Merge remote-tracking branch 'origin/main' into add-health-check-success-modal

deploy/charts/litellm-helm/templates/deployment.yaml

@@ -1,6 +1,8 @@
 apiVersion: apps/v1
 kind: Deployment
 metadata:
+  annotations:
+  {{- toYaml .Values.deploymentAnnotations | nindent 4 }}
   name: {{ include "litellm.fullname" . }}
   labels:
     {{- include "litellm.labels" . | nindent 4 }}

deploy/charts/litellm-helm/values.yaml

@@ -27,6 +27,9 @@ serviceAccount:
   # If not set and create is true, a name is generated using the fullname template
   name: ""
 
+# annotations for litellm deployment
+deploymentAnnotations: {}
+# annotations for litellm pods
 podAnnotations: {}
 podLabels: {}
 

docs/my-website/docs/mcp.md

@@ -265,6 +265,182 @@ if __name__ == "__main__":
 </Tabs>
 
 
+## Using your MCP with client side credentials
+
+Use this if you want to pass a client side authentication token to LiteLLM to then pass to your MCP to auth to your MCP.
+
+You can specify your MCP auth token using the header `x-mcp-auth`. LiteLLM will forward this token to your MCP server for authentication.
+
+<Tabs>
+<TabItem value="openai" label="OpenAI API">
+
+#### Connect via OpenAI Responses API with MCP Auth
+
+Use the OpenAI Responses API and include the `x-mcp-auth` header for your MCP server authentication:
+
+```bash title="cURL Example with MCP Auth" showLineNumbers
+curl --location 'https://api.openai.com/v1/responses' \
+--header 'Content-Type: application/json' \
+--header "Authorization: Bearer $OPENAI_API_KEY" \
+--data '{
+    "model": "gpt-4o",
+    "tools": [
+        {
+            "type": "mcp",
+            "server_label": "litellm",
+            "server_url": "<your-litellm-proxy-base-url>/mcp",
+            "require_approval": "never",
+            "headers": {
+                "x-litellm-api-key": "Bearer YOUR_LITELLM_API_KEY",
+                "x-mcp-auth": YOUR_MCP_AUTH_TOKEN
+            }
+        }
+    ],
+    "input": "Run available tools",
+    "tool_choice": "required"
+}'
+```
+
+</TabItem>
+
+<TabItem value="litellm" label="LiteLLM Proxy">
+
+#### Connect via LiteLLM Proxy Responses API with MCP Auth
+
+Use this when calling LiteLLM Proxy for LLM API requests to `/v1/responses` endpoint with MCP authentication:
+
+```bash title="cURL Example with MCP Auth" showLineNumbers
+curl --location '<your-litellm-proxy-base-url>/v1/responses' \
+--header 'Content-Type: application/json' \
+--header "Authorization: Bearer $LITELLM_API_KEY" \
+--data '{
+    "model": "gpt-4o",
+    "tools": [
+        {
+            "type": "mcp",
+            "server_label": "litellm",
+            "server_url": "<your-litellm-proxy-base-url>/mcp",
+            "require_approval": "never",
+            "headers": {
+                "x-litellm-api-key": "Bearer YOUR_LITELLM_API_KEY",
+                "x-mcp-auth": "YOUR_MCP_AUTH_TOKEN"
+            }
+        }
+    ],
+    "input": "Run available tools",
+    "tool_choice": "required"
+}'
+```
+
+</TabItem>
+
+<TabItem value="cursor" label="Cursor IDE">
+
+#### Connect via Cursor IDE with MCP Auth
+
+Use tools directly from Cursor IDE with LiteLLM MCP and include your MCP authentication token:
+
+**Setup Instructions:**
+
+1. **Open Cursor Settings**: Use `⇧+⌘+J` (Mac) or `Ctrl+Shift+J` (Windows/Linux)
+2. **Navigate to MCP Tools**: Go to the "MCP Tools" tab and click "New MCP Server"
+3. **Add Configuration**: Copy and paste the JSON configuration below, then save with `Cmd+S` or `Ctrl+S`
+
+```json title="Cursor MCP Configuration with Auth" showLineNumbers
+{
+  "mcpServers": {
+    "LiteLLM": {
+      "url": "<your-litellm-proxy-base-url>/mcp",
+      "headers": {
+        "x-litellm-api-key": "Bearer $LITELLM_API_KEY",
+        "x-mcp-auth": "$MCP_AUTH_TOKEN"
+      }
+    }
+  }
+}
+```
+
+</TabItem>
+
+<TabItem value="http" label="Streamable HTTP">
+
+#### Connect via Streamable HTTP Transport with MCP Auth
+
+Connect to LiteLLM MCP using HTTP transport with MCP authentication:
+
+**Server URL:**
+```text showLineNumbers
+<your-litellm-proxy-base-url>/mcp
+```
+
+**Headers:**
+```text showLineNumbers
+x-litellm-api-key: Bearer YOUR_LITELLM_API_KEY
+x-mcp-auth: Bearer YOUR_MCP_AUTH_TOKEN
+```
+
+This URL can be used with any MCP client that supports HTTP transport. The `x-mcp-auth` header will be forwarded to your MCP server for authentication.
+
+</TabItem>
+
+<TabItem value="fastmcp" label="Python FastMCP">
+
+#### Connect via Python FastMCP Client with MCP Auth
+
+Use the Python FastMCP client to connect to your LiteLLM MCP server with MCP authentication:
+
+```python title="Python FastMCP Example with MCP Auth" showLineNumbers
+import asyncio
+import json
+
+from fastmcp import Client
+from fastmcp.client.transports import StreamableHttpTransport
+
+# Create the transport with your LiteLLM MCP server URL and auth headers
+server_url = "<your-litellm-proxy-base-url>/mcp"
+transport = StreamableHttpTransport(
+    server_url,
+    headers={
+        "x-litellm-api-key": "Bearer YOUR_LITELLM_API_KEY",
+        "x-mcp-auth": "Bearer YOUR_MCP_AUTH_TOKEN"
+    }
+)
+
+# Initialize the client with the transport
+client = Client(transport=transport)
+
+
+async def main():
+    # Connection is established here
+    print("Connecting to LiteLLM MCP server with authentication...")
+    async with client:
+        print(f"Client connected: {client.is_connected()}")
+
+        # Make MCP calls within the context
+        print("Fetching available tools...")
+        tools = await client.list_tools()
+
+        print(f"Available tools: {json.dumps([t.name for t in tools], indent=2)}")
+        
+        # Example: Call a tool (replace 'tool_name' with an actual tool name)
+        if tools:
+            tool_name = tools[0].name
+            print(f"Calling tool: {tool_name}")
+            
+            # Call the tool with appropriate arguments
+            result = await client.call_tool(tool_name, arguments={})
+            print(f"Tool result: {result}")
+
+
+# Run the example
+if __name__ == "__main__":
+    asyncio.run(main())
+```
+
+</TabItem>
+</Tabs>
+
+
 ## ✨ MCP Permission Management
 
 LiteLLM supports managing permissions for MCP Servers by Keys, Teams, Organizations (entities) on LiteLLM. When a MCP client attempts to list tools, LiteLLM will only return the tools the entity has permissions to access.

docs/my-website/docs/providers/meta_llama.md

@@ -45,7 +45,7 @@ os.environ["LLAMA_API_KEY"] = ""  # your Meta Llama API key
 messages = [{"content": "Hello, how are you?", "role": "user"}]
 
 # Meta Llama call
-response = completion(model="meta_llama/Llama-3.3-70B-Instruct", messages=messages)
+response = completion(model="meta_llama/Llama-4-Maverick-17B-128E-Instruct-FP8", messages=messages)
 ```
 
 ### Streaming
@@ -61,7 +61,7 @@ messages = [{"content": "Hello, how are you?", "role": "user"}]
 
 # Meta Llama call with streaming
 response = completion(
-    model="meta_llama/Llama-3.3-70B-Instruct",
+    model="meta_llama/Llama-4-Maverick-17B-128E-Instruct-FP8",
     messages=messages,
     stream=True
 )
@@ -70,6 +70,104 @@ for chunk in response:
     print(chunk)
 ```
 
+### Function Calling
+
+```python showLineNumbers title="Meta Llama Function Calling"
+import os
+import litellm
+from litellm import completion
+
+os.environ["LLAMA_API_KEY"] = ""  # your Meta Llama API key
+
+messages = [{"content": "What's the weather like in San Francisco?", "role": "user"}]
+
+# Define the function
+tools = [
+    {
+        "type": "function",
+        "function": {
+            "name": "get_weather",
+            "description": "Get the current weather in a given location",
+            "parameters": {
+                "type": "object",
+                "properties": {
+                    "location": {
+                        "type": "string",
+                        "description": "The city and state, e.g. San Francisco, CA"
+                    },
+                    "unit": {
+                        "type": "string",
+                        "enum": ["celsius", "fahrenheit"]
+                    }
+                },
+                "required": ["location"]
+            }
+        }
+    }
+]
+
+# Meta Llama call with function calling
+response = completion(
+    model="meta_llama/Llama-4-Maverick-17B-128E-Instruct-FP8",
+    messages=messages,
+    tools=tools,
+    tool_choice="auto"
+)
+
+print(response.choices[0].message.tool_calls)
+```
+
+### Tool Use
+
+```python showLineNumbers title="Meta Llama Tool Use"
+import os
+import litellm
+from litellm import completion
+
+os.environ["LLAMA_API_KEY"] = ""  # your Meta Llama API key
+
+messages = [{"content": "Create a chart showing the population growth of New York City from 2010 to 2020", "role": "user"}]
+
+# Define the tools
+tools = [
+    {
+        "type": "function",
+        "function": {
+            "name": "create_chart",
+            "description": "Create a chart with the provided data",
+            "parameters": {
+                "type": "object",
+                "properties": {
+                    "chart_type": {
+                        "type": "string",
+                        "enum": ["bar", "line", "pie", "scatter"],
+                        "description": "The type of chart to create"
+                    },
+                    "title": {
+                        "type": "string",
+                        "description": "The title of the chart"
+                    },
+                    "data": {
+                        "type": "object",
+                        "description": "The data to plot in the chart"
+                    }
+                },
+                "required": ["chart_type", "title", "data"]
+            }
+        }
+    }
+]
+
+# Meta Llama call with tool use
+response = completion(
+    model="meta_llama/Llama-4-Maverick-17B-128E-Instruct-FP8",
+    messages=messages,
+    tools=tools,
+    tool_choice="auto"
+)
+
+print(response.choices[0].message.content)
+```
 
 ## Usage - LiteLLM Proxy
 
@@ -111,7 +209,7 @@ client = OpenAI(
 
 # Non-streaming response
 response = client.chat.completions.create(
-    model="meta_llama/Llama-3.3-70B-Instruct",
+    model="meta_llama/Llama-4-Maverick-17B-128E-Instruct-FP8",
     messages=[{"role": "user", "content": "Write a short poem about AI."}]
 )
 
@@ -129,7 +227,7 @@ client = OpenAI(
 
 # Streaming response
 response = client.chat.completions.create(
-    model="meta_llama/Llama-3.3-70B-Instruct",
+    model="meta_llama/Llama-4-Maverick-17B-128E-Instruct-FP8",
     messages=[{"role": "user", "content": "Write a short poem about AI."}],
     stream=True
 )

docs/my-website/release_notes/v1.72.6-stable/index.md

@@ -1,5 +1,5 @@
 ---
-title: "[PRE-RELEASE] v1.72.6-stable - MCP Gateway Permission Management"
+title: "v1.72.6-stable - MCP Gateway Permission Management"
 slug: "v1-72-6-stable"
 date: 2025-06-14T10:00:00
 authors:
@@ -36,14 +36,14 @@ The production version will be released on Wednesday.
 docker run
 -e STORE_MODEL_IN_DB=True
 -p 4000:4000
-ghcr.io/berriai/litellm:main-v1.72.6.post1-nightly
+ghcr.io/berriai/litellm:main-v1.72.6-stable
 ```
 </TabItem>
 
 <TabItem value="pip" label="Pip">
 
