
@ -80,8 +81,7 @@ const TeamInfoView: React.FC<TeamInfoProps> = ({
  is_team_admin, 
  is_proxy_admin,
  userModels,
-  editTeam,
-  onUpdate
+  editTeam
 }) => {
  const [teamData, setTeamData] = useState<TeamData | null>(null);
  const [loading, setLoading] = useState(true);
@ -202,10 +202,7 @@ const TeamInfoView: React.FC<TeamInfoProps> = ({
      };
      
      const response = await teamUpdateCall(accessToken, updateData);
-      if (onUpdate) {
-        onUpdate(response.data)
-      }
-    
+      
      message.success("Team settings updated successfully");
      setIsEditing(false);
      fetchTeamInfo();
@ -241,6 +238,7 @@ const TeamInfoView: React.FC<TeamInfoProps> = ({
            <Tab key="overview">Overview</Tab>,
            ...(canEditTeam ? [
              <Tab key="members">Members</Tab>,
+              <Tab key="member-permissions">Member Permissions</Tab>,
              <Tab key="settings">Settings</Tab>
            ] : [])
          ]}
@ -287,58 +285,23 @@ const TeamInfoView: React.FC<TeamInfoProps> = ({

          {/* Members Panel */}
          <TabPanel>
-            <div className="space-y-4">
-              <Card className="w-full mx-auto flex-auto overflow-y-auto max-h-[50vh]">
-                <Table>
-                  <TableHead>
-                    <TableRow>
-                      <TableHeaderCell>User ID</TableHeaderCell>
-                      <TableHeaderCell>User Email</TableHeaderCell>
-                      <TableHeaderCell>Role</TableHeaderCell>
-                      <TableHeaderCell></TableHeaderCell>
-                    </TableRow>
-                  </TableHead>
+            <TeamMembersComponent
+              teamData={teamData}
+              canEditTeam={canEditTeam}
+              handleMemberDelete={handleMemberDelete}
+              setSelectedEditMember={setSelectedEditMember}
+              setIsEditMemberModalVisible={setIsEditMemberModalVisible}
+              setIsAddMemberModalVisible={setIsAddMemberModalVisible}
+            />
+          </TabPanel>

-                  <TableBody>
-                    {teamData.team_info.members_with_roles.map((member: Member, index: number) => (
-                      <TableRow key={index}>
-                        <TableCell>
-                          <Text className="font-mono">{member.user_id}</Text>
-                        </TableCell>
-                        <TableCell>
-                          <Text className="font-mono">{member.user_email}</Text>
-                        </TableCell>
-                        <TableCell>
-                          <Text className="font-mono">{member.role}</Text>
-                        </TableCell>
-                        <TableCell>
-                          {canEditTeam && (
-                            <>
-                              <Icon
-                                icon={PencilAltIcon}
-                                size="sm"
-                                onClick={() => {
-                                  setSelectedEditMember(member);
-                                  setIsEditMemberModalVisible(true);
-                                }}
-                              />
-                              <Icon
-                                onClick={() => handleMemberDelete(member)}
-                                icon={TrashIcon}
-                                size="sm"
-                              />
-                            </>
-                          )}
-                        </TableCell>
-                      </TableRow>
-                    ))}
-                  </TableBody>
-                </Table>
-              </Card>
-              <TremorButton onClick={() => setIsAddMemberModalVisible(true)}>
-                Add Member
-              </TremorButton>
-            </div>
+          {/* Member Permissions Panel */}
+          <TabPanel>
+            <MemberPermissions 
+              teamId={teamId}
+              accessToken={accessToken}
+              canEditTeam={canEditTeam}
+            />
          </TabPanel>

          {/* Settings Panel */}
--- a/ui/litellm-dashboard/src/components/team/team_member_view.tsx
+++ b/ui/litellm-dashboard/src/components/team/team_member_view.tsx
@ -0,0 +1,93 @@
+import React from 'react';
+import { Member } from "@/components/networking";
+import {
+  Card,
+  Table,
+  TableHead,
+  TableRow,
+  TableHeaderCell,
+  TableBody,
+  TableCell,
+  Text,
+  Icon,
+  Button as TremorButton,
+} from '@tremor/react';
+import {
+    TeamData,
+} from './team_info';
+import { PencilAltIcon, PlusIcon, TrashIcon } from "@heroicons/react/outline";
+
+interface TeamMembersComponentProps {
+  teamData: TeamData;
+  canEditTeam: boolean;
+  handleMemberDelete: (member: Member) => void;
+  setSelectedEditMember: (member: Member) => void;
+  setIsEditMemberModalVisible: (visible: boolean) => void;
+  setIsAddMemberModalVisible: (visible: boolean) => void;
+}
+
+const TeamMembersComponent: React.FC<TeamMembersComponentProps> = ({
+  teamData,
+  canEditTeam,
+  handleMemberDelete,
+  setSelectedEditMember,
+  setIsEditMemberModalVisible,
+  setIsAddMemberModalVisible,
+}) => {
+  return (
+    <div className="space-y-4">
+      <Card className="w-full mx-auto flex-auto overflow-y-auto max-h-[50vh]">
+        <Table>
+          <TableHead>
+            <TableRow>
+              <TableHeaderCell>User ID</TableHeaderCell>
+              <TableHeaderCell>User Email</TableHeaderCell>
+              <TableHeaderCell>Role</TableHeaderCell>
+              <TableHeaderCell></TableHeaderCell>
+            </TableRow>
+          </TableHead>
+
+          <TableBody>
+            {teamData.team_info.members_with_roles.map((member: Member, index: number) => (
+              <TableRow key={index}>
+                <TableCell>
+                  <Text className="font-mono">{member.user_id}</Text>
+                </TableCell>
+                <TableCell>
+                  <Text className="font-mono">{member.user_email}</Text>
+                </TableCell>
+                <TableCell>
+                  <Text className="font-mono">{member.role}</Text>
+                </TableCell>
+                <TableCell>
+                  {canEditTeam && (
+                    <>
+                      <Icon
+                        icon={PencilAltIcon}
+                        size="sm"
+                        onClick={() => {
+                          setSelectedEditMember(member);
+                          setIsEditMemberModalVisible(true);
+                        }}
+                      />
+                      <Icon
+                        icon={TrashIcon}
+                        size="sm"
+                        onClick={() => handleMemberDelete(member)}
+                      />
+                    </>
+                  )}
+                </TableCell>
+              </TableRow>
+            ))}
+          </TableBody>
+        </Table>
+      </Card>
+      <TremorButton onClick={() => setIsAddMemberModalVisible(true)}>
+        Add Member
+      </TremorButton>
+    </div>
+  );
+};
+
+export default TeamMembersComponent;
--- a/ui/litellm-dashboard/src/components/teams.tsx
+++ b/ui/litellm-dashboard/src/components/teams.tsx
@ -27,6 +27,8 @@ import { Select, SelectItem } from "@tremor/react";
 import { InfoCircleOutlined } from '@ant-design/icons';
 import { getGuardrailsList } from "./networking";
 import TeamInfoView from "@/components/team/team_info";
+import TeamSSOSettings from "@/components/TeamSSOSettings";
+import { isAdminRole } from "@/utils/roles";
 import {
  Table,
  TableBody,
@ -322,7 +324,7 @@ const Teams: React.FC<TeamProps> = ({
      {selectedTeamId ? (
        <TeamInfoView 
        teamId={selectedTeamId} 
-        onUpdate={data => {
+        onUpdate={(data) => {
            setTeams(teams => {
              if (teams == null) {
                return teams;
@ -354,6 +356,7 @@ const Teams: React.FC<TeamProps> = ({
        <div className="flex">
          <Tab>Your Teams</Tab>
          <Tab>Available Teams</Tab>
+          {isAdminRole(userRole || "") && <Tab>Default Team Settings</Tab>}
          </div>
          <div className="flex items-center space-x-2">
            {lastRefreshed && <Text>Last Refreshed: {lastRefreshed}</Text>}
@ -797,6 +800,15 @@ const Teams: React.FC<TeamProps> = ({
          userID={userID}
        />
      </TabPanel>
+      {isAdminRole(userRole || "") && (
+        <TabPanel>
+          <TeamSSOSettings
+            accessToken={accessToken}
+            userID={userID || ""}
+            userRole={userRole || ""}
+          />
+        </TabPanel>
+      )}
      </TabPanels>

      </TabGroup>)}
--- a/ui/litellm-dashboard/src/utils/roles.ts
+++ b/ui/litellm-dashboard/src/utils/roles.ts
@ -5,4 +5,10 @@ export const all_admin_roles = [...old_admin_roles, ...v2_admin_role_names];

 export const internalUserRoles = ["Internal User", "Internal Viewer"];
 export const rolesAllowedToSeeUsage = ["Admin", "Admin Viewer", "Internal User", "Internal Viewer"]; 
-export const rolesWithWriteAccess = ["Internal User", "Admin"]; 
+export const rolesWithWriteAccess = ["Internal User", "Admin"]; 
+
+// Helper function to check if a role is in all_admin_roles
+export const isAdminRole = (role: string): boolean => {
+  return all_admin_roles.includes(role);
+};
+