 ``` showLineNumbers title="pip install litellm"
-pip install litellm==1.72.6.post1
+pip install litellm==1.72.6.post2
 ```
 
 </TabItem>

litellm/__init__.py

@@ -2,7 +2,7 @@
 import warnings
 
 warnings.filterwarnings("ignore", message=".*conflict with protected namespace.*")
-### INIT VARIABLES ###########
+### INIT VARIABLES ############
 import threading
 import os
 from typing import Callable, List, Optional, Dict, Union, Any, Literal, get_args

litellm/experimental_mcp_client/client.py

@@ -0,0 +1,164 @@
+"""
+LiteLLM Proxy uses this MCP Client to connnect to other MCP servers.
+"""
+import base64
+from datetime import timedelta
+from typing import List, Optional
+
+from mcp import ClientSession
+from mcp.client.sse import sse_client
+from mcp.client.streamable_http import streamablehttp_client
+from mcp.types import CallToolRequestParams as MCPCallToolRequestParams
+from mcp.types import CallToolResult as MCPCallToolResult
+from mcp.types import Tool as MCPTool
+
+from litellm.types.mcp import MCPAuth, MCPAuthType, MCPTransport, MCPTransportType
+
+
+def to_basic_auth(auth_value: str) -> str:
+    """Convert auth value to Basic Auth format."""
+    return base64.b64encode(auth_value.encode("utf-8")).decode()
+
+
+class MCPClient:
+    """
+    MCP Client supporting:
+      SSE and HTTP transports
+      Authentication via Bearer token, Basic Auth, or API Key
+      Tool calling with error handling and result parsing
+    """
+
+    def __init__(
+        self,
+        server_url: str,
+        transport_type: MCPTransportType = MCPTransport.http,
+        auth_type: MCPAuthType = None,
+        auth_value: Optional[str] = None,
+        timeout: float = 60.0,
+    ):
+        self.server_url: str = server_url
+        self.transport_type: MCPTransport = transport_type
+        self.auth_type: MCPAuthType = auth_type
+        self.timeout: float = timeout
+        self._mcp_auth_value: Optional[str] = None
+        self._session: Optional[ClientSession] = None
+        self._context = None
+        self._transport_ctx = None
+        self._transport = None
+        self._session_ctx = None
+
+        # handle the basic auth value if provided
+        if auth_value:
+            self.update_auth_value(auth_value)
+
+    async def __aenter__(self):
+        """
+        Enable async context manager support.
+          Initializes the transport and session.
+        """
+        await self.connect()
+        return self
+
+    async def connect(self):
+        """Initialize the transport and session."""
+        if self._session:
+            return  # Already connected
+            
+        headers = self._get_auth_headers()
+
+        if self.transport_type == MCPTransport.sse:
+            self._transport_ctx = sse_client(
+                url=self.server_url,
+                timeout=self.timeout,
+                headers=headers,
+            )
+            self._transport = await self._transport_ctx.__aenter__()
+            self._session_ctx = ClientSession(self._transport[0], self._transport[1])
+            self._session = await self._session_ctx.__aenter__()
+            await self._session.initialize()
+        else:
+            self._transport_ctx = streamablehttp_client(
+                url=self.server_url,
+                timeout=timedelta(seconds=self.timeout),
+                headers=headers,
+            )
+            self._transport = await self._transport_ctx.__aenter__()
+            self._session_ctx = ClientSession(self._transport[0], self._transport[1])
+            self._session = await self._session_ctx.__aenter__()
+            await self._session.initialize()
+
+    async def __aexit__(self, exc_type, exc_val, exc_tb):
+        """Cleanup when exiting context manager."""
+        if self._session:
+            await self._session_ctx.__aexit__(exc_type, exc_val, exc_tb) # type: ignore
+        if self._transport_ctx:
+            await self._transport_ctx.__aexit__(exc_type, exc_val, exc_tb)
+
+    async def disconnect(self):
+        """Clean up session and connections."""
+        if self._session:
+            try:
+                # Ensure session is properly closed
+                await self._session.close()  # type: ignore 
+            except Exception:
+                pass
+            self._session = None
+
+        if self._context:
+            try:
+                await self._context.__aexit__(None, None, None) # type: ignore
+            except Exception:
+                pass
+            self._context = None
+
+    def update_auth_value(self, mcp_auth_value: str):
+        """
+        Set the authentication header for the MCP client.
+        """
+        if self.auth_type == MCPAuth.basic:
+            # Assuming mcp_auth_value is in format "username:password", convert it when updating
+            mcp_auth_value = to_basic_auth(mcp_auth_value)
+        self._mcp_auth_value = mcp_auth_value
+
+    def _get_auth_headers(self) -> dict:
+        """Generate authentication headers based on auth type."""
+        if not self._mcp_auth_value:
+            return {}
+
+        if self.auth_type == MCPAuth.bearer_token:
+            return {"Authorization": f"Bearer {self._mcp_auth_value}"}
+        elif self.auth_type == MCPAuth.basic:
+            return {"Authorization": f"Basic {self._mcp_auth_value}"}
+        elif self.auth_type == MCPAuth.api_key:
+            return {"X-API-Key": self._mcp_auth_value}
+        return {}
+
+    async def list_tools(self) -> List[MCPTool]:
+        """List available tools from the server."""
+        if not self._session:
+            await self.connect()
+        if self._session is None:
+            raise ValueError("Session is not initialized")
+
+        result = await self._session.list_tools()
+        return result.tools
+
+    async def call_tool(
+        self, call_tool_request_params: MCPCallToolRequestParams
+    ) -> MCPCallToolResult:
+        """
+        Call an MCP Tool.
+        """
+        if not self._session:
+            await self.connect()
+
+        if self._session is None:
+            raise ValueError("Session is not initialized")
+        
+        tool_result = await self._session.call_tool(
+            name=call_tool_request_params.name,
+            arguments=call_tool_request_params.arguments,
+        )
+        return tool_result
+        
+

litellm/integrations/prometheus.py

@@ -215,40 +215,25 @@ class PrometheusLogger(CustomLogger):
             self.litellm_remaining_requests_metric = self._gauge_factory(
                 "litellm_remaining_requests",
                 "LLM Deployment Analytics - remaining requests for model, returned from LLM API Provider",
-                labelnames=[
-                    "model_group",
-                    "api_provider",
-                    "api_base",
-                    "litellm_model_name",
-                    "hashed_api_key",
-                    "api_key_alias",
-                ],
+                labelnames=self.get_labels_for_metric(
+                    "litellm_remaining_requests_metric"
+                ),
             )
 
             self.litellm_remaining_tokens_metric = self._gauge_factory(
                 "litellm_remaining_tokens",
                 "remaining tokens for model, returned from LLM API Provider",
-                labelnames=[
-                    "model_group",
-                    "api_provider",
-                    "api_base",
-                    "litellm_model_name",
-                    "hashed_api_key",
-                    "api_key_alias",
-                ],
+                labelnames=self.get_labels_for_metric(
+                    "litellm_remaining_tokens_metric"
+                ),
             )
 
             self.litellm_overhead_latency_metric = self._histogram_factory(
                 "litellm_overhead_latency_metric",
                 "Latency overhead (milliseconds) added by LiteLLM processing",
-                labelnames=[
-                    "model_group",
-                    "api_provider",
-                    "api_base",
-                    "litellm_model_name",
-                    "hashed_api_key",
-                    "api_key_alias",
-                ],
+                labelnames=self.get_labels_for_metric(
+                    "litellm_overhead_latency_metric"
+                ),
                 buckets=LATENCY_BUCKETS,
             )
             # llm api provider budget metrics
@@ -566,6 +551,7 @@ class PrometheusLogger(CustomLogger):
             hashed_api_key=user_api_key,
             api_key_alias=user_api_key_alias,
             requested_model=standard_logging_payload["model_group"],
+            model_group=standard_logging_payload["model_group"],
             team=user_api_team,
             team_alias=user_api_team_alias,
             user=user_id,
@@ -1160,6 +1146,7 @@ class PrometheusLogger(CustomLogger):
         enum_values: UserAPIKeyLabelValues,
         output_tokens: float = 1.0,
     ):
+
         try:
             verbose_logger.debug("setting remaining tokens requests metric")
             standard_logging_payload: Optional[StandardLoggingPayload] = (
@@ -1292,7 +1279,7 @@ class PrometheusLogger(CustomLogger):
                 ).observe(latency_per_token)
 
         except Exception as e:
-            verbose_logger.error(
+            verbose_logger.exception(
                 "Prometheus Error: set_llm_deployment_success_metrics. Exception occured - {}".format(
                     str(e)
                 )

litellm/litellm_core_utils/prompt_templates/factory.py

@@ -1053,10 +1053,10 @@ def convert_to_gemini_tool_call_invoke(
         if tool_calls is not None:
             for tool in tool_calls:
                 if "function" in tool:
-                    gemini_function_call: Optional[
-                        VertexFunctionCall
-                    ] = _gemini_tool_call_invoke_helper(
-                        function_call_params=tool["function"]
+                    gemini_function_call: Optional[VertexFunctionCall] = (
+                        _gemini_tool_call_invoke_helper(
+                            function_call_params=tool["function"]
+                        )
                     )
                     if gemini_function_call is not None:
                         _parts_list.append(
@@ -1573,9 +1573,9 @@ def anthropic_messages_pt(  # noqa: PLR0915
                             )
 
                             if "cache_control" in _content_element:
-                                _anthropic_content_element[
-                                    "cache_control"
-                                ] = _content_element["cache_control"]
+                                _anthropic_content_element["cache_control"] = (
+                                    _content_element["cache_control"]
+                                )
                             user_content.append(_anthropic_content_element)
                         elif m.get("type", "") == "text":
                             m = cast(ChatCompletionTextObject, m)
@@ -1613,9 +1613,9 @@ def anthropic_messages_pt(  # noqa: PLR0915
                     )
 
                     if "cache_control" in _content_element:
-                        _anthropic_content_text_element[
-                            "cache_control"
-                        ] = _content_element["cache_control"]
+                        _anthropic_content_text_element["cache_control"] = (
+                            _content_element["cache_control"]
+                        )
 
                     user_content.append(_anthropic_content_text_element)
 
@@ -2433,8 +2433,10 @@ class BedrockImageProcessor:
 
         # Extract MIME type using regular expression
         mime_type_match = re.match(r"data:(.*?);base64", image_metadata)
+
         if mime_type_match:
             mime_type = mime_type_match.group(1)
+            mime_type = mime_type.split(";")[0]
             image_format = mime_type.split("/")[1]
         else:
             mime_type = "image/jpeg"
@@ -2458,6 +2460,7 @@ class BedrockImageProcessor:
 
         document_types = ["application", "text"]
         is_document = any(mime_type.startswith(doc_type) for doc_type in document_types)
+
         supported_image_and_video_formats: List[str] = (
             supported_video_formats + supported_image_formats
         )

litellm/llms/anthropic/chat/transformation.py

@@ -77,9 +77,9 @@ class AnthropicConfig(AnthropicModelInfo, BaseConfig):
     to pass metadata to anthropic, it's {"user_id": "any-relevant-information"}
     """
 
-    max_tokens: Optional[
-        int
-    ] = DEFAULT_ANTHROPIC_CHAT_MAX_TOKENS  # anthropic requires a default value (Opus, Sonnet, and Haiku have the same default)
+    max_tokens: Optional[int] = (
+        DEFAULT_ANTHROPIC_CHAT_MAX_TOKENS  # anthropic requires a default value (Opus, Sonnet, and Haiku have the same default)
+    )
     stop_sequences: Optional[list] = None
     temperature: Optional[int] = None
     top_p: Optional[int] = None
@@ -104,11 +104,16 @@ class AnthropicConfig(AnthropicModelInfo, BaseConfig):
             if key != "self" and value is not None:
                 setattr(self.__class__, key, value)
 
+    @property
+    def custom_llm_provider(self) -> Optional[str]:
+        return "anthropic"
+
     @classmethod
     def get_config(cls):
         return super().get_config()
 
     def get_supported_openai_params(self, model: str):
+
         params = [
             "stream",
             "stop",
@@ -447,11 +452,11 @@ class AnthropicConfig(AnthropicModelInfo, BaseConfig):
                 if mcp_servers:
                     optional_params["mcp_servers"] = mcp_servers
             if param == "tool_choice" or param == "parallel_tool_calls":
-                _tool_choice: Optional[
-                    AnthropicMessagesToolChoice
-                ] = self._map_tool_choice(
-                    tool_choice=non_default_params.get("tool_choice"),
-                    parallel_tool_use=non_default_params.get("parallel_tool_calls"),
+                _tool_choice: Optional[AnthropicMessagesToolChoice] = (
+                    self._map_tool_choice(
+                        tool_choice=non_default_params.get("tool_choice"),
+                        parallel_tool_use=non_default_params.get("parallel_tool_calls"),
+                    )
                 )
 
                 if _tool_choice is not None:
@@ -557,9 +562,9 @@ class AnthropicConfig(AnthropicModelInfo, BaseConfig):
                         text=system_message_block["content"],
                     )
                     if "cache_control" in system_message_block:
-                        anthropic_system_message_content[
-                            "cache_control"
-                        ] = system_message_block["cache_control"]
+                        anthropic_system_message_content["cache_control"] = (
+                            system_message_block["cache_control"]
+                        )
                     anthropic_system_message_list.append(
                         anthropic_system_message_content
                     )
@@ -573,9 +578,9 @@ class AnthropicConfig(AnthropicModelInfo, BaseConfig):
                             )
                         )
                         if "cache_control" in _content:
-                            anthropic_system_message_content[
-                                "cache_control"
-                            ] = _content["cache_control"]
+                            anthropic_system_message_content["cache_control"] = (
+                                _content["cache_control"]
+                            )
 
                         anthropic_system_message_list.append(
                             anthropic_system_message_content
@@ -735,9 +740,7 @@ class AnthropicConfig(AnthropicModelInfo, BaseConfig):
                 )
         return _message
 
-    def extract_response_content(
-        self, completion_response: dict
-    ) -> Tuple[
+    def extract_response_content(self, completion_response: dict) -> Tuple[
         str,
         Optional[List[Any]],
         Optional[

litellm/llms/base_llm/chat/transformation.py

@@ -97,6 +97,7 @@ class BaseConfig(ABC):
                     types.BuiltinFunctionType,
                     classmethod,
                     staticmethod,
+                    property,
                 ),
             )
             and v is not None

litellm/llms/bedrock/chat/invoke_transformations/anthropic_claude3_transformation.py

@@ -28,6 +28,10 @@ class AmazonAnthropicClaude3Config(AmazonInvokeConfig, AnthropicConfig):
 
     anthropic_version: str = "bedrock-2023-05-31"
 
+    @property
+    def custom_llm_provider(self) -> Optional[str]:
+        return "bedrock"
+
     def get_supported_openai_params(self, model: str) -> List[str]:
         return AnthropicConfig.get_supported_openai_params(self, model)
 

litellm/llms/custom_httpx/http_handler.py

@@ -533,6 +533,39 @@ class AsyncHTTPHandler:
         verbose_logger.debug("Using AiohttpTransport...")
         return True
 
+    @staticmethod
+    def _get_ssl_connector_kwargs(
+        ssl_verify: Optional[bool] = None,
+        ssl_context: Optional[ssl.SSLContext] = None,
+    ) -> Dict[str, Any]:
+        """
+        Helper method to get SSL connector initialization arguments for aiohttp TCPConnector.
+        
+        SSL Configuration Priority:
+        1. If ssl_context is provided -> use the custom SSL context
+        2. If ssl_verify is False -> disable SSL verification (ssl=False)
+        3. If ssl_verify is True/None -> use default SSL context with certifi CA bundle
+
+        Returns:
+            Dict with appropriate SSL configuration for TCPConnector
+        """
+        connector_kwargs: Dict[str, Any] = {
+            "local_addr": ("0.0.0.0", 0) if litellm.force_ipv4 else None,
+        }
+        
+        if ssl_context is not None:
+            # Priority 1: Use the provided custom SSL context
+            connector_kwargs["ssl"] = ssl_context
+        elif ssl_verify is False:
+            # Priority 2: Explicitly disable SSL verification
+            connector_kwargs["verify_ssl"] = False
+        else:
+            # Priority 3: Use our default SSL context with certifi CA bundle
+            # This covers ssl_verify=True and ssl_verify=None cases
+            connector_kwargs["ssl"] = AsyncHTTPHandler._get_ssl_context()
+        
+        return connector_kwargs
+
     @staticmethod
     def _create_aiohttp_transport(
         ssl_verify: Optional[bool] = None,
@@ -541,29 +574,34 @@ class AsyncHTTPHandler:
         """
         Creates an AiohttpTransport with RequestNotRead error handling
 
-        - If force_ipv4 is True, it will create an AiohttpTransport with local_addr set to "0.0.0.0"
-        - [Default] If force_ipv4 is False, it will create an AiohttpTransport with default settings
+        Note: aiohttp TCPConnector ssl parameter accepts:
+        - SSLContext: custom SSL context
+        - False: disable SSL verification
+        - True: use default SSL verification (equivalent to ssl.create_default_context())
         """
         from litellm.llms.custom_httpx.aiohttp_transport import LiteLLMAiohttpTransport
 
-        #########################################################
-        # If ssl_verify is None, set it to True
-        # TCP Connector does not allow ssl_verify to be None
-        # by default aiohttp sets ssl_verify to True
-        #########################################################
-        if ssl_verify is None:
-            ssl_verify = True
+        connector_kwargs = AsyncHTTPHandler._get_ssl_connector_kwargs(
+            ssl_verify=ssl_verify, ssl_context=ssl_context
+        )
 
         verbose_logger.debug("Creating AiohttpTransport...")
         return LiteLLMAiohttpTransport(
             client=lambda: ClientSession(
-                connector=TCPConnector(
-                    verify_ssl=ssl_verify,
-                    ssl_context=ssl_context,
-                    local_addr=("0.0.0.0", 0) if litellm.force_ipv4 else None,
-                )
+                connector=TCPConnector(**connector_kwargs)
             ),
         )
+    
+
+    @staticmethod
+    def _get_ssl_context() -> ssl.SSLContext:
+        """
+        Get the SSL context for the AiohttpTransport
+        """
+        import certifi
+        return ssl.create_default_context(
+            cafile=certifi.where()
+        )
 
     @staticmethod
     def _create_httpx_transport() -> Optional[AsyncHTTPTransport]:

litellm/llms/litellm_proxy/chat/transformation.py

@@ -2,13 +2,16 @@
 Translate from OpenAI's `/v1/chat/completions` to VLLM's `/v1/chat/completions`
 """
 
-from typing import List, Optional, Tuple
+from typing import TYPE_CHECKING, List, Optional, Tuple
 
 from litellm.secret_managers.main import get_secret_bool, get_secret_str
 from litellm.types.router import LiteLLM_Params
 
 from ...openai.chat.gpt_transformation import OpenAIGPTConfig
 
+if TYPE_CHECKING:
+    from litellm.types.llms.openai import AllMessageValues
+
 
 class LiteLLMProxyChatConfig(OpenAIGPTConfig):
     def get_supported_openai_params(self, model: str) -> List:
@@ -113,3 +116,33 @@ class LiteLLMProxyChatConfig(OpenAIGPTConfig):
         )
 
         return model, custom_llm_provider, api_key, api_base
+
+    def transform_request(
+        self,
+        model: str,
+        messages: List["AllMessageValues"],
+        optional_params: dict,
+        litellm_params: dict,
+        headers: dict,
+    ) -> dict:
+        # don't transform the request
+        return {
+            "model": model,
+            "messages": messages,
+            **optional_params,
+        }
+
+    async def async_transform_request(
+        self,
+        model: str,
+        messages: List["AllMessageValues"],
+        optional_params: dict,
+        litellm_params: dict,
+        headers: dict,
+    ) -> dict:
+        # don't transform the request
+        return {
+            "model": model,
+            "messages": messages,
+            **optional_params,
+        }

litellm/llms/meta_llama/chat/transformation.py

@@ -6,9 +6,11 @@ Calls done in OpenAI/openai.py as Llama API is openai-compatible.
 Docs: https://llama.developer.meta.com/docs/features/compatibility/
 """
 
-from typing import Optional
+import warnings
+
+# Suppress Pydantic serialization warnings for Meta Llama responses
+warnings.filterwarnings("ignore", message="Pydantic serializer warnings")
 
-from litellm import get_model_info, verbose_logger
 from litellm.llms.openai.chat.gpt_transformation import OpenAIGPTConfig
 
 
@@ -17,27 +19,11 @@ class LlamaAPIConfig(OpenAIGPTConfig):
         """
         Llama API has limited support for OpenAI parameters
 
-        Tool calling, Functional Calling, tool choice are not working right now
+        function_call, tools, and tool_choice are working
         response_format: only json_schema is working
         """
-        supports_function_calling: Optional[bool] = None
-        supports_tool_choice: Optional[bool] = None
-        try:
-            model_info = get_model_info(model, custom_llm_provider="meta_llama")
-            supports_function_calling = model_info.get(
-                "supports_function_calling", False
-            )
-            supports_tool_choice = model_info.get("supports_tool_choice", False)
-        except Exception as e:
-            verbose_logger.debug(f"Error getting supported openai params: {e}")
-            pass
-
+        # Function calling and tool choice are now supported on Llama API
         optional_params = super().get_supported_openai_params(model)
-        if not supports_function_calling:
-            optional_params.remove("function_call")
-        if not supports_tool_choice:
-            optional_params.remove("tools")
-            optional_params.remove("tool_choice")
         return optional_params
 
     def map_openai_params(

litellm/llms/mistral/mistral_chat_transformation.py

@@ -86,8 +86,9 @@ class MistralConfig(OpenAIGPTConfig):
             "seed",
             "stop",
             "response_format",
+            "parallel_tool_calls",
         ]
-        
+
         # Add reasoning support for magistral models
         if "magistral" in model.lower():
             supported_params.extend(["thinking", "reasoning_effort"])
@@ -154,6 +155,8 @@ Then provide a clear, concise answer based on your reasoning."""
             if param == "thinking" and "magistral" in model.lower():
                 # Flag that we need to add reasoning system prompt
                 optional_params["_add_reasoning_prompt"] = True
+            if param == "parallel_tool_calls":
+                optional_params["parallel_tool_calls"] = value
         return optional_params
 
     def _get_openai_compatible_provider_info(
@@ -287,12 +290,18 @@ Then provide a clear, concise answer based on your reasoning."""
         """
         Mistral API only supports `name` in tool messages
 
-        If role == tool, then we keep `name`
+        If role == tool, then we keep `name` if it's not an empty string
         Otherwise, we drop `name`
         """
         _name = message.get("name")  # type: ignore
-        if _name is not None and message["role"] != "tool":
-            message.pop("name", None)  # type: ignore
+        
+        if _name is not None:
+            # Remove name if not a tool message
+            if message["role"] != "tool":
+                message.pop("name", None)  # type: ignore
+            # For tool messages, remove name if it's an empty string
+            elif isinstance(_name, str) and len(_name.strip()) == 0:
+                message.pop("name", None)  # type: ignore
 
         return message
 

litellm/llms/vertex_ai/gemini/vertex_and_google_ai_studio_gemini.py

@@ -1025,9 +1025,9 @@ class VertexGeminiConfig(VertexAIBaseConfig, BaseConfig):
             response_tokens_details = CompletionTokensDetailsWrapper()
             for detail in usage_metadata["responseTokensDetails"]:
                 if detail["modality"] == "TEXT":
-                    response_tokens_details.text_tokens = detail["tokenCount"]
+                    response_tokens_details.text_tokens = detail.get("tokenCount", 0)
                 elif detail["modality"] == "AUDIO":
-                    response_tokens_details.audio_tokens = detail["tokenCount"]
+                    response_tokens_details.audio_tokens = detail.get("tokenCount", 0)
         #########################################################
 
         if "promptTokensDetails" in usage_metadata:

litellm/llms/vertex_ai/vertex_ai_partner_models/anthropic/transformation.py

@@ -46,6 +46,7 @@ class VertexAIAnthropicConfig(AnthropicConfig):
 
     Note: Please make sure to modify the default parameters as required for your use case.
     """
+
     @property
     def custom_llm_provider(self) -> Optional[str]:
         return "vertex_ai"

litellm/llms/vertex_ai/vertex_llm_base.py

@@ -79,7 +79,15 @@ class VertexBase:
 
             # Check if the JSON object contains Workload Identity Federation configuration
             if "type" in json_obj and json_obj["type"] == "external_account":
-                creds = self._credentials_from_identity_pool(json_obj)
+                # If environment_id key contains "aws" value it corresponds to an AWS config file
+                if (
+                    "credential_source" in json_obj
+                    and "environment_id" in json_obj["credential_source"]
+                    and "aws" in json_obj["credential_source"]["environment_id"]
+                ):
+                    creds = self._credentials_from_identity_pool_with_aws(json_obj)
+                else:
+                    creds = self._credentials_from_identity_pool(json_obj)
             # Check if the JSON object contains Authorized User configuration (via gcloud auth application-default login)
             elif "type" in json_obj and json_obj["type"] == "authorized_user":
                 creds = self._credentials_from_authorized_user(
@@ -122,6 +130,11 @@ class VertexBase:
         from google.auth import identity_pool
 
         return identity_pool.Credentials.from_info(json_obj)
+    
+    def _credentials_from_identity_pool_with_aws(self, json_obj):
+        from google.auth import aws
+
+        return aws.Credentials.from_info(json_obj)
 
     def _credentials_from_authorized_user(self, json_obj, scopes):
         import google.oauth2.credentials

litellm/model_prices_and_context_window_backup.json

@@ -451,9 +451,9 @@
         "max_input_tokens": 128000,
         "max_output_tokens": 16384,
         "input_cost_per_token": 2.5e-06,
-        "input_cost_per_audio_token": 4.0e-5,
+        "input_cost_per_audio_token": 4e-05,
         "output_cost_per_token": 1e-05,
-        "output_cost_per_audio_token": 8.0e-5,
+        "output_cost_per_audio_token": 8e-05,
         "litellm_provider": "openai",
         "mode": "chat",
         "supports_function_calling": true,
@@ -594,7 +594,7 @@
         "max_output_tokens": 100000,
         "input_cost_per_token": 1.5e-06,
         "output_cost_per_token": 6e-06,
-        "cache_read_input_token_cost": 0.375e-06,
+        "cache_read_input_token_cost": 3.75e-07,
         "litellm_provider": "openai",
         "mode": "responses",
         "supports_pdf_input": true,
@@ -744,10 +744,10 @@
         "max_tokens": 100000,
         "max_input_tokens": 200000,
         "max_output_tokens": 100000,
-        "input_cost_per_token": 20e-06,
-        "input_cost_per_token_batches": 10e-06,
-        "output_cost_per_token_batches": 40e-06,
-        "output_cost_per_token": 80e-06,
+        "input_cost_per_token": 2e-05,
+        "input_cost_per_token_batches": 1e-05,
+        "output_cost_per_token_batches": 4e-05,
+        "output_cost_per_token": 8e-05,
         "litellm_provider": "openai",
         "mode": "responses",
         "supports_function_calling": true,
@@ -774,10 +774,10 @@
         "max_tokens": 100000,
         "max_input_tokens": 200000,
         "max_output_tokens": 100000,
-        "input_cost_per_token": 20e-06,
-        "input_cost_per_token_batches": 10e-06,
-        "output_cost_per_token_batches": 40e-06,
-        "output_cost_per_token": 80e-06,
+        "input_cost_per_token": 2e-05,
+        "input_cost_per_token_batches": 1e-05,
+        "output_cost_per_token_batches": 4e-05,
+        "output_cost_per_token": 8e-05,
         "litellm_provider": "openai",
         "mode": "responses",
         "supports_function_calling": true,
@@ -806,7 +806,7 @@
         "max_output_tokens": 100000,
         "input_cost_per_token": 2e-06,
         "output_cost_per_token": 8e-06,
-        "cache_read_input_token_cost": 0.5e-06,
+        "cache_read_input_token_cost": 5e-07,
         "litellm_provider": "openai",
         "mode": "chat",
         "supports_function_calling": true,
@@ -837,7 +837,7 @@
         "max_output_tokens": 100000,
         "input_cost_per_token": 2e-06,
         "output_cost_per_token": 8e-06,
-        "cache_read_input_token_cost": 0.5e-06,
+        "cache_read_input_token_cost": 5e-07,
         "litellm_provider": "openai",
         "mode": "chat",
         "supports_function_calling": true,
@@ -2685,7 +2685,7 @@
         "max_output_tokens": 100000,
         "input_cost_per_token": 1.5e-06,
         "output_cost_per_token": 6e-06,
-        "cache_read_input_token_cost": 0.375e-06,
+        "cache_read_input_token_cost": 3.75e-07,
         "litellm_provider": "azure",
         "mode": "responses",
         "supports_pdf_input": true,
@@ -4295,8 +4295,8 @@
         "max_tokens": 40000,
         "max_input_tokens": 40000,
         "max_output_tokens": 40000,
-        "input_cost_per_token": 0.5e-6,
-        "output_cost_per_token": 1.5e-6,
+        "input_cost_per_token": 5e-07,
+        "output_cost_per_token": 1.5e-06,
         "litellm_provider": "mistral",
         "mode": "chat",
         "source": "https://mistral.ai/pricing#api-pricing",
@@ -4309,7 +4309,7 @@
         "max_tokens": 40000,
         "max_input_tokens": 40000,
         "max_output_tokens": 40000,
-        "input_cost_per_token": 0.5e-06,
+        "input_cost_per_token": 5e-07,
         "output_cost_per_token": 1.5e-06,
         "litellm_provider": "mistral",
         "mode": "chat",
@@ -4579,9 +4579,9 @@
         "output_cost_per_token": 4e-06,
         "litellm_provider": "xai",
         "mode": "chat",
+        "supports_reasoning": true,
         "supports_function_calling": true,
         "supports_tool_choice": true,
-        "supports_reasoning": true,
         "supports_response_schema": false,
         "source": "https://x.ai/api#pricing",
         "supports_web_search": true
@@ -4616,21 +4616,6 @@
         "source": "https://x.ai/api#pricing",
         "supports_web_search": true
     },
-    "xai/grok-3-mini-fast-latest": {
-        "max_tokens": 131072,
-        "max_input_tokens": 131072,
-        "max_output_tokens": 131072,
-        "input_cost_per_token": 6e-07,
-        "output_cost_per_token": 4e-06,
-        "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",
-        "supports_web_search": true
-    },
     "xai/grok-vision-beta": {
         "max_tokens": 8192,
         "max_input_tokens": 8192,
@@ -5812,9 +5797,9 @@
         "max_output_tokens": 4028,
         "litellm_provider": "meta_llama",
         "mode": "chat",
-        "supports_function_calling": false,
+        "supports_function_calling": true,
         "source": "https://llama.developer.meta.com/docs/models",
-        "supports_tool_choice": false,
+        "supports_tool_choice": true,
         "supported_modalities": [
             "text",
             "image"
@@ -5829,9 +5814,9 @@
         "max_output_tokens": 4028,
         "litellm_provider": "meta_llama",
         "mode": "chat",
-        "supports_function_calling": false,
+        "supports_function_calling": true,
         "source": "https://llama.developer.meta.com/docs/models",
-        "supports_tool_choice": false,
+        "supports_tool_choice": true,
         "supported_modalities": [
             "text",
             "image"
@@ -5846,9 +5831,9 @@
         "max_output_tokens": 4028,
         "litellm_provider": "meta_llama",
         "mode": "chat",
-        "supports_function_calling": false,
+        "supports_function_calling": true,
         "source": "https://llama.developer.meta.com/docs/models",
-        "supports_tool_choice": false,
+        "supports_tool_choice": true,
         "supported_modalities": [
             "text"
         ],
@@ -5862,9 +5847,9 @@
         "max_output_tokens": 4028,
         "litellm_provider": "meta_llama",
         "mode": "chat",
-        "supports_function_calling": false,
+        "supports_function_calling": true,
         "source": "https://llama.developer.meta.com/docs/models",
-        "supports_tool_choice": false,
+        "supports_tool_choice": true,
         "supported_modalities": [
             "text"
         ],
@@ -6735,8 +6720,8 @@
         "output_cost_per_token_above_200k_tokens": 1.5e-05,
         "litellm_provider": "gemini",
         "mode": "chat",
-        "rpm": 2e-3,
-        "tpm": 8e-6,
+        "rpm": 2000,
+        "tpm": 800000,
         "supports_system_messages": true,
         "supports_function_calling": true,
         "supports_vision": true,
@@ -6802,8 +6787,9 @@
         "supports_parallel_function_calling": true,
         "supports_web_search": true,
         "supports_url_context": true,
-        "tpm": 8e-6,
-        "rpm": 1e-5
+        "tpm": 8000000,
+        "rpm": 100000,
+        "supports_pdf_input": true
     },
     "gemini-2.5-flash": {
         "max_tokens": 65535,
@@ -6845,7 +6831,8 @@
         "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview",
         "supports_parallel_function_calling": true,
         "supports_web_search": true,
-        "supports_url_context": true
+        "supports_url_context": true,
+        "supports_pdf_input": true
     },
     "gemini/gemini-2.5-flash-preview-tts": {
         "max_tokens": 65535,
@@ -6896,9 +6883,9 @@
         "max_audio_per_prompt": 1,
         "max_pdf_size_mb": 30,
         "input_cost_per_audio_token": 1e-06,
-        "input_cost_per_token": 1.5e-07,
-        "output_cost_per_token": 6e-07,
-        "output_cost_per_reasoning_token": 3.5e-06,
+        "input_cost_per_token": 3e-07,
+        "output_cost_per_token": 2.5e-06,
+        "output_cost_per_reasoning_token": 2.5e-06,
         "litellm_provider": "gemini",
         "mode": "chat",
         "rpm": 10,
@@ -6925,7 +6912,8 @@
         ],
         "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview",
         "supports_web_search": true,
-        "supports_url_context": true
+        "supports_url_context": true,
+        "supports_pdf_input": true
     },
     "gemini/gemini-2.5-flash-preview-04-17": {
         "max_tokens": 65535,
@@ -6966,7 +6954,53 @@
             "text"
         ],
         "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview",
-        "supports_web_search": true
+        "supports_web_search": true,
+        "supports_pdf_input": true
+    },
+    "gemini/gemini-2.5-flash-lite-preview-06-17": {
+        "max_tokens": 65535,
+        "max_input_tokens": 1048576,
+        "max_output_tokens": 65535,
+        "max_images_per_prompt": 3000,
+        "max_videos_per_prompt": 10,
+        "max_video_length": 1,
+        "max_audio_length_hours": 8.4,
+        "max_audio_per_prompt": 1,
+        "max_pdf_size_mb": 30,
+        "input_cost_per_audio_token": 5e-07,
+        "input_cost_per_token": 1e-07,
+        "output_cost_per_token": 4e-07,
+        "output_cost_per_reasoning_token": 4e-07,
+        "litellm_provider": "gemini",
+        "mode": "chat",
+        "rpm": 15,
+        "tpm": 250000,
+        "supports_reasoning": true,
+        "supports_system_messages": true,
+        "supports_function_calling": true,
+        "supports_vision": true,
+        "supports_response_schema": true,
+        "supports_audio_output": false,
+        "supports_tool_choice": true,
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/completions",
+            "/v1/batch"
+        ],
+        "supported_modalities": [
+            "text",
+            "image",
+            "audio",
+            "video"
+        ],
+        "supported_output_modalities": [
+            "text"
+        ],
+        "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-lite",
+        "supports_parallel_function_calling": true,
+        "supports_web_search": true,
+        "supports_url_context": true,
+        "supports_pdf_input": true
     },
     "gemini-2.5-flash-preview-05-20": {
         "max_tokens": 65535,
@@ -6979,9 +7013,9 @@
         "max_audio_per_prompt": 1,
         "max_pdf_size_mb": 30,
         "input_cost_per_audio_token": 1e-06,
-        "input_cost_per_token": 1.5e-07,
-        "output_cost_per_token": 6e-07,
-        "output_cost_per_reasoning_token": 3.5e-06,
+        "input_cost_per_token": 3e-07,
+        "output_cost_per_token": 2.5e-06,
+        "output_cost_per_reasoning_token": 2.5e-06,
         "litellm_provider": "vertex_ai-language-models",
         "mode": "chat",
         "supports_reasoning": true,
@@ -7008,7 +7042,8 @@
         "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview",
         "supports_parallel_function_calling": true,
         "supports_web_search": true,
-        "supports_url_context": true
+        "supports_url_context": true,
+        "supports_pdf_input": true
     },
     "gemini-2.5-flash-preview-04-17": {
         "max_tokens": 65535,
@@ -7049,7 +7084,8 @@
         ],
         "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview",
         "supports_parallel_function_calling": true,
-        "supports_web_search": true
+        "supports_web_search": true,
+        "supports_pdf_input": true
     },
     "gemini-2.5-flash-lite-preview-06-17": {
         "max_tokens": 65535,
@@ -7061,7 +7097,7 @@
         "max_audio_length_hours": 8.4,
         "max_audio_per_prompt": 1,
         "max_pdf_size_mb": 30,
-        "input_cost_per_audio_token": 1e-06,
+        "input_cost_per_audio_token": 5e-07,
         "input_cost_per_token": 1e-07,
         "output_cost_per_token": 4e-07,
         "output_cost_per_reasoning_token": 4e-07,
@@ -7091,7 +7127,8 @@
         "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview",
         "supports_parallel_function_calling": true,
         "supports_web_search": true,
-        "supports_url_context": true
+        "supports_url_context": true,
+        "supports_pdf_input": true
     },
     "gemini-2.0-flash": {
         "max_tokens": 8192,
@@ -7237,7 +7274,8 @@
         ],
         "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview",
         "supports_parallel_function_calling": true,
-        "supports_web_search": true
+        "supports_web_search": true,
+        "supports_pdf_input": true
     },
     "gemini-2.5-pro-preview-05-06": {
         "max_tokens": 65535,
@@ -7282,7 +7320,8 @@
         ],
         "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview",
         "supports_parallel_function_calling": true,
-        "supports_web_search": true
+        "supports_web_search": true,
+        "supports_pdf_input": true
     },
     "gemini-2.5-pro-preview-03-25": {
         "max_tokens": 65535,
@@ -7324,7 +7363,8 @@
         ],
         "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview",
         "supports_parallel_function_calling": true,
-        "supports_web_search": true
+        "supports_web_search": true,
+        "supports_pdf_input": true
     },
     "gemini-2.0-flash-preview-image-generation": {
         "max_tokens": 8192,
@@ -7649,7 +7689,8 @@
         ],
         "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-pro-preview",
         "supports_web_search": true,
-        "supports_url_context": true
+        "supports_url_context": true,
+        "supports_pdf_input": true
     },
     "gemini/gemini-2.5-pro-preview-05-06": {
         "max_tokens": 65535,
@@ -7687,7 +7728,8 @@
         ],
         "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-pro-preview",
         "supports_web_search": true,
-        "supports_url_context": true
+        "supports_url_context": true,
+        "supports_pdf_input": true
     },
     "gemini/gemini-2.5-pro-preview-03-25": {
         "max_tokens": 65535,
@@ -7724,7 +7766,8 @@
             "text"
         ],
         "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-pro-preview",
-        "supports_web_search": true
+        "supports_web_search": true,
+        "supports_pdf_input": true
     },
     "gemini/gemini-2.0-flash-exp": {
         "max_tokens": 8192,
@@ -8562,13 +8605,13 @@
         "litellm_provider": "vertex_ai-image-models",
         "mode": "image_generation",
         "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing"
-    },    
+    },
     "vertex_ai/imagen-4.0-fast-generate-preview-06-06": {
         "output_cost_per_image": 0.02,
         "litellm_provider": "vertex_ai-image-models",
         "mode": "image_generation",
         "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing"
-    },    
+    },
     "vertex_ai/imagen-3.0-generate-002": {
         "output_cost_per_image": 0.04,
         "litellm_provider": "vertex_ai-image-models",
@@ -10830,6 +10873,46 @@
         "supports_response_schema": true,
         "source": "https://aws.amazon.com/bedrock/pricing/"
     },
+    "apac.amazon.nova-micro-v1:0": {
+        "max_tokens": 10000,
+        "max_input_tokens": 300000,
+        "max_output_tokens": 10000,
+        "input_cost_per_token": 3.7e-08,
+        "output_cost_per_token": 1.48e-07,
+        "litellm_provider": "bedrock_converse",
+        "mode": "chat",
+        "supports_function_calling": true,
+        "supports_prompt_caching": true,
+        "supports_response_schema": true
+    },
+    "apac.amazon.nova-lite-v1:0": {
+        "max_tokens": 10000,
+        "max_input_tokens": 128000,
+        "max_output_tokens": 10000,
+        "input_cost_per_token": 6.3e-08,
+        "output_cost_per_token": 2.52e-07,
+        "litellm_provider": "bedrock_converse",
+        "mode": "chat",
+        "supports_function_calling": true,
+        "supports_vision": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_response_schema": true
+    },
+    "apac.amazon.nova-pro-v1:0": {
+        "max_tokens": 10000,
+        "max_input_tokens": 300000,
+        "max_output_tokens": 10000,
+        "input_cost_per_token": 8.4e-07,
+        "output_cost_per_token": 3.36e-06,
+        "litellm_provider": "bedrock_converse",
+        "mode": "chat",
+        "supports_function_calling": true,
+        "supports_vision": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_response_schema": true
+    },
     "us.amazon.nova-premier-v1:0": {
         "max_tokens": 10000,
         "max_input_tokens": 1000000,
@@ -11315,6 +11398,93 @@
         "supports_reasoning": true,
         "supports_computer_use": true
     },
+    "apac.anthropic.claude-3-haiku-20240307-v1:0": {
+        "max_tokens": 4096,
+        "max_input_tokens": 200000,
+        "max_output_tokens": 4096,
+        "input_cost_per_token": 2.5e-07,
+        "output_cost_per_token": 1.25e-06,
+        "litellm_provider": "bedrock",
+        "mode": "chat",
+        "supports_function_calling": true,
+        "supports_response_schema": true,
+        "supports_vision": true,
+        "supports_pdf_input": true,
+        "supports_tool_choice": true
+    },
+    "apac.anthropic.claude-3-sonnet-20240229-v1:0": {
+        "max_tokens": 4096,
+        "max_input_tokens": 200000,
+        "max_output_tokens": 4096,
+        "input_cost_per_token": 3e-06,
+        "output_cost_per_token": 1.5e-05,
+        "litellm_provider": "bedrock",
+        "mode": "chat",
+        "supports_function_calling": true,
+        "supports_response_schema": true,
+        "supports_vision": true,
+        "supports_pdf_input": true,
+        "supports_tool_choice": true
+    },
+    "apac.anthropic.claude-3-5-sonnet-20240620-v1:0": {
+        "max_tokens": 4096,
+        "max_input_tokens": 200000,
+        "max_output_tokens": 4096,
+        "input_cost_per_token": 3e-06,
+        "output_cost_per_token": 1.5e-05,
+        "litellm_provider": "bedrock",
+        "mode": "chat",
+        "supports_function_calling": true,
+        "supports_response_schema": true,
+        "supports_vision": true,
+        "supports_pdf_input": true,
+        "supports_tool_choice": true
+    },
+    "apac.anthropic.claude-3-5-sonnet-20241022-v2:0": {
+        "max_tokens": 8192,
+        "max_input_tokens": 200000,
+        "max_output_tokens": 8192,
+        "input_cost_per_token": 3e-06,
+        "output_cost_per_token": 1.5e-05,
+        "cache_creation_input_token_cost": 3.75e-06,
+        "cache_read_input_token_cost": 3e-07,
+        "litellm_provider": "bedrock",
+        "mode": "chat",
+        "supports_function_calling": true,
+        "supports_vision": true,
+        "supports_assistant_prefill": true,
+        "supports_computer_use": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_response_schema": true,
+        "supports_tool_choice": true
+    },
+    "apac.anthropic.claude-sonnet-4-20250514-v1:0": {
+        "max_tokens": 64000,
+        "max_input_tokens": 200000,
+        "max_output_tokens": 64000,
+        "input_cost_per_token": 3e-06,
+        "output_cost_per_token": 1.5e-05,
+        "search_context_cost_per_query": {
+            "search_context_size_low": 0.01,
+            "search_context_size_medium": 0.01,
+            "search_context_size_high": 0.01
+        },
+        "cache_creation_input_token_cost": 3.75e-06,
+        "cache_read_input_token_cost": 3e-07,
+        "litellm_provider": "bedrock_converse",
+        "mode": "chat",
+        "supports_function_calling": true,
+        "supports_vision": true,
+        "tool_use_system_prompt_tokens": 159,
+        "supports_assistant_prefill": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_response_schema": true,
+        "supports_tool_choice": true,
+        "supports_reasoning": true,
+        "supports_computer_use": true
+    },
     "eu.anthropic.claude-3-5-haiku-20241022-v1:0": {
         "max_tokens": 8192,
         "max_input_tokens": 200000,
@@ -14770,7 +14940,7 @@
     },
     "deepgram/nova-3": {
         "mode": "audio_transcription",
-        "input_cost_per_second": 0.00007167,
+        "input_cost_per_second": 7.167e-05,
         "output_cost_per_second": 0.0,
         "litellm_provider": "deepgram",
         "supported_endpoints": [
@@ -14784,7 +14954,7 @@
     },
     "deepgram/nova-3-general": {
         "mode": "audio_transcription",
-        "input_cost_per_second": 0.00007167,
+        "input_cost_per_second": 7.167e-05,
         "output_cost_per_second": 0.0,
         "litellm_provider": "deepgram",
         "supported_endpoints": [
@@ -14798,7 +14968,7 @@
     },
     "deepgram/nova-3-medical": {
         "mode": "audio_transcription",
-        "input_cost_per_second": 0.00008667,
+        "input_cost_per_second": 8.667e-05,
         "output_cost_per_second": 0.0,
         "litellm_provider": "deepgram",
         "supported_endpoints": [
@@ -14812,7 +14982,7 @@
     },
     "deepgram/nova-2": {
         "mode": "audio_transcription",
-        "input_cost_per_second": 0.00007167,
+        "input_cost_per_second": 7.167e-05,
         "output_cost_per_second": 0.0,
         "litellm_provider": "deepgram",
         "supported_endpoints": [
@@ -14826,7 +14996,7 @@
     },
     "deepgram/nova-2-general": {
         "mode": "audio_transcription",
-        "input_cost_per_second": 0.00007167,
+        "input_cost_per_second": 7.167e-05,
         "output_cost_per_second": 0.0,
         "litellm_provider": "deepgram",
         "supported_endpoints": [
@@ -14840,7 +15010,7 @@
     },
     "deepgram/nova-2-meeting": {
         "mode": "audio_transcription",
-        "input_cost_per_second": 0.00007167,
+        "input_cost_per_second": 7.167e-05,
         "output_cost_per_second": 0.0,
         "litellm_provider": "deepgram",
         "supported_endpoints": [
@@ -14854,7 +15024,7 @@
     },
     "deepgram/nova-2-phonecall": {
         "mode": "audio_transcription",
-        "input_cost_per_second": 0.00007167,
+        "input_cost_per_second": 7.167e-05,
         "output_cost_per_second": 0.0,
         "litellm_provider": "deepgram",
         "supported_endpoints": [
@@ -14868,7 +15038,7 @@
     },
     "deepgram/nova-2-voicemail": {
         "mode": "audio_transcription",
-        "input_cost_per_second": 0.00007167,
+        "input_cost_per_second": 7.167e-05,
         "output_cost_per_second": 0.0,
         "litellm_provider": "deepgram",
         "supported_endpoints": [
@@ -14882,7 +15052,7 @@
     },
     "deepgram/nova-2-finance": {
         "mode": "audio_transcription",
-        "input_cost_per_second": 0.00007167,
+        "input_cost_per_second": 7.167e-05,
         "output_cost_per_second": 0.0,
         "litellm_provider": "deepgram",
         "supported_endpoints": [
@@ -14896,7 +15066,7 @@
     },
     "deepgram/nova-2-conversationalai": {
         "mode": "audio_transcription",
-        "input_cost_per_second": 0.00007167,
+        "input_cost_per_second": 7.167e-05,
         "output_cost_per_second": 0.0,
         "litellm_provider": "deepgram",
         "supported_endpoints": [
@@ -14910,7 +15080,7 @@
     },
     "deepgram/nova-2-video": {
         "mode": "audio_transcription",
-        "input_cost_per_second": 0.00007167,
+        "input_cost_per_second": 7.167e-05,
         "output_cost_per_second": 0.0,
         "litellm_provider": "deepgram",
         "supported_endpoints": [
@@ -14924,7 +15094,7 @@
     },
     "deepgram/nova-2-drivethru": {
         "mode": "audio_transcription",
-        "input_cost_per_second": 0.00007167,
+        "input_cost_per_second": 7.167e-05,
         "output_cost_per_second": 0.0,
         "litellm_provider": "deepgram",
         "supported_endpoints": [
@@ -14938,7 +15108,7 @@
     },
     "deepgram/nova-2-automotive": {
         "mode": "audio_transcription",
-        "input_cost_per_second": 0.00007167,
+        "input_cost_per_second": 7.167e-05,
         "output_cost_per_second": 0.0,
         "litellm_provider": "deepgram",
         "supported_endpoints": [
@@ -14952,7 +15122,7 @@
     },
     "deepgram/nova-2-atc": {
         "mode": "audio_transcription",
-        "input_cost_per_second": 0.00007167,
+        "input_cost_per_second": 7.167e-05,
         "output_cost_per_second": 0.0,
         "litellm_provider": "deepgram",
         "supported_endpoints": [
@@ -14966,7 +15136,7 @@
     },
     "deepgram/nova": {
         "mode": "audio_transcription",
-        "input_cost_per_second": 0.00007167,
+        "input_cost_per_second": 7.167e-05,
         "output_cost_per_second": 0.0,
         "litellm_provider": "deepgram",
         "supported_endpoints": [
@@ -14980,7 +15150,7 @@
     },
     "deepgram/nova-general": {
         "mode": "audio_transcription",
-        "input_cost_per_second": 0.00007167,
+        "input_cost_per_second": 7.167e-05,
         "output_cost_per_second": 0.0,
         "litellm_provider": "deepgram",
         "supported_endpoints": [
@@ -14994,7 +15164,7 @@
     },
     "deepgram/nova-phonecall": {
         "mode": "audio_transcription",
-        "input_cost_per_second": 0.00007167,
+        "input_cost_per_second": 7.167e-05,
         "output_cost_per_second": 0.0,
         "litellm_provider": "deepgram",
         "supported_endpoints": [
@@ -15266,4 +15436,4 @@
             "notes": "Deepgram's hosted OpenAI Whisper models - pricing may differ from native Deepgram models"
         }
     }
-}
+}

litellm/proxy/_experimental/mcp_server/auth/litellm_auth_handler.py

@@ -1,3 +1,5 @@
+from typing import Optional
+
 from mcp.server.auth.middleware.bearer_auth import AuthenticatedUser
 
 from litellm.proxy._types import UserAPIKeyAuth
@@ -8,5 +10,6 @@ class LiteLLMAuthenticatedUser(AuthenticatedUser):
     Wrapper class to make UserAPIKeyAuth compatible with MCP's AuthenticatedUser
     """
 
-    def __init__(self, user_api_key_auth: UserAPIKeyAuth):
+    def __init__(self, user_api_key_auth: UserAPIKeyAuth, mcp_auth_header: Optional[str] = None):
         self.user_api_key_auth = user_api_key_auth
+        self.mcp_auth_header = mcp_auth_header

litellm/proxy/_experimental/mcp_server/auth/user_api_key_auth_mcp.py

@@ -1,11 +1,11 @@
-from typing import List, Optional
+from typing import List, Optional, Tuple
 
 from starlette.datastructures import Headers
 from starlette.requests import Request
 from starlette.types import Scope
 
 from litellm._logging import verbose_logger
-from litellm.proxy._types import LiteLLM_TeamTable, UserAPIKeyAuth
+from litellm.proxy._types import LiteLLM_TeamTable, SpecialHeaders, UserAPIKeyAuth
 from litellm.proxy.auth.user_api_key_auth import user_api_key_auth
 
 
@@ -16,11 +16,14 @@ class UserAPIKeyAuthMCP:
     Utilizes the main `user_api_key_auth` function to validate the request
     """
 
-    LITELLM_API_KEY_HEADER_NAME_PRIMARY = "x-litellm-api-key"
-    LITELLM_API_KEY_HEADER_NAME_SECONDARY = "Authorization"
+    LITELLM_API_KEY_HEADER_NAME_PRIMARY = SpecialHeaders.custom_litellm_api_key.value
+    LITELLM_API_KEY_HEADER_NAME_SECONDARY = SpecialHeaders.openai_authorization.value
+
+    # This is the header to use if you want LiteLLM to use this header for authenticating to the MCP server
+    LITELLM_MCP_AUTH_HEADER_NAME = SpecialHeaders.mcp_auth.value
 
     @staticmethod
-    async def user_api_key_auth_mcp(scope: Scope) -> UserAPIKeyAuth:
+    async def user_api_key_auth_mcp(scope: Scope) -> Tuple[UserAPIKeyAuth, Optional[str]]:
         """
         Validate and extract headers from the ASGI scope for MCP requests.
 
@@ -29,6 +32,7 @@ class UserAPIKeyAuthMCP:
 
         Returns:
             UserAPIKeyAuth containing validated authentication information
+            mcp_auth_header: Optional[str] MCP auth header to be passed to the MCP server
 
         Raises:
             HTTPException: If headers are invalid or missing required headers
@@ -37,6 +41,7 @@ class UserAPIKeyAuthMCP:
         litellm_api_key = (
             UserAPIKeyAuthMCP.get_litellm_api_key_from_headers(headers) or ""
         )
+        mcp_auth_header = headers.get(UserAPIKeyAuthMCP.LITELLM_MCP_AUTH_HEADER_NAME)
 
         # Create a proper Request object with mock body method to avoid ASGI receive channel issues
         request = Request(scope=scope)
@@ -52,7 +57,7 @@ class UserAPIKeyAuthMCP:
             api_key=litellm_api_key, request=request
         )
 
-        return validated_user_api_key_auth
+        return validated_user_api_key_auth, mcp_auth_header
 
     @staticmethod
     def get_litellm_api_key_from_headers(headers: Headers) -> Optional[str]:

litellm/proxy/_experimental/mcp_server/mcp_server_manager.py

@@ -11,12 +11,12 @@ import hashlib
 import json
 from typing import Any, Dict, List, Optional, cast
 
-from mcp import ClientSession
-from mcp.client.sse import sse_client
+from mcp.types import CallToolRequestParams as MCPCallToolRequestParams
 from mcp.types import CallToolResult
 from mcp.types import Tool as MCPTool
 
 from litellm._logging import verbose_logger
+from litellm.experimental_mcp_client.client import MCPClient
 from litellm.proxy._experimental.mcp_server.auth.user_api_key_auth_mcp import (
     UserAPIKeyAuthMCP,
 )
@@ -29,12 +29,6 @@ from litellm.proxy._types import (
     MCPTransportType,
     UserAPIKeyAuth,
 )
-
-try:
-    from mcp.client.streamable_http import streamablehttp_client
-except ImportError:
-    streamablehttp_client = None  # type: ignore
-
 from litellm.types.mcp_server.mcp_server_manager import MCPInfo, MCPServer
 
 
@@ -164,7 +158,9 @@ class MCPServerManager:
             return list(self.get_registry().keys())
 
     async def list_tools(
-        self, user_api_key_auth: Optional[UserAPIKeyAuth] = None
+        self, 
+        user_api_key_auth: Optional[UserAPIKeyAuth] = None,
+        mcp_auth_header: Optional[str] = None,
     ) -> List[MCPTool]:
         """
         List all tools available across all MCP Servers.
@@ -183,7 +179,10 @@ class MCPServerManager:
                 verbose_logger.warning(f"MCP Server {server_id} not found")
                 continue
             try:
-                tools = await self._get_tools_from_server(server)
+                tools = await self._get_tools_from_server(
+                    server=server,
+                    mcp_auth_header=mcp_auth_header,
+                )
                 list_tools_result.extend(tools)
             except Exception as e:
                 verbose_logger.exception(
@@ -192,7 +191,30 @@ class MCPServerManager:
 
         return list_tools_result
 
-    async def _get_tools_from_server(self, server: MCPServer) -> List[MCPTool]:
+    #########################################################
+    # Methods that call the upstream MCP servers
+    #########################################################
+    def _create_mcp_client(self, server: MCPServer, mcp_auth_header: Optional[str] = None) -> MCPClient:
+        """
+        Create an MCPClient instance for the given server.
+
+        Args:
+            server (MCPServer): The server configuration
+            mcp_auth_header: MCP auth header to be passed to the MCP server. This is optional and will be used if provided.
+
+        Returns:
+            MCPClient: Configured MCP client instance
+        """
+        transport = server.transport or MCPTransport.sse
+        return MCPClient(
+            server_url=server.url,
+            transport_type=transport,
+            auth_type=server.auth_type,
+            auth_value=mcp_auth_header or server.authentication_token,
+            timeout=60.0,
+        )
+
+    async def _get_tools_from_server(self, server: MCPServer, mcp_auth_header: Optional[str] = None) -> List[MCPTool]:
         """
         Helper method to get tools from a single MCP server.
 
@@ -203,57 +225,51 @@ class MCPServerManager:
             List[MCPTool]: List of tools available on the server
         """
         verbose_logger.debug(f"Connecting to url: {server.url}")
-
         verbose_logger.info("_get_tools_from_server...")
-        # send transport to connect to the server
-        if server.transport is None or server.transport == MCPTransport.sse:
-            async with sse_client(url=server.url) as (read, write):
-                async with ClientSession(read, write) as session:
-                    await session.initialize()
 
-                    tools_result = await session.list_tools()
-                    verbose_logger.debug(f"Tools from {server.name}: {tools_result}")
+        client = self._create_mcp_client(
+            server=server,
+            mcp_auth_header=mcp_auth_header,
+        )
+        async with client:
+            tools = await client.list_tools()
+            verbose_logger.debug(f"Tools from {server.name}: {tools}")
 
-                    # Update tool to server mapping
-                    for tool in tools_result.tools:
-                        self.tool_name_to_mcp_server_name_mapping[tool.name] = (
-                            server.name
-                        )
+            # Update tool to server mapping
+            for tool in tools:
+                self.tool_name_to_mcp_server_name_mapping[tool.name] = server.name
 
-                    return tools_result.tools
-        elif server.transport == MCPTransport.http:
-            if streamablehttp_client is None:
-                verbose_logger.error(
-                    "streamablehttp_client not available - install mcp with HTTP support"
-                )
-                raise ValueError(
-                    "streamablehttp_client not available - please run `pip install mcp -U`"
-                )
-            verbose_logger.debug(f"Using HTTP streamable transport for {server.url}")
-            async with streamablehttp_client(
-                url=server.url,
-            ) as (read_stream, write_stream, get_session_id):
-                async with ClientSession(read_stream, write_stream) as session:
-                    await session.initialize()
+            return tools
+    
+    async def call_tool(
+        self, 
+        name: str, 
+        arguments: Dict[str, Any],
+        user_api_key_auth: Optional[UserAPIKeyAuth] = None,
+        mcp_auth_header: Optional[str] = None,
+    ) -> CallToolResult:
+        """
+        Call a tool with the given name and arguments
+        """
+        mcp_server = self._get_mcp_server_from_tool_name(name)
+        if mcp_server is None:
+            raise ValueError(f"Tool {name} not found")
 
-                    if get_session_id is not None:
-                        session_id = get_session_id()
-                        if session_id:
-                            verbose_logger.debug(f"HTTP session ID: {session_id}")
+        client = self._create_mcp_client(
+            server=mcp_server,
+            mcp_auth_header=mcp_auth_header,
+        )
+        async with client:
+            call_tool_params = MCPCallToolRequestParams(
+                name=name,
+                arguments=arguments,
+            )
+            return await client.call_tool(call_tool_params)
+    
+    #########################################################
+    # End of Methods that call the upstream MCP servers
+    #########################################################
 
-                    tools_result = await session.list_tools()
-                    verbose_logger.debug(f"Tools from {server.name}: {tools_result}")
-
-                    # Update tool to server mapping
-                    for tool in tools_result.tools:
-                        self.tool_name_to_mcp_server_name_mapping[tool.name] = (
-                            server.name
-                        )
-
-                    return tools_result.tools
-        else:
-            verbose_logger.warning(f"Unsupported transport type: {server.transport}")
-            return []
 
     def initialize_tool_name_to_mcp_server_name_mapping(self):
         """
@@ -278,46 +294,6 @@ class MCPServerManager:
             for tool in tools:
                 self.tool_name_to_mcp_server_name_mapping[tool.name] = server.name
 
-    async def call_tool(self, name: str, arguments: Dict[str, Any]):
-        """
-        Call a tool with the given name and arguments
-        """
-        mcp_server = self._get_mcp_server_from_tool_name(name)
-        if mcp_server is None:
-            raise ValueError(f"Tool {name} not found")
-        elif mcp_server.transport is None or mcp_server.transport == MCPTransport.sse:
-            async with sse_client(url=mcp_server.url) as (read, write):
-                async with ClientSession(read, write) as session:
-                    await session.initialize()
-                    return await session.call_tool(name, arguments)
-        elif mcp_server.transport == MCPTransport.http:
-            if streamablehttp_client is None:
-                verbose_logger.error(
-                    "streamablehttp_client not available - install mcp with HTTP support"
-                )
-                raise ValueError(
-                    "streamablehttp_client not available - please run `pip install mcp -U`"
-                )
-            verbose_logger.debug(
-                f"Using HTTP streamable transport for tool call: {name}"
-            )
-            async with streamablehttp_client(
-                url=mcp_server.url,
-            ) as (read_stream, write_stream, get_session_id):
-                async with ClientSession(read_stream, write_stream) as session:
-                    await session.initialize()
-
-                    if get_session_id is not None:
-                        session_id = get_session_id()
-                        if session_id:
-                            verbose_logger.debug(
-                                f"HTTP session ID for tool call: {session_id}"
-                            )
-
-                    return await session.call_tool(name, arguments)
-        else:
-            return CallToolResult(content=[], isError=True)
-
     def _get_mcp_server_from_tool_name(self, tool_name: str) -> Optional[MCPServer]:
         """
         Get the MCP Server from the tool name

litellm/proxy/_experimental/mcp_server/rest_endpoints.py

@@ -70,7 +70,9 @@ if MCP_AVAILABLE:
             if server_id and server.server_id != server_id:
                 continue
             try:
-                tools = await global_mcp_server_manager._get_tools_from_server(server)
+                tools = await global_mcp_server_manager._get_tools_from_server(
+                    server=server,
+                )
                 for tool in tools:
                     list_tools_result.append(
                         ListMCPToolsRestAPIResponseObject(

litellm/proxy/_experimental/mcp_server/server.py

@@ -4,7 +4,7 @@ LiteLLM MCP Server Routes
 
 import asyncio
 import contextlib
-from typing import Any, AsyncIterator, Dict, List, Optional, Union
+from typing import Any, AsyncIterator, Dict, List, Optional, Tuple, Union
 
 from fastapi import FastAPI, HTTPException
 from pydantic import ConfigDict
@@ -166,11 +166,14 @@ if MCP_AVAILABLE:
         List all available tools
         """
         # Get user authentication from context variable
-        user_api_key_auth = get_auth_context()
+        user_api_key_auth, mcp_auth_header = get_auth_context()
         verbose_logger.debug(
             f"MCP list_tools - User API Key Auth from context: {user_api_key_auth}"
         )
-        return await _list_mcp_tools(user_api_key_auth)
+        return await _list_mcp_tools(
+            user_api_key_auth=user_api_key_auth,
+            mcp_auth_header=mcp_auth_header,
+        )
 
     @server.call_tool()
     async def mcp_server_tool_call(
@@ -190,9 +193,15 @@ if MCP_AVAILABLE:
             HTTPException: If tool not found or arguments missing
         """
         # Validate arguments
+        user_api_key_auth, mcp_auth_header = get_auth_context()
+        verbose_logger.debug(
+            f"MCP mcp_server_tool_call - User API Key Auth from context: {user_api_key_auth}"
+        )
         response = await call_mcp_tool(
             name=name,
             arguments=arguments,
+            user_api_key_auth=user_api_key_auth,
+            mcp_auth_header=mcp_auth_header,
         )
         return response
 
@@ -206,6 +215,7 @@ if MCP_AVAILABLE:
 
     async def _list_mcp_tools(
         user_api_key_auth: Optional[UserAPIKeyAuth] = None,
+        mcp_auth_header: Optional[str] = None,
     ) -> List[MCPTool]:
         """
         List all available tools
@@ -229,6 +239,7 @@ if MCP_AVAILABLE:
         tools_from_mcp_servers: List[MCPTool] = (
             await global_mcp_server_manager.list_tools(
                 user_api_key_auth=user_api_key_auth,
+                mcp_auth_header=mcp_auth_header,
             )
         )
         verbose_logger.debug("TOOLS FROM MCP SERVERS: %s", tools_from_mcp_servers)
@@ -238,7 +249,11 @@ if MCP_AVAILABLE:
 
     @client
     async def call_mcp_tool(
-        name: str, arguments: Optional[Dict[str, Any]] = None, **kwargs: Any
+        name: str, 
+        arguments: Optional[Dict[str, Any]] = None, 
+        user_api_key_auth: Optional[UserAPIKeyAuth] = None,
+        mcp_auth_header: Optional[str] = None, 
+        **kwargs: Any
     ) -> List[Union[MCPTextContent, MCPImageContent, MCPEmbeddedResource]]:
         """
         Call a specific tool with the provided arguments
@@ -270,7 +285,12 @@ if MCP_AVAILABLE:
 
         # Try managed server tool first
         if name in global_mcp_server_manager.tool_name_to_mcp_server_name_mapping:
-            return await _handle_managed_mcp_tool(name, arguments)
+            return await _handle_managed_mcp_tool(
+                name=name,
+                arguments=arguments,
+                user_api_key_auth=user_api_key_auth,
+                mcp_auth_header=mcp_auth_header,
+            )
 
         # Fall back to local tool registry
         return await _handle_local_mcp_tool(name, arguments)
@@ -295,12 +315,17 @@ if MCP_AVAILABLE:
             )
 
     async def _handle_managed_mcp_tool(
-        name: str, arguments: Dict[str, Any]
+        name: str, 
+        arguments: Dict[str, Any],
+        user_api_key_auth: Optional[UserAPIKeyAuth] = None,
+        mcp_auth_header: Optional[str] = None,
     ) -> List[Union[MCPTextContent, MCPImageContent, MCPEmbeddedResource]]:
         """Handle tool execution for managed server tools"""
         call_tool_result = await global_mcp_server_manager.call_tool(
             name=name,
             arguments=arguments,
+            user_api_key_auth=user_api_key_auth,
+            mcp_auth_header=mcp_auth_header,
         )
         verbose_logger.debug("CALL TOOL RESULT: %s", call_tool_result)
         return call_tool_result.content
@@ -325,11 +350,14 @@ if MCP_AVAILABLE:
         """Handle MCP requests through StreamableHTTP."""
         try:
             # Validate headers and log request info
-            user_api_key_auth: UserAPIKeyAuth = (
+            user_api_key_auth, mcp_auth_header = (
                 await UserAPIKeyAuthMCP.user_api_key_auth_mcp(scope)
             )
             # Set the auth context variable for easy access in MCP functions
-            set_auth_context(user_api_key_auth)
+            set_auth_context(
+                user_api_key_auth=user_api_key_auth,
+                mcp_auth_header=mcp_auth_header,
+            )
 
             # Ensure session managers are initialized
             if not _SESSION_MANAGERS_INITIALIZED:
@@ -346,11 +374,14 @@ if MCP_AVAILABLE:
         """Handle MCP requests through SSE."""
         try:
             # Validate headers and log request info
-            user_api_key_auth: UserAPIKeyAuth = (
+            user_api_key_auth, mcp_auth_header = (
                 await UserAPIKeyAuthMCP.user_api_key_auth_mcp(scope)
             )
             # Set the auth context variable for easy access in MCP functions
-            set_auth_context(user_api_key_auth)
+            set_auth_context(
+                user_api_key_auth=user_api_key_auth,
+                mcp_auth_header=mcp_auth_header,
+            )
 
             # Ensure session managers are initialized
             if not _SESSION_MANAGERS_INITIALIZED:
@@ -390,17 +421,31 @@ if MCP_AVAILABLE:
     ############ Auth Context Functions ####################
     ########################################################
 
-    def set_auth_context(user_api_key_auth: UserAPIKeyAuth) -> None:
-        """Set the UserAPIKeyAuth in the auth context variable."""
-        auth_user = LiteLLMAuthenticatedUser(user_api_key_auth)
+    def set_auth_context(user_api_key_auth: UserAPIKeyAuth, mcp_auth_header: Optional[str] = None) -> None:
+        """
+        Set the UserAPIKeyAuth in the auth context variable.
+
+        Args:
+            user_api_key_auth: UserAPIKeyAuth object
+            mcp_auth_header: MCP auth header to be passed to the MCP server
+        """
+        auth_user = LiteLLMAuthenticatedUser(
+            user_api_key_auth=user_api_key_auth,
+            mcp_auth_header=mcp_auth_header,
+        )
         auth_context_var.set(auth_user)
 
-    def get_auth_context() -> Optional[UserAPIKeyAuth]:
-        """Get the UserAPIKeyAuth from the auth context variable."""
+    def get_auth_context() -> Tuple[Optional[UserAPIKeyAuth], Optional[str]]:
+        """
+        Get the UserAPIKeyAuth from the auth context variable.
+
+        Returns:
+            Tuple[Optional[UserAPIKeyAuth], Optional[str]]: UserAPIKeyAuth object and MCP auth header
+        """
         auth_user = auth_context_var.get()
         if auth_user and isinstance(auth_user, LiteLLMAuthenticatedUser):
-            return auth_user.user_api_key_auth
-        return None
+            return auth_user.user_api_key_auth, auth_user.mcp_auth_header
+        return None, None
 
     ########################################################
     ############ End of Auth Context Functions #############

litellm/proxy/_experimental/out/_next/static/chunks/webpack-a426aae3231a8df1.js

@@ -1 +1 @@
-!function(){"use strict";var e,t,n,r,o,u,i,c,f,a={},l={};function d(e){var t=l[e];if(void 0!==t)return t.exports;var n=l[e]={id:e,loaded:!1,exports:{}},r=!0;try{a[e].call(n.exports,n,n.exports,d),r=!1}finally{r&&delete l[e]}return n.loaded=!0,n.exports}d.m=a,e=[],d.O=function(t,n,r,o){if(n){o=o||0;for(var u=e.length;u>0&&e[u-1][2]>o;u--)e[u]=e[u-1];e[u]=[n,r,o];return}for(var i=1/0,u=0;u<e.length;u++){for(var n=e[u][0],r=e[u][1],o=e[u][2],c=!0,f=0;f<n.length;f++)i>=o&&Object.keys(d.O).every(function(e){return d.O[e](n[f])})?n.splice(f--,1):(c=!1,o<i&&(i=o));if(c){e.splice(u--,1);var a=r();void 0!==a&&(t=a)}}return t},d.n=function(e){var t=e&&e.__esModule?function(){return e.default}:function(){return e};return d.d(t,{a:t}),t},n=Object.getPrototypeOf?function(e){return Object.getPrototypeOf(e)}:function(e){return e.__proto__},d.t=function(e,r){if(1&r&&(e=this(e)),8&r||"object"==typeof e&&e&&(4&r&&e.__esModule||16&r&&"function"==typeof e.then))return e;var o=Object.create(null);d.r(o);var u={};t=t||[null,n({}),n([]),n(n)];for(var i=2&r&&e;"object"==typeof i&&!~t.indexOf(i);i=n(i))Object.getOwnPropertyNames(i).forEach(function(t){u[t]=function(){return e[t]}});return u.default=function(){return e},d.d(o,u),o},d.d=function(e,t){for(var n in t)d.o(t,n)&&!d.o(e,n)&&Object.defineProperty(e,n,{enumerable:!0,get:t[n]})},d.f={},d.e=function(e){return Promise.all(Object.keys(d.f).reduce(function(t,n){return d.f[n](e,t),t},[]))},d.u=function(e){},d.miniCssF=function(e){},d.g=function(){if("object"==typeof globalThis)return globalThis;try{return this||Function("return this")()}catch(e){if("object"==typeof window)return window}}(),d.o=function(e,t){return Object.prototype.hasOwnProperty.call(e,t)},r={},o="_N_E:",d.l=function(e,t,n,u){if(r[e]){r[e].push(t);return}if(void 0!==n)for(var i,c,f=document.getElementsByTagName("script"),a=0;a<f.length;a++){var l=f[a];if(l.getAttribute("src")==e||l.getAttribute("data-webpack")==o+n){i=l;break}}i||(c=!0,(i=document.createElement("script")).charset="utf-8",i.timeout=120,d.nc&&i.setAttribute("nonce",d.nc),i.setAttribute("data-webpack",o+n),i.src=d.tu(e)),r[e]=[t];var s=function(t,n){i.onerror=i.onload=null,clearTimeout(p);var o=r[e];if(delete r[e],i.parentNode&&i.parentNode.removeChild(i),o&&o.forEach(function(e){return e(n)}),t)return t(n)},p=setTimeout(s.bind(null,void 0,{type:"timeout",target:i}),12e4);i.onerror=s.bind(null,i.onerror),i.onload=s.bind(null,i.onload),c&&document.head.appendChild(i)},d.r=function(e){"undefined"!=typeof Symbol&&Symbol.toStringTag&&Object.defineProperty(e,Symbol.toStringTag,{value:"Module"}),Object.defineProperty(e,"__esModule",{value:!0})},d.nmd=function(e){return e.paths=[],e.children||(e.children=[]),e},d.tt=function(){return void 0===u&&(u={createScriptURL:function(e){return e}},"undefined"!=typeof trustedTypes&&trustedTypes.createPolicy&&(u=trustedTypes.createPolicy("nextjs#bundler",u))),u},d.tu=function(e){return d.tt().createScriptURL(e)},d.p="/_next/",i={272:0,919:0,986:0},d.f.j=function(e,t){var n=d.o(i,e)?i[e]:void 0;if(0!==n){if(n)t.push(n[2]);else if(/^(272|919|986)$/.test(e))i[e]=0;else{var r=new Promise(function(t,r){n=i[e]=[t,r]});t.push(n[2]=r);var o=d.p+d.u(e),u=Error();d.l(o,function(t){if(d.o(i,e)&&(0!==(n=i[e])&&(i[e]=void 0),n)){var r=t&&("load"===t.type?"missing":t.type),o=t&&t.target&&t.target.src;u.message="Loading chunk "+e+" failed.\n("+r+": "+o+")",u.name="ChunkLoadError",u.type=r,u.request=o,n[1](u)}},"chunk-"+e,e)}}},d.O.j=function(e){return 0===i[e]},c=function(e,t){var n,r,o=t[0],u=t[1],c=t[2],f=0;if(o.some(function(e){return 0!==i[e]})){for(n in u)d.o(u,n)&&(d.m[n]=u[n]);if(c)var a=c(d)}for(e&&e(t);f<o.length;f++)r=o[f],d.o(i,r)&&i[r]&&i[r][0](),i[r]=0;return d.O(a)},(f=self.webpackChunk_N_E=self.webpackChunk_N_E||[]).forEach(c.bind(null,0)),f.push=c.bind(null,f.push.bind(f))}();
+!function(){"use strict";var e,t,n,r,o,u,i,c,f,a={},l={};function d(e){var t=l[e];if(void 0!==t)return t.exports;var n=l[e]={id:e,loaded:!1,exports:{}},r=!0;try{a[e].call(n.exports,n,n.exports,d),r=!1}finally{r&&delete l[e]}return n.loaded=!0,n.exports}d.m=a,e=[],d.O=function(t,n,r,o){if(n){o=o||0;for(var u=e.length;u>0&&e[u-1][2]>o;u--)e[u]=e[u-1];e[u]=[n,r,o];return}for(var i=1/0,u=0;u<e.length;u++){for(var n=e[u][0],r=e[u][1],o=e[u][2],c=!0,f=0;f<n.length;f++)i>=o&&Object.keys(d.O).every(function(e){return d.O[e](n[f])})?n.splice(f--,1):(c=!1,o<i&&(i=o));if(c){e.splice(u--,1);var a=r();void 0!==a&&(t=a)}}return t},d.n=function(e){var t=e&&e.__esModule?function(){return e.default}:function(){return e};return d.d(t,{a:t}),t},n=Object.getPrototypeOf?function(e){return Object.getPrototypeOf(e)}:function(e){return e.__proto__},d.t=function(e,r){if(1&r&&(e=this(e)),8&r||"object"==typeof e&&e&&(4&r&&e.__esModule||16&r&&"function"==typeof e.then))return e;var o=Object.create(null);d.r(o);var u={};t=t||[null,n({}),n([]),n(n)];for(var i=2&r&&e;"object"==typeof i&&!~t.indexOf(i);i=n(i))Object.getOwnPropertyNames(i).forEach(function(t){u[t]=function(){return e[t]}});return u.default=function(){return e},d.d(o,u),o},d.d=function(e,t){for(var n in t)d.o(t,n)&&!d.o(e,n)&&Object.defineProperty(e,n,{enumerable:!0,get:t[n]})},d.f={},d.e=function(e){return Promise.all(Object.keys(d.f).reduce(function(t,n){return d.f[n](e,t),t},[]))},d.u=function(e){},d.miniCssF=function(e){},d.g=function(){if("object"==typeof globalThis)return globalThis;try{return this||Function("return this")()}catch(e){if("object"==typeof window)return window}}(),d.o=function(e,t){return Object.prototype.hasOwnProperty.call(e,t)},r={},o="_N_E:",d.l=function(e,t,n,u){if(r[e]){r[e].push(t);return}if(void 0!==n)for(var i,c,f=document.getElementsByTagName("script"),a=0;a<f.length;a++){var l=f[a];if(l.getAttribute("src")==e||l.getAttribute("data-webpack")==o+n){i=l;break}}i||(c=!0,(i=document.createElement("script")).charset="utf-8",i.timeout=120,d.nc&&i.setAttribute("nonce",d.nc),i.setAttribute("data-webpack",o+n),i.src=d.tu(e)),r[e]=[t];var s=function(t,n){i.onerror=i.onload=null,clearTimeout(p);var o=r[e];if(delete r[e],i.parentNode&&i.parentNode.removeChild(i),o&&o.forEach(function(e){return e(n)}),t)return t(n)},p=setTimeout(s.bind(null,void 0,{type:"timeout",target:i}),12e4);i.onerror=s.bind(null,i.onerror),i.onload=s.bind(null,i.onload),c&&document.head.appendChild(i)},d.r=function(e){"undefined"!=typeof Symbol&&Symbol.toStringTag&&Object.defineProperty(e,Symbol.toStringTag,{value:"Module"}),Object.defineProperty(e,"__esModule",{value:!0})},d.nmd=function(e){return e.paths=[],e.children||(e.children=[]),e},d.tt=function(){return void 0===u&&(u={createScriptURL:function(e){return e}},"undefined"!=typeof trustedTypes&&trustedTypes.createPolicy&&(u=trustedTypes.createPolicy("nextjs#bundler",u))),u},d.tu=function(e){return d.tt().createScriptURL(e)},d.p="/litellm-asset-prefix/_next/",i={272:0,919:0,986:0},d.f.j=function(e,t){var n=d.o(i,e)?i[e]:void 0;if(0!==n){if(n)t.push(n[2]);else if(/^(272|919|986)$/.test(e))i[e]=0;else{var r=new Promise(function(t,r){n=i[e]=[t,r]});t.push(n[2]=r);var o=d.p+d.u(e),u=Error();d.l(o,function(t){if(d.o(i,e)&&(0!==(n=i[e])&&(i[e]=void 0),n)){var r=t&&("load"===t.type?"missing":t.type),o=t&&t.target&&t.target.src;u.message="Loading chunk "+e+" failed.\n("+r+": "+o+")",u.name="ChunkLoadError",u.type=r,u.request=o,n[1](u)}},"chunk-"+e,e)}}},d.O.j=function(e){return 0===i[e]},c=function(e,t){var n,r,o=t[0],u=t[1],c=t[2],f=0;if(o.some(function(e){return 0!==i[e]})){for(n in u)d.o(u,n)&&(d.m[n]=u[n]);if(c)var a=c(d)}for(e&&e(t);f<o.length;f++)r=o[f],d.o(i,r)&&i[r]&&i[r][0](),i[r]=0;return d.O(a)},(f=self.webpackChunk_N_E=self.webpackChunk_N_E||[]).forEach(c.bind(null,0)),f.push=c.bind(null,f.push.bind(f))}();

litellm/proxy/_experimental/out/_next/static/css/31b7f215e119031e.css

@@ -1 +1 @@
-@font-face{font-family:__Inter_b0dd8a;font-style:normal;font-weight:100 900;font-display:swap;src:url(/_next/static/media/55c55f0601d81cf3-s.woff2) format("woff2");unicode-range:u+0460-052f,u+1c80-1c8a,u+20b4,u+2de0-2dff,u+a640-a69f,u+fe2e-fe2f}@font-face{font-family:__Inter_b0dd8a;font-style:normal;font-weight:100 900;font-display:swap;src:url(/_next/static/media/26a46d62cd723877-s.woff2) format("woff2");unicode-range:u+0301,u+0400-045f,u+0490-0491,u+04b0-04b1,u+2116}@font-face{font-family:__Inter_b0dd8a;font-style:normal;font-weight:100 900;font-display:swap;src:url(/_next/static/media/97e0cb1ae144a2a9-s.woff2) format("woff2");unicode-range:u+1f??}@font-face{font-family:__Inter_b0dd8a;font-style:normal;font-weight:100 900;font-display:swap;src:url(/_next/static/media/581909926a08bbc8-s.woff2) format("woff2");unicode-range:u+0370-0377,u+037a-037f,u+0384-038a,u+038c,u+038e-03a1,u+03a3-03ff}@font-face{font-family:__Inter_b0dd8a;font-style:normal;font-weight:100 900;font-display:swap;src:url(/_next/static/media/df0a9ae256c0569c-s.woff2) format("woff2");unicode-range:u+0102-0103,u+0110-0111,u+0128-0129,u+0168-0169,u+01a0-01a1,u+01af-01b0,u+0300-0301,u+0303-0304,u+0308-0309,u+0323,u+0329,u+1ea0-1ef9,u+20ab}@font-face{font-family:__Inter_b0dd8a;font-style:normal;font-weight:100 900;font-display:swap;src:url(/_next/static/media/8e9860b6e62d6359-s.woff2) format("woff2");unicode-range:u+0100-02ba,u+02bd-02c5,u+02c7-02cc,u+02ce-02d7,u+02dd-02ff,u+0304,u+0308,u+0329,u+1d00-1dbf,u+1e00-1e9f,u+1ef2-1eff,u+2020,u+20a0-20ab,u+20ad-20c0,u+2113,u+2c60-2c7f,u+a720-a7ff}@font-face{font-family:__Inter_b0dd8a;font-style:normal;font-weight:100 900;font-display:swap;src:url(/_next/static/media/e4af272ccee01ff0-s.p.woff2) format("woff2");unicode-range:u+00??,u+0131,u+0152-0153,u+02bb-02bc,u+02c6,u+02da,u+02dc,u+0304,u+0308,u+0329,u+2000-206f,u+20ac,u+2122,u+2191,u+2193,u+2212,u+2215,u+feff,u+fffd}@font-face{font-family:__Inter_Fallback_b0dd8a;src:local("Arial");ascent-override:90.49%;descent-override:22.56%;line-gap-override:0.00%;size-adjust:107.06%}.__className_b0dd8a{font-family:__Inter_b0dd8a,__Inter_Fallback_b0dd8a;font-style:normal}
+@font-face{font-family:__Inter_b0dd8a;font-style:normal;font-weight:100 900;font-display:swap;src:url(/litellm-asset-prefix/_next/static/media/55c55f0601d81cf3-s.woff2) format("woff2");unicode-range:u+0460-052f,u+1c80-1c8a,u+20b4,u+2de0-2dff,u+a640-a69f,u+fe2e-fe2f}@font-face{font-family:__Inter_b0dd8a;font-style:normal;font-weight:100 900;font-display:swap;src:url(/litellm-asset-prefix/_next/static/media/26a46d62cd723877-s.woff2) format("woff2");unicode-range:u+0301,u+0400-045f,u+0490-0491,u+04b0-04b1,u+2116}@font-face{font-family:__Inter_b0dd8a;font-style:normal;font-weight:100 900;font-display:swap;src:url(/litellm-asset-prefix/_next/static/media/97e0cb1ae144a2a9-s.woff2) format("woff2");unicode-range:u+1f??}@font-face{font-family:__Inter_b0dd8a;font-style:normal;font-weight:100 900;font-display:swap;src:url(/litellm-asset-prefix/_next/static/media/581909926a08bbc8-s.woff2) format("woff2");unicode-range:u+0370-0377,u+037a-037f,u+0384-038a,u+038c,u+038e-03a1,u+03a3-03ff}@font-face{font-family:__Inter_b0dd8a;font-style:normal;font-weight:100 900;font-display:swap;src:url(/litellm-asset-prefix/_next/static/media/df0a9ae256c0569c-s.woff2) format("woff2");unicode-range:u+0102-0103,u+0110-0111,u+0128-0129,u+0168-0169,u+01a0-01a1,u+01af-01b0,u+0300-0301,u+0303-0304,u+0308-0309,u+0323,u+0329,u+1ea0-1ef9,u+20ab}@font-face{font-family:__Inter_b0dd8a;font-style:normal;font-weight:100 900;font-display:swap;src:url(/litellm-asset-prefix/_next/static/media/8e9860b6e62d6359-s.woff2) format("woff2");unicode-range:u+0100-02ba,u+02bd-02c5,u+02c7-02cc,u+02ce-02d7,u+02dd-02ff,u+0304,u+0308,u+0329,u+1d00-1dbf,u+1e00-1e9f,u+1ef2-1eff,u+2020,u+20a0-20ab,u+20ad-20c0,u+2113,u+2c60-2c7f,u+a720-a7ff}@font-face{font-family:__Inter_b0dd8a;font-style:normal;font-weight:100 900;font-display:swap;src:url(/litellm-asset-prefix/_next/static/media/e4af272ccee01ff0-s.p.woff2) format("woff2");unicode-range:u+00??,u+0131,u+0152-0153,u+02bb-02bc,u+02c6,u+02da,u+02dc,u+0304,u+0308,u+0329,u+2000-206f,u+20ac,u+2122,u+2191,u+2193,u+2212,u+2215,u+feff,u+fffd}@font-face{font-family:__Inter_Fallback_b0dd8a;src:local("Arial");ascent-override:90.49%;descent-override:22.56%;line-gap-override:0.00%;size-adjust:107.06%}.__className_b0dd8a{font-family:__Inter_b0dd8a,__Inter_Fallback_b0dd8a;font-style:normal}

litellm/proxy/_experimental/out/assets/logos/aws.svg

@@ -1,34 +1,34 @@
-<?xml version="1.0" encoding="utf-8"?>
-<!-- Generator: Adobe Illustrator 26.0.3, SVG Export Plug-In . SVG Version: 6.00 Build 0)  -->
-<svg version="1.0" id="katman_1" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" x="0px" y="0px"
-	 viewBox="0 0 600 450" style="enable-background:new 0 0 600 450;" xml:space="preserve">
-<style type="text/css">
-	.st0{fill:none;}
-	.st1{fill-rule:evenodd;clip-rule:evenodd;fill:#343B45;}
-	.st2{fill-rule:evenodd;clip-rule:evenodd;fill:#F4981A;}
-</style>
-<g id="_x31__stroke">
-	<g id="Amazon_1_">
-		<rect x="161.2" y="86.5" class="st0" width="277.8" height="277.8"/>
-		<g id="Amazon">
-			<path class="st1" d="M315,163.7c-8,0.6-17.2,1.2-26.4,2.4c-14.1,1.9-28.2,4.3-39.8,9.8c-22.7,9.2-38,28.8-38,57.6
-				c0,36.2,23.3,54.6,52.7,54.6c9.8,0,17.8-1.2,25.1-3.1c11.7-3.7,21.5-10.4,33.1-22.7c6.7,9.2,8.6,13.5,20.2,23.3
-				c3.1,1.2,6.1,1.2,8.6-0.6c7.4-6.1,20.3-17.2,27-23.3c3.1-2.5,2.5-6.1,0.6-9.2c-6.7-8.6-13.5-16-13.5-32.5V165
-				c0-23.3,1.9-44.8-15.3-60.7c-14.1-12.9-36.2-17.8-53.4-17.8h-7.4c-31.2,1.8-64.3,15.3-71.7,54c-1.2,4.9,2.5,6.8,4.9,7.4l34.3,4.3
-				c3.7-0.6,5.5-3.7,6.1-6.7c3.1-13.5,14.1-20.2,26.3-21.5h2.5c7.4,0,15.3,3.1,19.6,9.2c4.9,7.4,4.3,17.2,4.3,25.8L315,163.7
-				L315,163.7z M308.2,236.7c-4.3,8.6-11.7,14.1-19.6,16c-1.2,0-3.1,0.6-4.9,0.6c-13.5,0-21.4-10.4-21.4-25.8
-				c0-19.6,11.6-28.8,26.3-33.1c8-1.8,17.2-2.5,26.4-2.5v7.4C315,213.4,315.6,224.4,308.2,236.7z"/>
-			<path class="st2" d="M398.8,311.4c-1.4,0-2.8,0.3-4.1,0.9c-1.5,0.6-3,1.3-4.4,1.9l-2.1,0.9l-2.7,1.1v0
-				c-29.8,12.1-61.1,19.2-90.1,19.8c-1.1,0-2.1,0-3.2,0c-45.6,0-82.8-21.1-120.3-42c-1.3-0.7-2.7-1-4-1c-1.7,0-3.4,0.6-4.7,1.8
-				c-1.3,1.2-2,2.9-2,4.7c0,2.3,1.2,4.4,2.9,5.7c35.2,30.6,73.8,59,125.7,59c1,0,2,0,3.1,0c33-0.7,70.3-11.9,99.3-30.1l0.2-0.1
-				c3.8-2.3,7.6-4.9,11.2-7.7c2.2-1.6,3.8-4.2,3.8-6.9C407.2,314.6,403.2,311.4,398.8,311.4z M439,294.5L439,294.5
-				c-0.1-2.9-0.7-5.1-1.9-6.9l-0.1-0.2l-0.1-0.2c-1.2-1.3-2.4-1.8-3.7-2.4c-3.8-1.5-9.3-2.3-16-2.3c-4.8,0-10.1,0.5-15.4,1.6l0-0.4
-				l-5.3,1.8l-0.1,0l-3,1v0.1c-3.5,1.5-6.8,3.3-9.8,5.5c-1.9,1.4-3.4,3.2-3.5,6.1c0,1.5,0.7,3.3,2,4.3c1.3,1,2.8,1.4,4.1,1.4
-				c0.3,0,0.6,0,0.9-0.1l0.3,0l0.2,0c2.6-0.6,6.4-0.9,10.9-1.6c3.8-0.4,7.9-0.7,11.4-0.7c2.5,0,4.7,0.2,6.3,0.5
-				c0.8,0.2,1.3,0.4,1.6,0.5c0.1,0,0.2,0.1,0.2,0.1c0.1,0.2,0.2,0.8,0.1,1.5c0,2.9-1.2,8.4-2.9,13.7c-1.7,5.3-3.7,10.7-5,14.2
-				c-0.3,0.8-0.5,1.7-0.5,2.7c0,1.4,0.6,3.2,1.8,4.3c1.2,1.1,2.8,1.6,4.1,1.6h0.1c2,0,3.6-0.8,5.1-1.9
-				c13.6-12.2,18.3-31.7,18.5-42.6L439,294.5z"/>
-		</g>
-	</g>
-</g>
-</svg>
+<?xml version="1.0" encoding="utf-8"?>
+<!-- Generator: Adobe Illustrator 26.0.3, SVG Export Plug-In . SVG Version: 6.00 Build 0)  -->
+<svg version="1.0" id="katman_1" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" x="0px" y="0px"
+	 viewBox="0 0 600 450" style="enable-background:new 0 0 600 450;" xml:space="preserve">
+<style type="text/css">
+	.st0{fill:none;}
+	.st1{fill-rule:evenodd;clip-rule:evenodd;fill:#343B45;}
+	.st2{fill-rule:evenodd;clip-rule:evenodd;fill:#F4981A;}
+</style>
+<g id="_x31__stroke">
+	<g id="Amazon_1_">
+		<rect x="161.2" y="86.5" class="st0" width="277.8" height="277.8"/>
+		<g id="Amazon">
+			<path class="st1" d="M315,163.7c-8,0.6-17.2,1.2-26.4,2.4c-14.1,1.9-28.2,4.3-39.8,9.8c-22.7,9.2-38,28.8-38,57.6
+				c0,36.2,23.3,54.6,52.7,54.6c9.8,0,17.8-1.2,25.1-3.1c11.7-3.7,21.5-10.4,33.1-22.7c6.7,9.2,8.6,13.5,20.2,23.3
+				c3.1,1.2,6.1,1.2,8.6-0.6c7.4-6.1,20.3-17.2,27-23.3c3.1-2.5,2.5-6.1,0.6-9.2c-6.7-8.6-13.5-16-13.5-32.5V165
+				c0-23.3,1.9-44.8-15.3-60.7c-14.1-12.9-36.2-17.8-53.4-17.8h-7.4c-31.2,1.8-64.3,15.3-71.7,54c-1.2,4.9,2.5,6.8,4.9,7.4l34.3,4.3
+				c3.7-0.6,5.5-3.7,6.1-6.7c3.1-13.5,14.1-20.2,26.3-21.5h2.5c7.4,0,15.3,3.1,19.6,9.2c4.9,7.4,4.3,17.2,4.3,25.8L315,163.7
+				L315,163.7z M308.2,236.7c-4.3,8.6-11.7,14.1-19.6,16c-1.2,0-3.1,0.6-4.9,0.6c-13.5,0-21.4-10.4-21.4-25.8
+				c0-19.6,11.6-28.8,26.3-33.1c8-1.8,17.2-2.5,26.4-2.5v7.4C315,213.4,315.6,224.4,308.2,236.7z"/>
+			<path class="st2" d="M398.8,311.4c-1.4,0-2.8,0.3-4.1,0.9c-1.5,0.6-3,1.3-4.4,1.9l-2.1,0.9l-2.7,1.1v0
+				c-29.8,12.1-61.1,19.2-90.1,19.8c-1.1,0-2.1,0-3.2,0c-45.6,0-82.8-21.1-120.3-42c-1.3-0.7-2.7-1-4-1c-1.7,0-3.4,0.6-4.7,1.8
+				c-1.3,1.2-2,2.9-2,4.7c0,2.3,1.2,4.4,2.9,5.7c35.2,30.6,73.8,59,125.7,59c1,0,2,0,3.1,0c33-0.7,70.3-11.9,99.3-30.1l0.2-0.1
+				c3.8-2.3,7.6-4.9,11.2-7.7c2.2-1.6,3.8-4.2,3.8-6.9C407.2,314.6,403.2,311.4,398.8,311.4z M439,294.5L439,294.5
+				c-0.1-2.9-0.7-5.1-1.9-6.9l-0.1-0.2l-0.1-0.2c-1.2-1.3-2.4-1.8-3.7-2.4c-3.8-1.5-9.3-2.3-16-2.3c-4.8,0-10.1,0.5-15.4,1.6l0-0.4
+				l-5.3,1.8l-0.1,0l-3,1v0.1c-3.5,1.5-6.8,3.3-9.8,5.5c-1.9,1.4-3.4,3.2-3.5,6.1c0,1.5,0.7,3.3,2,4.3c1.3,1,2.8,1.4,4.1,1.4
+				c0.3,0,0.6,0,0.9-0.1l0.3,0l0.2,0c2.6-0.6,6.4-0.9,10.9-1.6c3.8-0.4,7.9-0.7,11.4-0.7c2.5,0,4.7,0.2,6.3,0.5
+				c0.8,0.2,1.3,0.4,1.6,0.5c0.1,0,0.2,0.1,0.2,0.1c0.1,0.2,0.2,0.8,0.1,1.5c0,2.9-1.2,8.4-2.9,13.7c-1.7,5.3-3.7,10.7-5,14.2
+				c-0.3,0.8-0.5,1.7-0.5,2.7c0,1.4,0.6,3.2,1.8,4.3c1.2,1.1,2.8,1.6,4.1,1.6h0.1c2,0,3.6-0.8,5.1-1.9
+				c13.6-12.2,18.3-31.7,18.5-42.6L439,294.5z"/>
+		</g>
+	</g>
+</g>
+</svg>

litellm/proxy/_experimental/out/assets/logos/cerebras.svg

@@ -1,89 +1,89 @@
-<?xml version="1.0" encoding="utf-8"?>
-<!-- Generator: Adobe Illustrator 26.0.3, SVG Export Plug-In . SVG Version: 6.00 Build 0)  -->
-<svg version="1.0" id="katman_1" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" x="0px" y="0px"
-	 viewBox="0 0 800 600" style="enable-background:new 0 0 800 600;" xml:space="preserve">
-<style type="text/css">
-	.st0{fill-rule:evenodd;clip-rule:evenodd;fill:#F05A28;}
-	.st1{fill-rule:evenodd;clip-rule:evenodd;fill:#231F20;}
-</style>
-<g id="Contact">
-	<g id="Contact-us" transform="translate(-234.000000, -1114.000000)">
-		<g id="map" transform="translate(-6.000000, 1027.000000)">
-			<g id="Contact-box" transform="translate(190.000000, 36.000000)">
-				<g id="Group-26" transform="translate(50.000000, 51.000000)">
-					<g id="Group-3">
-						<path id="Fill-1" class="st0" d="M220.9,421c-17,0-33.1-3.4-47.8-9.5c-22-9.2-40.8-24.6-54.1-44c-13.3-19.4-21-42.7-21-67.9
-							c0-16.8,3.4-32.7,9.7-47.3c9.3-21.8,24.9-40.3,44.5-53.4c19.6-13.1,43.2-20.7,68.7-20.7v-18.3c-19.5,0-38.1,3.9-55.1,11
-							c-25.4,10.6-47,28.3-62.2,50.6c-15.3,22.3-24.2,49.2-24.2,78.1c0,19.3,4,37.7,11.1,54.4c10.7,25.1,28.7,46.4,51.2,61.5
-							c22.6,15.1,49.8,23.9,79.1,23.9V421z"/>
-						<path id="Fill-4" class="st0" d="M157.9,374.1c-11.5-9.6-20.1-21.2-25.9-33.9c-5.8-12.7-8.8-26.4-8.8-40.2
-							c0-11,1.9-22,5.6-32.5c3.8-10.5,9.4-20.5,17.1-29.6c9.6-11.4,21.3-20,34-25.8c12.7-5.8,26.6-8.7,40.4-8.7
-							c11,0,22.1,1.9,32.6,5.6c10.6,3.8,20.6,9.4,29.7,17l11.9-14.1c-10.8-9-22.8-15.8-35.4-20.2c-12.6-4.5-25.7-6.7-38.8-6.7
-							c-16.5,0-32.9,3.5-48.1,10.4c-15.2,6.9-29.1,17.2-40.5,30.7c-9.1,10.8-15.8,22.7-20.3,35.2c-4.5,12.5-6.7,25.6-6.7,38.7
-							c0,16.4,3.5,32.8,10.4,47.9c6.9,15.1,17.3,29,30.9,40.3L157.9,374.1z"/>
-						<path id="Fill-6" class="st0" d="M186.4,362.2c-12.1-6.4-21.6-15.7-28.1-26.6c-6.5-10.9-9.9-23.5-9.9-36.2
-							c0-11.2,2.6-22.5,8.3-33c6.4-12.1,15.8-21.5,26.8-27.9c11-6.5,23.6-9.9,36.4-9.9c11.2,0,22.6,2.6,33.2,8.2l8.6-16.3
-							c-13.3-7-27.7-10.4-41.9-10.3c-16.1,0-32,4.3-45.8,12.4c-13.8,8.1-25.7,20.1-33.7,35.2c-7,13.3-10.4,27.6-10.4,41.6
-							c0,16,4.3,31.8,12.5,45.5c8.2,13.8,20.2,25.5,35.4,33.5L186.4,362.2z"/>
-						<path id="Fill-8" class="st0" d="M221,344.6c-6.3,0-12.3-1.3-17.7-3.6c-8.2-3.4-15.1-9.2-20-16.5c-4.9-7.3-7.8-16-7.8-25.4
-							c0-6.3,1.3-12.3,3.6-17.7c3.4-8.1,9.2-15.1,16.5-20c7.3-4.9,16-7.8,25.4-7.8v-18.4c-8.8,0-17.2,1.8-24.9,5
-							c-11.5,4.9-21.2,12.9-28.1,23.1C161,273.6,157,286,157,299.2c0,8.8,1.8,17.2,5,24.9c4.9,11.5,13,21.2,23.2,28.1
-							C195.4,359,207.7,363,221,363V344.6z"/>
-					</g>
-					<g id="Group" transform="translate(22.000000, 13.000000)">
-						<path id="Fill-10" class="st1" d="M214,271.6c-2.1-2.2-4.4-4-6.7-5.3c-2.3-1.3-4.7-2-7.2-2c-3.4,0-6.3,0.6-9,1.8
-							c-2.6,1.2-4.9,2.8-6.8,4.9c-1.9,2-3.3,4.4-4.3,7c-1,2.6-1.4,5.4-1.4,8.2c0,2.8,0.5,5.6,1.4,8.2c1,2.6,2.4,5,4.3,7
-							c1.9,2,4.1,3.7,6.8,4.9c2.6,1.2,5.6,1.8,9,1.8c2.8,0,5.5-0.6,7.9-1.7c2.4-1.2,4.5-2.9,6.2-5.1l12.2,13.1
-							c-1.8,1.8-3.9,3.4-6.3,4.7c-2.4,1.3-4.8,2.4-7.2,3.2s-4.8,1.4-7,1.7c-2.2,0.4-4.2,0.5-5.8,0.5c-5.5,0-10.7-0.9-15.5-2.7
-							c-4.9-1.8-9.1-4.4-12.6-7.8c-3.6-3.3-6.4-7.4-8.5-12.1c-2.1-4.7-3.1-10-3.1-15.7c0-5.8,1-11,3.1-15.7
-							c2.1-4.7,4.9-8.7,8.5-12.1c3.6-3.3,7.8-5.9,12.6-7.8c4.9-1.8,10.1-2.7,15.5-2.7c4.7,0,9.4,0.9,14.1,2.7
-							c4.7,1.8,8.9,4.6,12.4,8.4L214,271.6z"/>
-						<path id="Fill-12" class="st1" d="M280.4,278.9c-0.1-5.4-1.8-9.6-5-12.7c-3.3-3.1-7.8-4.6-13.6-4.6c-5.5,0-9.8,1.6-13,4.7
-							c-3.2,3.1-5.2,7.4-5.9,12.6H280.4z M243,292.6c0.6,5.5,2.7,9.7,6.4,12.8c3.7,3,8.1,4.6,13.3,4.6c4.6,0,8.4-0.9,11.5-2.8
-							c3.1-1.9,5.8-4.2,8.2-7.1l13.1,9.9c-4.3,5.3-9,9-14.3,11.3c-5.3,2.2-10.8,3.3-16.6,3.3c-5.5,0-10.7-0.9-15.5-2.7
-							c-4.9-1.8-9.1-4.4-12.6-7.8c-3.6-3.3-6.4-7.4-8.5-12.1c-2.1-4.7-3.1-10-3.1-15.7c0-5.8,1-11,3.1-15.7
-							c2.1-4.7,4.9-8.7,8.5-12.1c3.6-3.3,7.8-5.9,12.6-7.8c4.9-1.8,10.1-2.7,15.5-2.7c5.1,0,9.7,0.9,13.9,2.7
-							c4.2,1.8,7.8,4.3,10.8,7.7c3,3.3,5.3,7.5,7,12.4c1.7,4.9,2.5,10.6,2.5,17v5H243z"/>
-						<path id="Fill-14" class="st1" d="M306.5,249.7h18.3v11.5h0.3c2-4.3,4.9-7.5,8.7-9.9c3.8-2.3,8.1-3.5,12.9-3.5
-							c1.1,0,2.2,0.1,3.3,0.3c1.1,0.2,2.2,0.5,3.3,0.8v17.6c-1.5-0.4-3-0.7-4.5-1c-1.5-0.3-2.9-0.4-4.3-0.4c-4.3,0-7.7,0.8-10.3,2.4
-							c-2.6,1.6-4.6,3.4-5.9,5.4c-1.4,2-2.3,4.1-2.7,6.1c-0.5,2-0.7,3.5-0.7,4.6v39h-18.3V249.7z"/>
-						<path id="Fill-16" class="st1" d="M409,278.9c-0.1-5.4-1.8-9.6-5-12.7c-3.3-3.1-7.8-4.6-13.6-4.6c-5.5,0-9.8,1.6-13,4.7
-							c-3.2,3.1-5.2,7.4-5.9,12.6H409z M371.6,292.6c0.6,5.5,2.7,9.7,6.4,12.8c3.7,3,8.1,4.6,13.3,4.6c4.6,0,8.4-0.9,11.5-2.8
-							c3.1-1.9,5.8-4.2,8.2-7.1l13.1,9.9c-4.3,5.3-9,9-14.3,11.3c-5.3,2.2-10.8,3.3-16.6,3.3c-5.5,0-10.7-0.9-15.5-2.7
-							c-4.9-1.8-9.1-4.4-12.6-7.8c-3.6-3.3-6.4-7.4-8.5-12.1c-2.1-4.7-3.1-10-3.1-15.7c0-5.8,1-11,3.1-15.7
-							c2.1-4.7,4.9-8.7,8.5-12.1c3.6-3.3,7.8-5.9,12.6-7.8c4.9-1.8,10.1-2.7,15.5-2.7c5.1,0,9.7,0.9,13.9,2.7
-							c4.2,1.8,7.8,4.3,10.8,7.7c3,3.3,5.3,7.5,7,12.4c1.7,4.9,2.5,10.6,2.5,17v5H371.6z"/>
-						<path id="Fill-18" class="st1" d="M494.6,286.2c0-2.8-0.5-5.6-1.5-8.2c-1-2.6-2.4-5-4.3-7c-1.9-2-4.2-3.7-6.9-4.9
-							c-2.7-1.2-5.7-1.8-9.1-1.8c-3.4,0-6.4,0.6-9.1,1.8c-2.7,1.2-5,2.8-6.9,4.9c-1.9,2-3.3,4.4-4.3,7c-1,2.6-1.5,5.4-1.5,8.2
-							c0,2.8,0.5,5.6,1.5,8.2c1,2.6,2.4,5,4.3,7c1.9,2,4.2,3.7,6.9,4.9c2.7,1.2,5.7,1.8,9.1,1.8c3.4,0,6.4-0.6,9.1-1.8
-							c2.7-1.2,5-2.8,6.9-4.9c1.9-2,3.3-4.4,4.3-7C494.1,291.8,494.6,289,494.6,286.2L494.6,286.2z M433.2,207.6h18.5v51.3h0.5
-							c0.9-1.2,2.1-2.5,3.5-3.7c1.4-1.3,3.2-2.5,5.2-3.6c2.1-1.1,4.4-2,7.1-2.7c2.7-0.7,5.8-1.1,9.3-1.1c5.2,0,10.1,1,14.5,3
-							c4.4,2,8.2,4.7,11.3,8.1c3.1,3.5,5.6,7.5,7.3,12.2c1.7,4.7,2.6,9.7,2.6,15.1c0,5.4-0.8,10.4-2.5,15.1
-							c-1.6,4.7-4.1,8.7-7.2,12.2c-3.2,3.5-7,6.2-11.6,8.1c-4.5,2-9.6,3-15.3,3c-5.2,0-10.1-1-14.7-3c-4.5-2-8.1-5.3-10.8-9.7h-0.3
-							v11h-17.6V207.6z"/>
-						<path id="Fill-20" class="st1" d="M520.9,249.7h18.3v11.5h0.3c2-4.3,4.9-7.5,8.7-9.9c3.8-2.3,8.1-3.5,12.9-3.5
-							c1.1,0,2.2,0.1,3.3,0.3c1.1,0.2,2.2,0.5,3.3,0.8v17.6c-1.5-0.4-3-0.7-4.5-1c-1.5-0.3-2.9-0.4-4.3-0.4c-4.3,0-7.7,0.8-10.3,2.4
-							c-2.6,1.6-4.6,3.4-5.9,5.4c-1.4,2-2.3,4.1-2.7,6.1c-0.5,2-0.7,3.5-0.7,4.6v39h-18.3V249.7z"/>
-						<path id="Fill-22" class="st1" d="M616,290h-3.9c-2.6,0-5.5,0.1-8.7,0.3c-3.2,0.2-6.2,0.7-9.1,1.4c-2.8,0.8-5.2,1.9-7.2,3.3
-							c-2,1.5-2.9,3.5-2.9,6.2c0,1.7,0.4,3.2,1.2,4.3c0.8,1.2,1.8,2.2,3,3c1.2,0.8,2.6,1.4,4.2,1.8c1.5,0.4,3.1,0.5,4.6,0.5
-							c6.4,0,11.1-1.5,14.2-4.5c3-3,4.6-7.1,4.6-12.2V290z M617.1,312.7h-0.5c-2.7,4.2-6.1,7.2-10.2,9.1c-4.1,1.9-8.7,2.8-13.6,2.8
-							c-3.4,0-6.7-0.5-10-1.4s-6.1-2.3-8.7-4.1c-2.5-1.8-4.6-4.1-6.1-6.8s-2.3-5.9-2.3-9.6c0-4,0.7-7.3,2.2-10.1
-							c1.4-2.8,3.4-5.1,5.8-7c2.4-1.9,5.2-3.4,8.4-4.5c3.2-1.1,6.5-2,10-2.5c3.5-0.6,6.9-0.9,10.5-1.1c3.5-0.2,6.8-0.2,9.9-0.2h4.6
-							v-2c0-4.6-1.6-8-4.8-10.3c-3.2-2.3-7.3-3.4-12.2-3.4c-3.9,0-7.6,0.7-11,2.1c-3.4,1.4-6.4,3.2-8.8,5.6l-9.8-9.6
-							c4.1-4.2,9-7.1,14.5-9c5.5-1.8,11.2-2.7,17.1-2.7c5.3,0,9.7,0.6,13.3,1.7c3.6,1.2,6.6,2.7,9,4.5c2.4,1.8,4.2,3.9,5.5,6.3
-							c1.3,2.4,2.2,4.8,2.8,7.2c0.6,2.4,0.9,4.8,1,7.1c0.1,2.3,0.2,4.3,0.2,6v42h-16.7V312.7z"/>
-						<path id="Fill-24" class="st1" d="M683.6,269.9c-3.6-5-8.4-7.5-14.4-7.5c-2.5,0-4.9,0.6-7.2,1.8c-2.4,1.2-3.5,3.2-3.5,5.9
-							c0,2.2,1,3.9,2.9,4.9c1.9,1,4.4,1.9,7.4,2.6c3,0.7,6.2,1.4,9.6,2.2c3.4,0.8,6.6,1.9,9.6,3.5c3,1.6,5.4,3.7,7.4,6.5
-							c1.9,2.7,2.9,6.5,2.9,11.3c0,4.4-0.9,8-2.8,11c-1.9,3-4.3,5.4-7.4,7.2c-3,1.8-6.4,3.1-10.2,4c-3.8,0.8-7.6,1.2-11.3,1.2
-							c-5.7,0-11-0.8-15.8-2.4c-4.8-1.6-9.1-4.6-12.9-8.8l12.3-11.4c2.4,2.6,4.9,4.8,7.6,6.5c2.7,1.7,6,2.5,9.9,2.5
-							c1.3,0,2.7-0.2,4.1-0.5c1.4-0.3,2.8-0.8,4-1.5c1.2-0.7,2.2-1.6,3-2.7c0.8-1.1,1.1-2.3,1.1-3.7c0-2.5-1-4.4-2.9-5.6
-							c-1.9-1.2-4.4-2.2-7.4-3c-3-0.8-6.2-1.5-9.6-2.1c-3.4-0.7-6.6-1.7-9.6-3.2c-3-1.5-5.4-3.5-7.4-6.2c-1.9-2.6-2.9-6.3-2.9-11
-							c0-4.1,0.8-7.6,2.5-10.6c1.7-3,3.9-5.4,6.7-7.4c2.8-1.9,5.9-3.3,9.5-4.3c3.6-0.9,7.2-1.4,10.9-1.4c4.9,0,9.8,0.8,14.6,2.5
-							c4.8,1.7,8.7,4.5,11.7,8.6L683.6,269.9z"/>
-					</g>
-				</g>
-			</g>
-		</g>
-	</g>
-</g>
-</svg>
+<?xml version="1.0" encoding="utf-8"?>
+<!-- Generator: Adobe Illustrator 26.0.3, SVG Export Plug-In . SVG Version: 6.00 Build 0)  -->
+<svg version="1.0" id="katman_1" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" x="0px" y="0px"
+	 viewBox="0 0 800 600" style="enable-background:new 0 0 800 600;" xml:space="preserve">
+<style type="text/css">
+	.st0{fill-rule:evenodd;clip-rule:evenodd;fill:#F05A28;}
+	.st1{fill-rule:evenodd;clip-rule:evenodd;fill:#231F20;}
+</style>
+<g id="Contact">
+	<g id="Contact-us" transform="translate(-234.000000, -1114.000000)">
+		<g id="map" transform="translate(-6.000000, 1027.000000)">
+			<g id="Contact-box" transform="translate(190.000000, 36.000000)">
+				<g id="Group-26" transform="translate(50.000000, 51.000000)">
+					<g id="Group-3">
+						<path id="Fill-1" class="st0" d="M220.9,421c-17,0-33.1-3.4-47.8-9.5c-22-9.2-40.8-24.6-54.1-44c-13.3-19.4-21-42.7-21-67.9
+							c0-16.8,3.4-32.7,9.7-47.3c9.3-21.8,24.9-40.3,44.5-53.4c19.6-13.1,43.2-20.7,68.7-20.7v-18.3c-19.5,0-38.1,3.9-55.1,11
+							c-25.4,10.6-47,28.3-62.2,50.6c-15.3,22.3-24.2,49.2-24.2,78.1c0,19.3,4,37.7,11.1,54.4c10.7,25.1,28.7,46.4,51.2,61.5
+							c22.6,15.1,49.8,23.9,79.1,23.9V421z"/>
+						<path id="Fill-4" class="st0" d="M157.9,374.1c-11.5-9.6-20.1-21.2-25.9-33.9c-5.8-12.7-8.8-26.4-8.8-40.2
+							c0-11,1.9-22,5.6-32.5c3.8-10.5,9.4-20.5,17.1-29.6c9.6-11.4,21.3-20,34-25.8c12.7-5.8,26.6-8.7,40.4-8.7
+							c11,0,22.1,1.9,32.6,5.6c10.6,3.8,20.6,9.4,29.7,17l11.9-14.1c-10.8-9-22.8-15.8-35.4-20.2c-12.6-4.5-25.7-6.7-38.8-6.7
+							c-16.5,0-32.9,3.5-48.1,10.4c-15.2,6.9-29.1,17.2-40.5,30.7c-9.1,10.8-15.8,22.7-20.3,35.2c-4.5,12.5-6.7,25.6-6.7,38.7
+							c0,16.4,3.5,32.8,10.4,47.9c6.9,15.1,17.3,29,30.9,40.3L157.9,374.1z"/>
+						<path id="Fill-6" class="st0" d="M186.4,362.2c-12.1-6.4-21.6-15.7-28.1-26.6c-6.5-10.9-9.9-23.5-9.9-36.2
+							c0-11.2,2.6-22.5,8.3-33c6.4-12.1,15.8-21.5,26.8-27.9c11-6.5,23.6-9.9,36.4-9.9c11.2,0,22.6,2.6,33.2,8.2l8.6-16.3
+							c-13.3-7-27.7-10.4-41.9-10.3c-16.1,0-32,4.3-45.8,12.4c-13.8,8.1-25.7,20.1-33.7,35.2c-7,13.3-10.4,27.6-10.4,41.6
+							c0,16,4.3,31.8,12.5,45.5c8.2,13.8,20.2,25.5,35.4,33.5L186.4,362.2z"/>
+						<path id="Fill-8" class="st0" d="M221,344.6c-6.3,0-12.3-1.3-17.7-3.6c-8.2-3.4-15.1-9.2-20-16.5c-4.9-7.3-7.8-16-7.8-25.4
+							c0-6.3,1.3-12.3,3.6-17.7c3.4-8.1,9.2-15.1,16.5-20c7.3-4.9,16-7.8,25.4-7.8v-18.4c-8.8,0-17.2,1.8-24.9,5
+							c-11.5,4.9-21.2,12.9-28.1,23.1C161,273.6,157,286,157,299.2c0,8.8,1.8,17.2,5,24.9c4.9,11.5,13,21.2,23.2,28.1
+							C195.4,359,207.7,363,221,363V344.6z"/>
+					</g>
+					<g id="Group" transform="translate(22.000000, 13.000000)">
+						<path id="Fill-10" class="st1" d="M214,271.6c-2.1-2.2-4.4-4-6.7-5.3c-2.3-1.3-4.7-2-7.2-2c-3.4,0-6.3,0.6-9,1.8
+							c-2.6,1.2-4.9,2.8-6.8,4.9c-1.9,2-3.3,4.4-4.3,7c-1,2.6-1.4,5.4-1.4,8.2c0,2.8,0.5,5.6,1.4,8.2c1,2.6,2.4,5,4.3,7
+							c1.9,2,4.1,3.7,6.8,4.9c2.6,1.2,5.6,1.8,9,1.8c2.8,0,5.5-0.6,7.9-1.7c2.4-1.2,4.5-2.9,6.2-5.1l12.2,13.1
+							c-1.8,1.8-3.9,3.4-6.3,4.7c-2.4,1.3-4.8,2.4-7.2,3.2s-4.8,1.4-7,1.7c-2.2,0.4-4.2,0.5-5.8,0.5c-5.5,0-10.7-0.9-15.5-2.7
+							c-4.9-1.8-9.1-4.4-12.6-7.8c-3.6-3.3-6.4-7.4-8.5-12.1c-2.1-4.7-3.1-10-3.1-15.7c0-5.8,1-11,3.1-15.7
+							c2.1-4.7,4.9-8.7,8.5-12.1c3.6-3.3,7.8-5.9,12.6-7.8c4.9-1.8,10.1-2.7,15.5-2.7c4.7,0,9.4,0.9,14.1,2.7
+							c4.7,1.8,8.9,4.6,12.4,8.4L214,271.6z"/>
+						<path id="Fill-12" class="st1" d="M280.4,278.9c-0.1-5.4-1.8-9.6-5-12.7c-3.3-3.1-7.8-4.6-13.6-4.6c-5.5,0-9.8,1.6-13,4.7
+							c-3.2,3.1-5.2,7.4-5.9,12.6H280.4z M243,292.6c0.6,5.5,2.7,9.7,6.4,12.8c3.7,3,8.1,4.6,13.3,4.6c4.6,0,8.4-0.9,11.5-2.8
+							c3.1-1.9,5.8-4.2,8.2-7.1l13.1,9.9c-4.3,5.3-9,9-14.3,11.3c-5.3,2.2-10.8,3.3-16.6,3.3c-5.5,0-10.7-0.9-15.5-2.7
+							c-4.9-1.8-9.1-4.4-12.6-7.8c-3.6-3.3-6.4-7.4-8.5-12.1c-2.1-4.7-3.1-10-3.1-15.7c0-5.8,1-11,3.1-15.7
+							c2.1-4.7,4.9-8.7,8.5-12.1c3.6-3.3,7.8-5.9,12.6-7.8c4.9-1.8,10.1-2.7,15.5-2.7c5.1,0,9.7,0.9,13.9,2.7
+							c4.2,1.8,7.8,4.3,10.8,7.7c3,3.3,5.3,7.5,7,12.4c1.7,4.9,2.5,10.6,2.5,17v5H243z"/>
+						<path id="Fill-14" class="st1" d="M306.5,249.7h18.3v11.5h0.3c2-4.3,4.9-7.5,8.7-9.9c3.8-2.3,8.1-3.5,12.9-3.5
+							c1.1,0,2.2,0.1,3.3,0.3c1.1,0.2,2.2,0.5,3.3,0.8v17.6c-1.5-0.4-3-0.7-4.5-1c-1.5-0.3-2.9-0.4-4.3-0.4c-4.3,0-7.7,0.8-10.3,2.4
+							c-2.6,1.6-4.6,3.4-5.9,5.4c-1.4,2-2.3,4.1-2.7,6.1c-0.5,2-0.7,3.5-0.7,4.6v39h-18.3V249.7z"/>
+						<path id="Fill-16" class="st1" d="M409,278.9c-0.1-5.4-1.8-9.6-5-12.7c-3.3-3.1-7.8-4.6-13.6-4.6c-5.5,0-9.8,1.6-13,4.7
+							c-3.2,3.1-5.2,7.4-5.9,12.6H409z M371.6,292.6c0.6,5.5,2.7,9.7,6.4,12.8c3.7,3,8.1,4.6,13.3,4.6c4.6,0,8.4-0.9,11.5-2.8
+							c3.1-1.9,5.8-4.2,8.2-7.1l13.1,9.9c-4.3,5.3-9,9-14.3,11.3c-5.3,2.2-10.8,3.3-16.6,3.3c-5.5,0-10.7-0.9-15.5-2.7
+							c-4.9-1.8-9.1-4.4-12.6-7.8c-3.6-3.3-6.4-7.4-8.5-12.1c-2.1-4.7-3.1-10-3.1-15.7c0-5.8,1-11,3.1-15.7
+							c2.1-4.7,4.9-8.7,8.5-12.1c3.6-3.3,7.8-5.9,12.6-7.8c4.9-1.8,10.1-2.7,15.5-2.7c5.1,0,9.7,0.9,13.9,2.7
+							c4.2,1.8,7.8,4.3,10.8,7.7c3,3.3,5.3,7.5,7,12.4c1.7,4.9,2.5,10.6,2.5,17v5H371.6z"/>
+						<path id="Fill-18" class="st1" d="M494.6,286.2c0-2.8-0.5-5.6-1.5-8.2c-1-2.6-2.4-5-4.3-7c-1.9-2-4.2-3.7-6.9-4.9
+							c-2.7-1.2-5.7-1.8-9.1-1.8c-3.4,0-6.4,0.6-9.1,1.8c-2.7,1.2-5,2.8-6.9,4.9c-1.9,2-3.3,4.4-4.3,7c-1,2.6-1.5,5.4-1.5,8.2
+							c0,2.8,0.5,5.6,1.5,8.2c1,2.6,2.4,5,4.3,7c1.9,2,4.2,3.7,6.9,4.9c2.7,1.2,5.7,1.8,9.1,1.8c3.4,0,6.4-0.6,9.1-1.8
+							c2.7-1.2,5-2.8,6.9-4.9c1.9-2,3.3-4.4,4.3-7C494.1,291.8,494.6,289,494.6,286.2L494.6,286.2z M433.2,207.6h18.5v51.3h0.5
+							c0.9-1.2,2.1-2.5,3.5-3.7c1.4-1.3,3.2-2.5,5.2-3.6c2.1-1.1,4.4-2,7.1-2.7c2.7-0.7,5.8-1.1,9.3-1.1c5.2,0,10.1,1,14.5,3
+							c4.4,2,8.2,4.7,11.3,8.1c3.1,3.5,5.6,7.5,7.3,12.2c1.7,4.7,2.6,9.7,2.6,15.1c0,5.4-0.8,10.4-2.5,15.1
+							c-1.6,4.7-4.1,8.7-7.2,12.2c-3.2,3.5-7,6.2-11.6,8.1c-4.5,2-9.6,3-15.3,3c-5.2,0-10.1-1-14.7-3c-4.5-2-8.1-5.3-10.8-9.7h-0.3
+							v11h-17.6V207.6z"/>
+						<path id="Fill-20" class="st1" d="M520.9,249.7h18.3v11.5h0.3c2-4.3,4.9-7.5,8.7-9.9c3.8-2.3,8.1-3.5,12.9-3.5
+							c1.1,0,2.2,0.1,3.3,0.3c1.1,0.2,2.2,0.5,3.3,0.8v17.6c-1.5-0.4-3-0.7-4.5-1c-1.5-0.3-2.9-0.4-4.3-0.4c-4.3,0-7.7,0.8-10.3,2.4
+							c-2.6,1.6-4.6,3.4-5.9,5.4c-1.4,2-2.3,4.1-2.7,6.1c-0.5,2-0.7,3.5-0.7,4.6v39h-18.3V249.7z"/>
+						<path id="Fill-22" class="st1" d="M616,290h-3.9c-2.6,0-5.5,0.1-8.7,0.3c-3.2,0.2-6.2,0.7-9.1,1.4c-2.8,0.8-5.2,1.9-7.2,3.3
+							c-2,1.5-2.9,3.5-2.9,6.2c0,1.7,0.4,3.2,1.2,4.3c0.8,1.2,1.8,2.2,3,3c1.2,0.8,2.6,1.4,4.2,1.8c1.5,0.4,3.1,0.5,4.6,0.5
+							c6.4,0,11.1-1.5,14.2-4.5c3-3,4.6-7.1,4.6-12.2V290z M617.1,312.7h-0.5c-2.7,4.2-6.1,7.2-10.2,9.1c-4.1,1.9-8.7,2.8-13.6,2.8
+							c-3.4,0-6.7-0.5-10-1.4s-6.1-2.3-8.7-4.1c-2.5-1.8-4.6-4.1-6.1-6.8s-2.3-5.9-2.3-9.6c0-4,0.7-7.3,2.2-10.1
+							c1.4-2.8,3.4-5.1,5.8-7c2.4-1.9,5.2-3.4,8.4-4.5c3.2-1.1,6.5-2,10-2.5c3.5-0.6,6.9-0.9,10.5-1.1c3.5-0.2,6.8-0.2,9.9-0.2h4.6
+							v-2c0-4.6-1.6-8-4.8-10.3c-3.2-2.3-7.3-3.4-12.2-3.4c-3.9,0-7.6,0.7-11,2.1c-3.4,1.4-6.4,3.2-8.8,5.6l-9.8-9.6
+							c4.1-4.2,9-7.1,14.5-9c5.5-1.8,11.2-2.7,17.1-2.7c5.3,0,9.7,0.6,13.3,1.7c3.6,1.2,6.6,2.7,9,4.5c2.4,1.8,4.2,3.9,5.5,6.3
+							c1.3,2.4,2.2,4.8,2.8,7.2c0.6,2.4,0.9,4.8,1,7.1c0.1,2.3,0.2,4.3,0.2,6v42h-16.7V312.7z"/>
+						<path id="Fill-24" class="st1" d="M683.6,269.9c-3.6-5-8.4-7.5-14.4-7.5c-2.5,0-4.9,0.6-7.2,1.8c-2.4,1.2-3.5,3.2-3.5,5.9
+							c0,2.2,1,3.9,2.9,4.9c1.9,1,4.4,1.9,7.4,2.6c3,0.7,6.2,1.4,9.6,2.2c3.4,0.8,6.6,1.9,9.6,3.5c3,1.6,5.4,3.7,7.4,6.5
+							c1.9,2.7,2.9,6.5,2.9,11.3c0,4.4-0.9,8-2.8,11c-1.9,3-4.3,5.4-7.4,7.2c-3,1.8-6.4,3.1-10.2,4c-3.8,0.8-7.6,1.2-11.3,1.2
+							c-5.7,0-11-0.8-15.8-2.4c-4.8-1.6-9.1-4.6-12.9-8.8l12.3-11.4c2.4,2.6,4.9,4.8,7.6,6.5c2.7,1.7,6,2.5,9.9,2.5
+							c1.3,0,2.7-0.2,4.1-0.5c1.4-0.3,2.8-0.8,4-1.5c1.2-0.7,2.2-1.6,3-2.7c0.8-1.1,1.1-2.3,1.1-3.7c0-2.5-1-4.4-2.9-5.6
+							c-1.9-1.2-4.4-2.2-7.4-3c-3-0.8-6.2-1.5-9.6-2.1c-3.4-0.7-6.6-1.7-9.6-3.2c-3-1.5-5.4-3.5-7.4-6.2c-1.9-2.6-2.9-6.3-2.9-11
+							c0-4.1,0.8-7.6,2.5-10.6c1.7-3,3.9-5.4,6.7-7.4c2.8-1.9,5.9-3.3,9.5-4.3c3.6-0.9,7.2-1.4,10.9-1.4c4.9,0,9.8,0.8,14.6,2.5
+							c4.8,1.7,8.7,4.5,11.7,8.6L683.6,269.9z"/>
+					</g>
+				</g>
+			</g>
+		</g>
+	</g>
+</g>
+</svg>

litellm/proxy/_experimental/out/assets/logos/deepseek.svg

@@ -1,25 +1,25 @@
-<?xml version="1.0" encoding="utf-8"?>
-<!-- Generator: Adobe Illustrator 25.4.1, SVG Export Plug-In . SVG Version: 6.00 Build 0)  -->
-<svg version="1.1" id="Layer_1" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" x="0px" y="0px"
-	 viewBox="0 0 292.6 215.3" style="enable-background:new 0 0 292.6 215.3;" xml:space="preserve">
-<style type="text/css">
-	.st0{fill:#566AB2;}
-</style>
-<path class="st0" d="M191.3,123.7c-2.4,1-4.9,1.8-7.2,1.9c-3.6,0.2-7.6-1.3-9.7-3.1c-3.3-2.8-5.7-4.4-6.7-9.2
-	c-0.4-2.1-0.2-5.3,0.2-7.2c0.9-4-0.1-6.5-2.9-8.9c-2.3-1.9-5.2-2.4-8.4-2.4s-2.3-0.5-3.1-1c-1.3-0.7-2.4-2.3-1.4-4.4
-	c0.3-0.7,2-2.3,2.3-2.5c4.3-2.5,9.4-1.7,14,0.2c4.3,1.7,7.5,5,12.2,9.5c4.8,5.5,5.6,7,8.4,11.1c2.1,3.2,4.1,6.6,5.4,10.4
-	C195.2,120.5,194.2,122.4,191.3,123.7L191.3,123.7z M153.4,104.3c0-2.1,1.7-3.7,3.8-3.7s0.9,0.1,1.3,0.2c0.5,0.2,1,0.5,1.4,0.9
-	c0.7,0.7,1.1,1.6,1.1,2.6c0,2.1-1.7,3.8-3.8,3.8s-3.7-1.7-3.7-3.8H153.4z M141.2,182.8c-25.5-20-37.8-26.6-42.9-26.3
-	c-4.8,0.3-3.9,5.7-2.8,9.3c1.1,3.5,2.5,5.9,4.5,9c1.4,2,2.3,5.1-1.4,7.3c-8.2,5.1-22.5-1.7-23.1-2c-16.6-9.8-30.5-22.7-40.2-40.3
-	c-9.5-17-14.9-35.2-15.8-54.6c-0.2-4.7,1.1-6.4,5.8-7.2c6.2-1.1,12.5-1.4,18.7-0.5c26,3.8,48.1,15.4,66.7,33.8
-	c10.6,10.5,18.6,23,26.8,35.2c8.8,13,18.2,25.4,30.2,35.5c4.3,3.6,7.6,6.3,10.9,8.2c-9.8,1.1-26.1,1.3-37.2-7.5L141.2,182.8z
-	 M289.5,18c-3.1-1.5-4.4,1.4-6.3,2.8c-0.6,0.5-1.1,1.1-1.7,1.7c-4.5,4.8-9.8,8-16.8,7.6c-10.1-0.6-18.7,2.6-26.4,10.4
-	c-1.6-9.5-7-15.2-15.2-18.9c-4.3-1.9-8.6-3.8-11.6-7.9c-2.1-2.9-2.7-6.2-3.7-9.4c-0.7-2-1.3-3.9-3.6-4.3c-2.4-0.4-3.4,1.7-4.3,3.4
-	c-3.8,7-5.3,14.6-5.2,22.4c0.3,17.5,7.7,31.5,22.4,41.4c1.7,1.1,2.1,2.3,1.6,3.9c-1,3.4-2.2,6.7-3.3,10.1c-0.7,2.2-1.7,2.7-4,1.7
-	c-8.1-3.4-15-8.4-21.2-14.4c-10.4-10.1-19.9-21.2-31.6-30c-2.8-2.1-5.5-4-8.4-5.7c-12-11.7,1.6-21.3,4.7-22.4
-	c3.3-1.2,1.2-5.3-9.5-5.2c-10.6,0-20.3,3.6-32.8,8.4c-1.8,0.7-3.7,1.2-5.7,1.7c-11.3-2.1-22.9-2.6-35.1-1.2
-	c-23,2.5-41.4,13.4-54.8,32C1,68.3-2.8,93.6,1.9,120c4.9,27.8,19.1,50.9,41,68.9c22.6,18.7,48.7,27.8,78.5,26.1
-	c18.1-1,38.2-3.5,60.9-22.7c5.7,2.8,11.7,4,21.7,4.8c7.7,0.7,15.1-0.4,20.8-1.5c9-1.9,8.4-10.2,5.1-11.7
-	c-26.3-12.3-20.5-7.3-25.7-11.3c13.3-15.8,33.5-32.2,41.3-85.4c0.6-4.2,0.1-6.9,0-10.3c0-2.1,0.4-2.9,2.8-3.1
-	c6.6-0.8,13-2.6,18.8-5.8c17-9.3,23.9-24.6,25.5-42.9c0.2-2.8,0-5.7-3-7.2L289.5,18z"/>
-</svg>
+<?xml version="1.0" encoding="utf-8"?>
+<!-- Generator: Adobe Illustrator 25.4.1, SVG Export Plug-In . SVG Version: 6.00 Build 0)  -->
+<svg version="1.1" id="Layer_1" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" x="0px" y="0px"
+	 viewBox="0 0 292.6 215.3" style="enable-background:new 0 0 292.6 215.3;" xml:space="preserve">
+<style type="text/css">
+	.st0{fill:#566AB2;}
+</style>
+<path class="st0" d="M191.3,123.7c-2.4,1-4.9,1.8-7.2,1.9c-3.6,0.2-7.6-1.3-9.7-3.1c-3.3-2.8-5.7-4.4-6.7-9.2
+	c-0.4-2.1-0.2-5.3,0.2-7.2c0.9-4-0.1-6.5-2.9-8.9c-2.3-1.9-5.2-2.4-8.4-2.4s-2.3-0.5-3.1-1c-1.3-0.7-2.4-2.3-1.4-4.4
+	c0.3-0.7,2-2.3,2.3-2.5c4.3-2.5,9.4-1.7,14,0.2c4.3,1.7,7.5,5,12.2,9.5c4.8,5.5,5.6,7,8.4,11.1c2.1,3.2,4.1,6.6,5.4,10.4
+	C195.2,120.5,194.2,122.4,191.3,123.7L191.3,123.7z M153.4,104.3c0-2.1,1.7-3.7,3.8-3.7s0.9,0.1,1.3,0.2c0.5,0.2,1,0.5,1.4,0.9
+	c0.7,0.7,1.1,1.6,1.1,2.6c0,2.1-1.7,3.8-3.8,3.8s-3.7-1.7-3.7-3.8H153.4z M141.2,182.8c-25.5-20-37.8-26.6-42.9-26.3
+	c-4.8,0.3-3.9,5.7-2.8,9.3c1.1,3.5,2.5,5.9,4.5,9c1.4,2,2.3,5.1-1.4,7.3c-8.2,5.1-22.5-1.7-23.1-2c-16.6-9.8-30.5-22.7-40.2-40.3
+	c-9.5-17-14.9-35.2-15.8-54.6c-0.2-4.7,1.1-6.4,5.8-7.2c6.2-1.1,12.5-1.4,18.7-0.5c26,3.8,48.1,15.4,66.7,33.8
+	c10.6,10.5,18.6,23,26.8,35.2c8.8,13,18.2,25.4,30.2,35.5c4.3,3.6,7.6,6.3,10.9,8.2c-9.8,1.1-26.1,1.3-37.2-7.5L141.2,182.8z
+	 M289.5,18c-3.1-1.5-4.4,1.4-6.3,2.8c-0.6,0.5-1.1,1.1-1.7,1.7c-4.5,4.8-9.8,8-16.8,7.6c-10.1-0.6-18.7,2.6-26.4,10.4
+	c-1.6-9.5-7-15.2-15.2-18.9c-4.3-1.9-8.6-3.8-11.6-7.9c-2.1-2.9-2.7-6.2-3.7-9.4c-0.7-2-1.3-3.9-3.6-4.3c-2.4-0.4-3.4,1.7-4.3,3.4
+	c-3.8,7-5.3,14.6-5.2,22.4c0.3,17.5,7.7,31.5,22.4,41.4c1.7,1.1,2.1,2.3,1.6,3.9c-1,3.4-2.2,6.7-3.3,10.1c-0.7,2.2-1.7,2.7-4,1.7
+	c-8.1-3.4-15-8.4-21.2-14.4c-10.4-10.1-19.9-21.2-31.6-30c-2.8-2.1-5.5-4-8.4-5.7c-12-11.7,1.6-21.3,4.7-22.4
+	c3.3-1.2,1.2-5.3-9.5-5.2c-10.6,0-20.3,3.6-32.8,8.4c-1.8,0.7-3.7,1.2-5.7,1.7c-11.3-2.1-22.9-2.6-35.1-1.2
+	c-23,2.5-41.4,13.4-54.8,32C1,68.3-2.8,93.6,1.9,120c4.9,27.8,19.1,50.9,41,68.9c22.6,18.7,48.7,27.8,78.5,26.1
+	c18.1-1,38.2-3.5,60.9-22.7c5.7,2.8,11.7,4,21.7,4.8c7.7,0.7,15.1-0.4,20.8-1.5c9-1.9,8.4-10.2,5.1-11.7
+	c-26.3-12.3-20.5-7.3-25.7-11.3c13.3-15.8,33.5-32.2,41.3-85.4c0.6-4.2,0.1-6.9,0-10.3c0-2.1,0.4-2.9,2.8-3.1
+	c6.6-0.8,13-2.6,18.8-5.8c17-9.3,23.9-24.6,25.5-42.9c0.2-2.8,0-5.7-3-7.2L289.5,18z"/>
+</svg>

litellm/proxy/_experimental/out/assets/logos/perplexity-ai.svg

@@ -1,16 +1,16 @@
-<?xml version="1.0" encoding="iso-8859-1"?>
-<!-- Generator: Adobe Illustrator 26.1.0, SVG Export Plug-In . SVG Version: 6.00 Build 0)  -->
-<svg version="1.1" id="Layer_1" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" x="0px" y="0px"
-	 viewBox="0 0 48 48" style="enable-background:new 0 0 48 48;" xml:space="preserve">
-<linearGradient id="SVGID_1_" gradientUnits="userSpaceOnUse" x1="10.5862" y1="1.61" x2="36.0543" y2="44.1206">
-	<stop  offset="0.002" style="stop-color:#9C55D4"/>
-	<stop  offset="0.003" style="stop-color:#20808D"/>
-	<stop  offset="0.3731" style="stop-color:#218F9B"/>
-	<stop  offset="1" style="stop-color:#22B1BC"/>
-</linearGradient>
-<path style="fill-rule:evenodd;clip-rule:evenodd;fill:url(#SVGID_1_);" d="M11.469,4l11.39,10.494v-0.002V4.024h2.217v10.517
-	L36.518,4v11.965h4.697v17.258h-4.683v10.654L25.077,33.813v10.18h-2.217V33.979L11.482,44V33.224H6.785V15.965h4.685V4z
-	 M21.188,18.155H9.002v12.878h2.477v-4.062L21.188,18.155z M13.699,27.943v11.17l9.16-8.068V19.623L13.699,27.943z M25.141,30.938
-	V19.612l9.163,8.321v5.291h0.012v5.775L25.141,30.938z M36.532,31.033h2.466V18.155H26.903l9.629,8.725V31.033z M34.301,15.965
-	V9.038l-7.519,6.927H34.301z M21.205,15.965h-7.519V9.038L21.205,15.965z"/>
+<?xml version="1.0" encoding="iso-8859-1"?>
+<!-- Generator: Adobe Illustrator 26.1.0, SVG Export Plug-In . SVG Version: 6.00 Build 0)  -->
+<svg version="1.1" id="Layer_1" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" x="0px" y="0px"
+	 viewBox="0 0 48 48" style="enable-background:new 0 0 48 48;" xml:space="preserve">
+<linearGradient id="SVGID_1_" gradientUnits="userSpaceOnUse" x1="10.5862" y1="1.61" x2="36.0543" y2="44.1206">
+	<stop  offset="0.002" style="stop-color:#9C55D4"/>
+	<stop  offset="0.003" style="stop-color:#20808D"/>
+	<stop  offset="0.3731" style="stop-color:#218F9B"/>
+	<stop  offset="1" style="stop-color:#22B1BC"/>
+</linearGradient>
+<path style="fill-rule:evenodd;clip-rule:evenodd;fill:url(#SVGID_1_);" d="M11.469,4l11.39,10.494v-0.002V4.024h2.217v10.517
+	L36.518,4v11.965h4.697v17.258h-4.683v10.654L25.077,33.813v10.18h-2.217V33.979L11.482,44V33.224H6.785V15.965h4.685V4z
+	 M21.188,18.155H9.002v12.878h2.477v-4.062L21.188,18.155z M13.699,27.943v11.17l9.16-8.068V19.623L13.699,27.943z M25.141,30.938
+	V19.612l9.163,8.321v5.291h0.012v5.775L25.141,30.938z M36.532,31.033h2.466V18.155H26.903l9.629,8.725V31.033z M34.301,15.965
+	V9.038l-7.519,6.927H34.301z M21.205,15.965h-7.519V9.038L21.205,15.965z"/>
 </svg>

litellm/proxy/_experimental/out/index.txt

@@ -1,7 +1,7 @@
 2:I[19107,[],"ClientPageRoot"]
-3:I[86917,["665","static/chunks/3014691f-b7b79b78e27792f3.js","990","static/chunks/13b76428-ebdf3012af0e4489.js","402","static/chunks/402-ba983153c902cb17.js","313","static/chunks/313-cf4a28394ee560d6.js","899","static/chunks/899-ebef5c8ffc176e86.js","276","static/chunks/276-859a00a1fe124231.js","250","static/chunks/250-562275aca86e6d43.js","699","static/chunks/699-7660d0629950118b.js","931","static/chunks/app/page-00691d283cb03cc8.js"],"default",1]
+3:I[34125,["665","static/chunks/3014691f-b7b79b78e27792f3.js","990","static/chunks/13b76428-ebdf3012af0e4489.js","402","static/chunks/402-239a4ed70dc393da.js","313","static/chunks/313-cf4a28394ee560d6.js","899","static/chunks/899-0459bccb48a6666d.js","966","static/chunks/966-d23842bbd48c2bc2.js","250","static/chunks/250-8d759a787d622b48.js","699","static/chunks/699-96a60f79614507d5.js","931","static/chunks/app/page-86bbb3edba7ec5f0.js"],"default",1]
 4:I[4707,[],""]
 5:I[36423,[],""]
-0:["aV7wX1vsNVbDvWm3r-ZF3",[[["",{"children":["__PAGE__",{}]},"$undefined","$undefined",true],["",{"children":["__PAGE__",{},[["$L1",["$","$L2",null,{"props":{"params":{},"searchParams":{}},"Component":"$3"}],null],null],null]},[[[["$","link","0",{"rel":"stylesheet","href":"/_next/static/css/31b7f215e119031e.css","precedence":"next","crossOrigin":"$undefined"}],["$","link","1",{"rel":"stylesheet","href":"/_next/static/css/20729c6c90dc7f33.css","precedence":"next","crossOrigin":"$undefined"}]],["$","html",null,{"lang":"en","children":["$","body",null,{"className":"__className_b0dd8a","children":["$","$L4",null,{"parallelRouterKey":"children","segmentPath":["children"],"error":"$undefined","errorStyles":"$undefined","errorScripts":"$undefined","template":["$","$L5",null,{}],"templateStyles":"$undefined","templateScripts":"$undefined","notFound":[["$","title",null,{"children":"404: This page could not be found."}],["$","div",null,{"style":{"fontFamily":"system-ui,\"Segoe UI\",Roboto,Helvetica,Arial,sans-serif,\"Apple Color Emoji\",\"Segoe UI Emoji\"","height":"100vh","textAlign":"center","display":"flex","flexDirection":"column","alignItems":"center","justifyContent":"center"},"children":["$","div",null,{"children":[["$","style",null,{"dangerouslySetInnerHTML":{"__html":"body{color:#000;background:#fff;margin:0}.next-error-h1{border-right:1px solid rgba(0,0,0,.3)}@media (prefers-color-scheme:dark){body{color:#fff;background:#000}.next-error-h1{border-right:1px solid rgba(255,255,255,.3)}}"}}],["$","h1",null,{"className":"next-error-h1","style":{"display":"inline-block","margin":"0 20px 0 0","padding":"0 23px 0 0","fontSize":24,"fontWeight":500,"verticalAlign":"top","lineHeight":"49px"},"children":"404"}],["$","div",null,{"style":{"display":"inline-block"},"children":["$","h2",null,{"style":{"fontSize":14,"fontWeight":400,"lineHeight":"49px","margin":0},"children":"This page could not be found."}]}]]}]}]],"notFoundStyles":[]}]}]}]],null],null],["$L6",null]]]]
+0:["zyqLTLglamGh14G70gBJG",[[["",{"children":["__PAGE__",{}]},"$undefined","$undefined",true],["",{"children":["__PAGE__",{},[["$L1",["$","$L2",null,{"props":{"params":{},"searchParams":{}},"Component":"$3"}],null],null],null]},[[[["$","link","0",{"rel":"stylesheet","href":"/litellm-asset-prefix/_next/static/css/31b7f215e119031e.css","precedence":"next","crossOrigin":"$undefined"}],["$","link","1",{"rel":"stylesheet","href":"/litellm-asset-prefix/_next/static/css/27aa365198bdc7c8.css","precedence":"next","crossOrigin":"$undefined"}]],["$","html",null,{"lang":"en","children":["$","body",null,{"className":"__className_b0dd8a","children":["$","$L4",null,{"parallelRouterKey":"children","segmentPath":["children"],"error":"$undefined","errorStyles":"$undefined","errorScripts":"$undefined","template":["$","$L5",null,{}],"templateStyles":"$undefined","templateScripts":"$undefined","notFound":[["$","title",null,{"children":"404: This page could not be found."}],["$","div",null,{"style":{"fontFamily":"system-ui,\"Segoe UI\",Roboto,Helvetica,Arial,sans-serif,\"Apple Color Emoji\",\"Segoe UI Emoji\"","height":"100vh","textAlign":"center","display":"flex","flexDirection":"column","alignItems":"center","justifyContent":"center"},"children":["$","div",null,{"children":[["$","style",null,{"dangerouslySetInnerHTML":{"__html":"body{color:#000;background:#fff;margin:0}.next-error-h1{border-right:1px solid rgba(0,0,0,.3)}@media (prefers-color-scheme:dark){body{color:#fff;background:#000}.next-error-h1{border-right:1px solid rgba(255,255,255,.3)}}"}}],["$","h1",null,{"className":"next-error-h1","style":{"display":"inline-block","margin":"0 20px 0 0","padding":"0 23px 0 0","fontSize":24,"fontWeight":500,"verticalAlign":"top","lineHeight":"49px"},"children":"404"}],["$","div",null,{"style":{"display":"inline-block"},"children":["$","h2",null,{"style":{"fontSize":14,"fontWeight":400,"lineHeight":"49px","margin":0},"children":"This page could not be found."}]}]]}]}]],"notFoundStyles":[]}]}]}]],null],null],["$L6",null]]]]
 6:[["$","meta","0",{"name":"viewport","content":"width=device-width, initial-scale=1"}],["$","meta","1",{"charSet":"utf-8"}],["$","title","2",{"children":"LiteLLM Dashboard"}],["$","meta","3",{"name":"description","content":"LiteLLM Proxy Admin UI"}],["$","link","4",{"rel":"icon","href":"/favicon.ico","type":"image/x-icon","sizes":"16x16"}],["$","link","5",{"rel":"icon","href":"./favicon.ico"}],["$","meta","6",{"name":"next-size-adjust"}]]
 1:null

litellm/proxy/_experimental/out/model_hub.txt

@@ -1,7 +1,7 @@
 2:I[19107,[],"ClientPageRoot"]
-3:I[52829,["402","static/chunks/402-ba983153c902cb17.js","313","static/chunks/313-cf4a28394ee560d6.js","250","static/chunks/250-562275aca86e6d43.js","699","static/chunks/699-7660d0629950118b.js","418","static/chunks/app/model_hub/page-ce40c5a05f3174ca.js"],"default",1]
+3:I[52829,["402","static/chunks/402-239a4ed70dc393da.js","313","static/chunks/313-cf4a28394ee560d6.js","250","static/chunks/250-8d759a787d622b48.js","699","static/chunks/699-96a60f79614507d5.js","418","static/chunks/app/model_hub/page-ce40c5a05f3174ca.js"],"default",1]
 4:I[4707,[],""]
 5:I[36423,[],""]
-0:["aV7wX1vsNVbDvWm3r-ZF3",[[["",{"children":["model_hub",{"children":["__PAGE__",{}]}]},"$undefined","$undefined",true],["",{"children":["model_hub",{"children":["__PAGE__",{},[["$L1",["$","$L2",null,{"props":{"params":{},"searchParams":{}},"Component":"$3"}],null],null],null]},[null,["$","$L4",null,{"parallelRouterKey":"children","segmentPath":["children","model_hub","children"],"error":"$undefined","errorStyles":"$undefined","errorScripts":"$undefined","template":["$","$L5",null,{}],"templateStyles":"$undefined","templateScripts":"$undefined","notFound":"$undefined","notFoundStyles":"$undefined"}]],null]},[[[["$","link","0",{"rel":"stylesheet","href":"/_next/static/css/31b7f215e119031e.css","precedence":"next","crossOrigin":"$undefined"}],["$","link","1",{"rel":"stylesheet","href":"/_next/static/css/20729c6c90dc7f33.css","precedence":"next","crossOrigin":"$undefined"}]],["$","html",null,{"lang":"en","children":["$","body",null,{"className":"__className_b0dd8a","children":["$","$L4",null,{"parallelRouterKey":"children","segmentPath":["children"],"error":"$undefined","errorStyles":"$undefined","errorScripts":"$undefined","template":["$","$L5",null,{}],"templateStyles":"$undefined","templateScripts":"$undefined","notFound":[["$","title",null,{"children":"404: This page could not be found."}],["$","div",null,{"style":{"fontFamily":"system-ui,\"Segoe UI\",Roboto,Helvetica,Arial,sans-serif,\"Apple Color Emoji\",\"Segoe UI Emoji\"","height":"100vh","textAlign":"center","display":"flex","flexDirection":"column","alignItems":"center","justifyContent":"center"},"children":["$","div",null,{"children":[["$","style",null,{"dangerouslySetInnerHTML":{"__html":"body{color:#000;background:#fff;margin:0}.next-error-h1{border-right:1px solid rgba(0,0,0,.3)}@media (prefers-color-scheme:dark){body{color:#fff;background:#000}.next-error-h1{border-right:1px solid rgba(255,255,255,.3)}}"}}],["$","h1",null,{"className":"next-error-h1","style":{"display":"inline-block","margin":"0 20px 0 0","padding":"0 23px 0 0","fontSize":24,"fontWeight":500,"verticalAlign":"top","lineHeight":"49px"},"children":"404"}],["$","div",null,{"style":{"display":"inline-block"},"children":["$","h2",null,{"style":{"fontSize":14,"fontWeight":400,"lineHeight":"49px","margin":0},"children":"This page could not be found."}]}]]}]}]],"notFoundStyles":[]}]}]}]],null],null],["$L6",null]]]]
+0:["zyqLTLglamGh14G70gBJG",[[["",{"children":["model_hub",{"children":["__PAGE__",{}]}]},"$undefined","$undefined",true],["",{"children":["model_hub",{"children":["__PAGE__",{},[["$L1",["$","$L2",null,{"props":{"params":{},"searchParams":{}},"Component":"$3"}],null],null],null]},[null,["$","$L4",null,{"parallelRouterKey":"children","segmentPath":["children","model_hub","children"],"error":"$undefined","errorStyles":"$undefined","errorScripts":"$undefined","template":["$","$L5",null,{}],"templateStyles":"$undefined","templateScripts":"$undefined","notFound":"$undefined","notFoundStyles":"$undefined"}]],null]},[[[["$","link","0",{"rel":"stylesheet","href":"/litellm-asset-prefix/_next/static/css/31b7f215e119031e.css","precedence":"next","crossOrigin":"$undefined"}],["$","link","1",{"rel":"stylesheet","href":"/litellm-asset-prefix/_next/static/css/27aa365198bdc7c8.css","precedence":"next","crossOrigin":"$undefined"}]],["$","html",null,{"lang":"en","children":["$","body",null,{"className":"__className_b0dd8a","children":["$","$L4",null,{"parallelRouterKey":"children","segmentPath":["children"],"error":"$undefined","errorStyles":"$undefined","errorScripts":"$undefined","template":["$","$L5",null,{}],"templateStyles":"$undefined","templateScripts":"$undefined","notFound":[["$","title",null,{"children":"404: This page could not be found."}],["$","div",null,{"style":{"fontFamily":"system-ui,\"Segoe UI\",Roboto,Helvetica,Arial,sans-serif,\"Apple Color Emoji\",\"Segoe UI Emoji\"","height":"100vh","textAlign":"center","display":"flex","flexDirection":"column","alignItems":"center","justifyContent":"center"},"children":["$","div",null,{"children":[["$","style",null,{"dangerouslySetInnerHTML":{"__html":"body{color:#000;background:#fff;margin:0}.next-error-h1{border-right:1px solid rgba(0,0,0,.3)}@media (prefers-color-scheme:dark){body{color:#fff;background:#000}.next-error-h1{border-right:1px solid rgba(255,255,255,.3)}}"}}],["$","h1",null,{"className":"next-error-h1","style":{"display":"inline-block","margin":"0 20px 0 0","padding":"0 23px 0 0","fontSize":24,"fontWeight":500,"verticalAlign":"top","lineHeight":"49px"},"children":"404"}],["$","div",null,{"style":{"display":"inline-block"},"children":["$","h2",null,{"style":{"fontSize":14,"fontWeight":400,"lineHeight":"49px","margin":0},"children":"This page could not be found."}]}]]}]}]],"notFoundStyles":[]}]}]}]],null],null],["$L6",null]]]]
 6:[["$","meta","0",{"name":"viewport","content":"width=device-width, initial-scale=1"}],["$","meta","1",{"charSet":"utf-8"}],["$","title","2",{"children":"LiteLLM Dashboard"}],["$","meta","3",{"name":"description","content":"LiteLLM Proxy Admin UI"}],["$","link","4",{"rel":"icon","href":"/favicon.ico","type":"image/x-icon","sizes":"16x16"}],["$","link","5",{"rel":"icon","href":"./favicon.ico"}],["$","meta","6",{"name":"next-size-adjust"}]]
 1:null

litellm/proxy/_experimental/out/onboarding.txt

@@ -1,7 +1,7 @@
 2:I[19107,[],"ClientPageRoot"]
-3:I[12011,["665","static/chunks/3014691f-b7b79b78e27792f3.js","402","static/chunks/402-ba983153c902cb17.js","899","static/chunks/899-ebef5c8ffc176e86.js","250","static/chunks/250-562275aca86e6d43.js","461","static/chunks/app/onboarding/page-74706b15590d94d7.js"],"default",1]
+3:I[12011,["665","static/chunks/3014691f-b7b79b78e27792f3.js","402","static/chunks/402-239a4ed70dc393da.js","899","static/chunks/899-0459bccb48a6666d.js","250","static/chunks/250-8d759a787d622b48.js","461","static/chunks/app/onboarding/page-be52e5770ada890a.js"],"default",1]
 4:I[4707,[],""]
 5:I[36423,[],""]
-0:["aV7wX1vsNVbDvWm3r-ZF3",[[["",{"children":["onboarding",{"children":["__PAGE__",{}]}]},"$undefined","$undefined",true],["",{"children":["onboarding",{"children":["__PAGE__",{},[["$L1",["$","$L2",null,{"props":{"params":{},"searchParams":{}},"Component":"$3"}],null],null],null]},[null,["$","$L4",null,{"parallelRouterKey":"children","segmentPath":["children","onboarding","children"],"error":"$undefined","errorStyles":"$undefined","errorScripts":"$undefined","template":["$","$L5",null,{}],"templateStyles":"$undefined","templateScripts":"$undefined","notFound":"$undefined","notFoundStyles":"$undefined"}]],null]},[[[["$","link","0",{"rel":"stylesheet","href":"/_next/static/css/31b7f215e119031e.css","precedence":"next","crossOrigin":"$undefined"}],["$","link","1",{"rel":"stylesheet","href":"/_next/static/css/20729c6c90dc7f33.css","precedence":"next","crossOrigin":"$undefined"}]],["$","html",null,{"lang":"en","children":["$","body",null,{"className":"__className_b0dd8a","children":["$","$L4",null,{"parallelRouterKey":"children","segmentPath":["children"],"error":"$undefined","errorStyles":"$undefined","errorScripts":"$undefined","template":["$","$L5",null,{}],"templateStyles":"$undefined","templateScripts":"$undefined","notFound":[["$","title",null,{"children":"404: This page could not be found."}],["$","div",null,{"style":{"fontFamily":"system-ui,\"Segoe UI\",Roboto,Helvetica,Arial,sans-serif,\"Apple Color Emoji\",\"Segoe UI Emoji\"","height":"100vh","textAlign":"center","display":"flex","flexDirection":"column","alignItems":"center","justifyContent":"center"},"children":["$","div",null,{"children":[["$","style",null,{"dangerouslySetInnerHTML":{"__html":"body{color:#000;background:#fff;margin:0}.next-error-h1{border-right:1px solid rgba(0,0,0,.3)}@media (prefers-color-scheme:dark){body{color:#fff;background:#000}.next-error-h1{border-right:1px solid rgba(255,255,255,.3)}}"}}],["$","h1",null,{"className":"next-error-h1","style":{"display":"inline-block","margin":"0 20px 0 0","padding":"0 23px 0 0","fontSize":24,"fontWeight":500,"verticalAlign":"top","lineHeight":"49px"},"children":"404"}],["$","div",null,{"style":{"display":"inline-block"},"children":["$","h2",null,{"style":{"fontSize":14,"fontWeight":400,"lineHeight":"49px","margin":0},"children":"This page could not be found."}]}]]}]}]],"notFoundStyles":[]}]}]}]],null],null],["$L6",null]]]]
+0:["zyqLTLglamGh14G70gBJG",[[["",{"children":["onboarding",{"children":["__PAGE__",{}]}]},"$undefined","$undefined",true],["",{"children":["onboarding",{"children":["__PAGE__",{},[["$L1",["$","$L2",null,{"props":{"params":{},"searchParams":{}},"Component":"$3"}],null],null],null]},[null,["$","$L4",null,{"parallelRouterKey":"children","segmentPath":["children","onboarding","children"],"error":"$undefined","errorStyles":"$undefined","errorScripts":"$undefined","template":["$","$L5",null,{}],"templateStyles":"$undefined","templateScripts":"$undefined","notFound":"$undefined","notFoundStyles":"$undefined"}]],null]},[[[["$","link","0",{"rel":"stylesheet","href":"/litellm-asset-prefix/_next/static/css/31b7f215e119031e.css","precedence":"next","crossOrigin":"$undefined"}],["$","link","1",{"rel":"stylesheet","href":"/litellm-asset-prefix/_next/static/css/27aa365198bdc7c8.css","precedence":"next","crossOrigin":"$undefined"}]],["$","html",null,{"lang":"en","children":["$","body",null,{"className":"__className_b0dd8a","children":["$","$L4",null,{"parallelRouterKey":"children","segmentPath":["children"],"error":"$undefined","errorStyles":"$undefined","errorScripts":"$undefined","template":["$","$L5",null,{}],"templateStyles":"$undefined","templateScripts":"$undefined","notFound":[["$","title",null,{"children":"404: This page could not be found."}],["$","div",null,{"style":{"fontFamily":"system-ui,\"Segoe UI\",Roboto,Helvetica,Arial,sans-serif,\"Apple Color Emoji\",\"Segoe UI Emoji\"","height":"100vh","textAlign":"center","display":"flex","flexDirection":"column","alignItems":"center","justifyContent":"center"},"children":["$","div",null,{"children":[["$","style",null,{"dangerouslySetInnerHTML":{"__html":"body{color:#000;background:#fff;margin:0}.next-error-h1{border-right:1px solid rgba(0,0,0,.3)}@media (prefers-color-scheme:dark){body{color:#fff;background:#000}.next-error-h1{border-right:1px solid rgba(255,255,255,.3)}}"}}],["$","h1",null,{"className":"next-error-h1","style":{"display":"inline-block","margin":"0 20px 0 0","padding":"0 23px 0 0","fontSize":24,"fontWeight":500,"verticalAlign":"top","lineHeight":"49px"},"children":"404"}],["$","div",null,{"style":{"display":"inline-block"},"children":["$","h2",null,{"style":{"fontSize":14,"fontWeight":400,"lineHeight":"49px","margin":0},"children":"This page could not be found."}]}]]}]}]],"notFoundStyles":[]}]}]}]],null],null],["$L6",null]]]]
 6:[["$","meta","0",{"name":"viewport","content":"width=device-width, initial-scale=1"}],["$","meta","1",{"charSet":"utf-8"}],["$","title","2",{"children":"LiteLLM Dashboard"}],["$","meta","3",{"name":"description","content":"LiteLLM Proxy Admin UI"}],["$","link","4",{"rel":"icon","href":"/favicon.ico","type":"image/x-icon","sizes":"16x16"}],["$","link","5",{"rel":"icon","href":"./favicon.ico"}],["$","meta","6",{"name":"next-size-adjust"}]]
 1:null

litellm/proxy/_new_secret_config.yaml

@@ -3,6 +3,12 @@ model_list:
     litellm_params:
       model: codex-mini-latest
       api_key: os.environ/OPENAI_API_KEY
+  - model_name: bedrock/*
+    litellm_params:
+      model: bedrock/*
+  - model_name: eu.anthropic.claude-3-5-sonnet-20240620-v1:0
+    litellm_params:
+      model: eu.anthropic.claude-3-5-sonnet-20240620-v1:0
   - model_name: "gpt-4o-mini-openai"
     litellm_params:
       model: gpt-4o-mini

litellm/proxy/_types.py

@@ -17,6 +17,13 @@ from typing_extensions import Required, TypedDict
 
 from litellm.types.integrations.slack_alerting import AlertType
 from litellm.types.llms.openai import AllMessageValues, OpenAIFileObject
+from litellm.types.mcp import (
+    MCPAuthType,
+    MCPSpecVersion,
+    MCPSpecVersionType,
+    MCPTransport,
+    MCPTransportType,
+)
 from litellm.types.router import RouterErrors, UpdateRouterConfig
 from litellm.types.utils import (
     CallTypes,
@@ -830,32 +837,6 @@ class SpecialMCPServerName(str, enum.Enum):
     all_team_servers = "all-team-mcpservers"
     all_proxy_servers = "all-proxy-mcpservers"
 
-
-class MCPTransport(str, enum.Enum):
-    sse = "sse"
-    http = "http"
-
-
-class MCPSpecVersion(str, enum.Enum):
-    nov_2024 = "2024-11-05"
-    mar_2025 = "2025-03-26"
-
-
-class MCPAuth(str, enum.Enum):
-    none = "none"
-    api_key = "api_key"
-    bearer_token = "bearer_token"
-    basic = "basic"
-
-
-# MCP Literals
-MCPTransportType = Literal[MCPTransport.sse, MCPTransport.http]
-MCPSpecVersionType = Literal[MCPSpecVersion.nov_2024, MCPSpecVersion.mar_2025]
-MCPAuthType = Optional[
-    Literal[MCPAuth.none, MCPAuth.api_key, MCPAuth.bearer_token, MCPAuth.basic]
-]
-
-
 # MCP Proxy Request Types
 class NewMCPServerRequest(LiteLLMPydanticObjectBase):
     server_id: Optional[str] = None
@@ -2703,6 +2684,7 @@ class SpecialHeaders(enum.Enum):
     google_ai_studio_authorization = "x-goog-api-key"
     azure_apim_authorization = "Ocp-Apim-Subscription-Key"
     custom_litellm_api_key = "x-litellm-api-key"
+    mcp_auth = "x-mcp-auth"
 
 
 class LitellmDataForBackendLLMCall(TypedDict, total=False):

litellm/proxy/management_endpoints/internal_user_endpoints.py

@@ -199,14 +199,17 @@ async def _add_user_to_team(
                     str(e)
                 )
             )
-    except ProxyException as e:
+    except Exception as e:
         if "already exists" in str(e) or "doesn't exist" in str(e):
             verbose_proxy_logger.debug(
                 "litellm.proxy.management_endpoints.internal_user_endpoints.new_user(): User already exists in team - {}".format(
                     str(e)
                 )
             )
-        elif ProxyErrorTypes.team_member_already_in_team in e.type:
+        elif (
+            isinstance(e, ProxyException)
+            and ProxyErrorTypes.team_member_already_in_team in e.type
+        ):
             verbose_proxy_logger.debug(
                 "litellm.proxy.management_endpoints.internal_user_endpoints.new_user(): User already exists in team - {}".format(
                     str(e)

litellm/proxy/management_endpoints/tag_management_endpoints.py

@@ -1,18 +1,19 @@
 """
 TAG MANAGEMENT
 
-All /tag management endpoints 
+All /tag management endpoints
 
-/tag/new   
+/tag/new
 /tag/info
 /tag/update
 /tag/delete
 /tag/list
 """
 
+import asyncio
 import datetime
 import json
-from typing import Dict, List, Optional
+from typing import TYPE_CHECKING, Dict, List, Optional
 
 from fastapi import APIRouter, Depends, HTTPException
 
@@ -33,6 +34,10 @@ from litellm.types.tag_management import (
     TagUpdateRequest,
 )
 
+if TYPE_CHECKING:
+    from litellm import Router
+    from litellm.types.router import Deployment
+
 router = APIRouter()
 
 
@@ -111,6 +116,33 @@ async def _save_tags_config(prisma_client, tags_config: Dict[str, TagConfig]):
         )
 
 
+async def get_deployments_by_model(
+    model: str, llm_router: "Router"
+) -> List["Deployment"]:
+    """
+    Get all deployments by model
+    """
+    from litellm.types.router import Deployment, LiteLLM_Params, ModelInfo
+
+    # Check if model id
+    deployment = llm_router.get_deployment(model_id=model)
+    if deployment is not None:
+        return [deployment]
+
+    # Check if model name
+    deployments = llm_router.get_model_list(model_name=model)
+    if deployments is None:
+        return []
+    return [
+        Deployment(
+            model_name=deployment["model_name"],
+            litellm_params=LiteLLM_Params(**deployment["litellm_params"]),  # type: ignore
+            model_info=ModelInfo(**deployment.get("model_info") or {}),
+        )
+        for deployment in deployments
+    ]
+
+
 @router.post(
     "/tag/new",
     tags=["tag management"],
@@ -126,12 +158,19 @@ async def new_tag(
     Parameters:
     - name: str - The name of the tag
     - description: Optional[str] - Description of what this tag represents
-    - models: List[str] - List of LLM models allowed for this tag
+    - models: List[str] - List of either 'model_id' or 'model_name' allowed for this tag
     """
-    from litellm.proxy.proxy_server import prisma_client
+    from litellm.proxy._types import CommonProxyErrors
+    from litellm.proxy.proxy_server import llm_router, prisma_client
 
     if prisma_client is None:
-        raise HTTPException(status_code=500, detail="Database not connected")
+        raise HTTPException(
+            status_code=500, detail=CommonProxyErrors.db_not_connected_error.value
+        )
+    if llm_router is None:
+        raise HTTPException(
+            status_code=500, detail=CommonProxyErrors.no_llm_router.value
+        )
     try:
         # Get existing tags config
         tags_config = await _get_tags_config(prisma_client)
@@ -160,11 +199,19 @@ async def new_tag(
 
         # Update models with new tag
         if tag.models:
-            for model_id in tag.models:
-                await _add_tag_to_deployment(
-                    model_id=model_id,
-                    tag=tag.name,
+            tasks = []
+            for model in tag.models:
+                deployments = await get_deployments_by_model(model, llm_router)
+                tasks.extend(
+                    [
+                        _add_tag_to_deployment(
+                            deployment=deployment,
+                            tag=tag.name,
+                        )
+                        for deployment in deployments
+                    ]
                 )
+            await asyncio.gather(*tasks)
 
         # Get model names for response
         model_info = await _get_model_names(prisma_client, tag.models or [])
@@ -179,27 +226,26 @@ async def new_tag(
         raise HTTPException(status_code=500, detail=str(e))
 
 
-async def _add_tag_to_deployment(model_id: str, tag: str):
+async def _add_tag_to_deployment(deployment: "Deployment", tag: str):
     """Helper function to add tag to deployment"""
     from litellm.proxy.proxy_server import prisma_client
 
     if prisma_client is None:
         raise HTTPException(status_code=500, detail="Database not connected")
 
-    deployment = await prisma_client.db.litellm_proxymodeltable.find_unique(
-        where={"model_id": model_id}
-    )
-    if deployment is None:
-        raise HTTPException(status_code=404, detail=f"Deployment {model_id} not found")
-
     litellm_params = deployment.litellm_params
     if "tags" not in litellm_params:
         litellm_params["tags"] = []
     litellm_params["tags"].append(tag)
-    await prisma_client.db.litellm_proxymodeltable.update(
-        where={"model_id": model_id},
-        data={"litellm_params": safe_dumps(litellm_params)},
-    )
+
+    try:
+        await prisma_client.db.litellm_proxymodeltable.update(
+            where={"model_id": deployment.model_info.id},
+            data={"litellm_params": safe_dumps(litellm_params)},
+        )
+    except Exception as e:
+        verbose_proxy_logger.exception(f"Error adding tag to deployment: {str(e)}")
+        raise HTTPException(status_code=500, detail=str(e))
 
 
 @router.post(

litellm/proxy/proxy_server.py

@@ -752,21 +752,6 @@ try:
     current_dir = os.path.dirname(os.path.abspath(__file__))
     ui_path = os.path.join(current_dir, "_experimental", "out")
     litellm_asset_prefix = "/litellm-asset-prefix"
-    # # Mount the _next directory at the root level
-    app.mount(
-        "/_next",
-        StaticFiles(directory=os.path.join(ui_path, "_next")),
-        name="next_static",
-    )
-    app.mount(
-        f"{litellm_asset_prefix}/_next",
-        StaticFiles(directory=os.path.join(ui_path, "_next")),
-        name="next_static",
-    )
-    # print(f"mounted _next at {server_root_path}/ui/_next")
-
-    app.mount("/ui", StaticFiles(directory=ui_path, html=True), name="ui")
-
     # Iterate through files in the UI directory
     for root, dirs, files in os.walk(ui_path):
         for filename in files:
@@ -792,19 +777,37 @@ try:
 
                 # Replace the asset prefix with the server root path
                 modified_content = content.replace(
-                    f"{litellm_asset_prefix}", server_root_path
+                    f"{litellm_asset_prefix}",
+                    f"{server_root_path}",
                 )
+
                 # Replace the /.well-known/litellm-ui-config with the server root path
                 modified_content = modified_content.replace(
                     "/litellm/.well-known/litellm-ui-config",
                     f"{server_root_path}/.well-known/litellm-ui-config",
                 )
+
                 with open(file_path, "w", encoding="utf-8") as f:
                     f.write(modified_content)
             except UnicodeDecodeError:
                 # Skip binary files that can't be decoded
                 continue
 
+    # # Mount the _next directory at the root level
+    app.mount(
+        "/_next",
+        StaticFiles(directory=os.path.join(ui_path, "_next")),
+        name="next_static",
+    )
+    app.mount(
+        f"{litellm_asset_prefix}/_next",
+        StaticFiles(directory=os.path.join(ui_path, "_next")),
+        name="next_static",
+    )
+    # print(f"mounted _next at {server_root_path}/ui/_next")
+
+    app.mount("/ui", StaticFiles(directory=ui_path, html=True), name="ui")
+
     # Handle HTML file restructuring
     for filename in os.listdir(ui_path):
         if filename.endswith(".html") and filename != "index.html":

litellm/responses/litellm_completion_transformation/transformation.py

@@ -2,7 +2,7 @@
 Handles transforming from Responses API -> LiteLLM completion  (Chat Completion API)
 """
 
-from typing import Any, Dict, List, Optional, Union, cast
+from typing import Any, Dict, List, Literal, Optional, Tuple, Union, cast
 
 from openai.types.responses.tool_param import FunctionToolParam
 from typing_extensions import TypedDict
@@ -32,6 +32,8 @@ from litellm.types.llms.openai import (
     ChatCompletionUserMessage,
     GenericChatCompletionMessage,
     OpenAIMcpServerTool,
+    OpenAIWebSearchOptions,
+    OpenAIWebSearchUserLocation,
     Reasoning,
     ResponseAPIUsage,
     ResponseInputParam,
@@ -109,6 +111,9 @@ class LiteLLMCompletionResponsesConfig:
         """
         Transform a Responses API request into a Chat Completion request
         """
+        tools, web_search_options = LiteLLMCompletionResponsesConfig.transform_responses_api_tools_to_chat_completion_tools(
+            responses_api_request.get("tools") or []  # type: ignore
+        )
         litellm_completion_request: dict = {
             "messages": LiteLLMCompletionResponsesConfig.transform_responses_api_input_to_messages(
                 input=input,
@@ -116,9 +121,7 @@ class LiteLLMCompletionResponsesConfig:
             ),
             "model": model,
             "tool_choice": responses_api_request.get("tool_choice"),
-            "tools": LiteLLMCompletionResponsesConfig.transform_responses_api_tools_to_chat_completion_tools(
-                responses_api_request.get("tools") or []  # type: ignore
-            ),
+            "tools": tools,
             "top_p": responses_api_request.get("top_p"),
             "user": responses_api_request.get("user"),
             "temperature": responses_api_request.get("temperature"),
@@ -127,6 +130,7 @@ class LiteLLMCompletionResponsesConfig:
             "stream": stream,
             "metadata": kwargs.get("metadata"),
             "service_tier": kwargs.get("service_tier"),
+            "web_search_options": web_search_options,
             # litellm specific params
             "custom_llm_provider": custom_llm_provider,
         }
@@ -468,32 +472,40 @@ class LiteLLMCompletionResponsesConfig:
     @staticmethod
     def transform_responses_api_tools_to_chat_completion_tools(
         tools: Optional[List[Union[FunctionToolParam, OpenAIMcpServerTool]]],
-    ) -> List[Union[ChatCompletionToolParam, OpenAIMcpServerTool]]:
+    ) -> Tuple[List[Union[ChatCompletionToolParam, OpenAIMcpServerTool]], Optional[OpenAIWebSearchOptions]]:
         """
         Transform a Responses API tools into a Chat Completion tools
         """
         if tools is None:
-            return []
+            return [], None
         chat_completion_tools: List[
             Union[ChatCompletionToolParam, OpenAIMcpServerTool]
         ] = []
+        web_search_options: Optional[OpenAIWebSearchOptions] = None
         for tool in tools:
             if tool.get("type") == "mcp":
                 chat_completion_tools.append(cast(OpenAIMcpServerTool, tool))
+            elif tool.get("type") == "web_search_preview" or tool.get("type") == "web_search":
+                _search_context_size: Literal["low", "medium", "high"] = cast(Literal["low", "medium", "high"], tool.get("search_context_size"))
+                _user_location: Optional[OpenAIWebSearchUserLocation] = cast(Optional[OpenAIWebSearchUserLocation], tool.get("user_location") or None)
+                web_search_options = OpenAIWebSearchOptions(
+                    search_context_size=_search_context_size,
+                    user_location=_user_location,
+                )
             else:
                 typed_tool = cast(FunctionToolParam, tool)
                 chat_completion_tools.append(
                     ChatCompletionToolParam(
                         type="function",
                         function=ChatCompletionToolParamFunctionChunk(
-                            name=typed_tool["name"],
+                            name=typed_tool.get("name") or "",
                             description=typed_tool.get("description") or "",
                             parameters=dict(typed_tool.get("parameters", {}) or {}),
                             strict=typed_tool.get("strict", False) or False,
                         ),
                     )
                 )
-        return chat_completion_tools
+        return chat_completion_tools, web_search_options
 
     @staticmethod
     def transform_chat_completion_tools_to_responses_tools(

litellm/types/integrations/prometheus.py

@@ -71,6 +71,7 @@ class UserAPIKeyLabelNames(Enum):
     STATUS_CODE = "status_code"
     FALLBACK_MODEL = "fallback_model"
     ROUTE = "route"
+    MODEL_GROUP = "model_group"
 
 
 DEFINED_PROMETHEUS_METRICS = Literal[
@@ -161,7 +162,7 @@ class PrometheusMetricLabels:
     ]
 
     litellm_overhead_latency_metric = [
-        UserAPIKeyLabelNames.REQUESTED_MODEL.value,
+        UserAPIKeyLabelNames.MODEL_GROUP.value,
         UserAPIKeyLabelNames.API_PROVIDER.value,
         UserAPIKeyLabelNames.API_BASE.value,
         UserAPIKeyLabelNames.v2_LITELLM_MODEL_NAME.value,
@@ -170,7 +171,7 @@ class PrometheusMetricLabels:
     ]
 
     litellm_remaining_requests_metric = [
-        UserAPIKeyLabelNames.REQUESTED_MODEL.value,
+        UserAPIKeyLabelNames.MODEL_GROUP.value,
         UserAPIKeyLabelNames.API_PROVIDER.value,
         UserAPIKeyLabelNames.API_BASE.value,
         UserAPIKeyLabelNames.v2_LITELLM_MODEL_NAME.value,
@@ -179,7 +180,7 @@ class PrometheusMetricLabels:
     ]
 
     litellm_remaining_tokens_metric = [
-        UserAPIKeyLabelNames.REQUESTED_MODEL.value,
+        UserAPIKeyLabelNames.MODEL_GROUP.value,
         UserAPIKeyLabelNames.API_PROVIDER.value,
         UserAPIKeyLabelNames.API_BASE.value,
         UserAPIKeyLabelNames.v2_LITELLM_MODEL_NAME.value,
@@ -335,6 +336,9 @@ class UserAPIKeyLabelValues(BaseModel):
     team_alias: Annotated[
         Optional[str], Field(..., alias=UserAPIKeyLabelNames.TEAM_ALIAS.value)
     ] = None
+    model_group: Annotated[
+        Optional[str], Field(..., alias=UserAPIKeyLabelNames.MODEL_GROUP.value)
+    ] = None
     requested_model: Annotated[
         Optional[str], Field(..., alias=UserAPIKeyLabelNames.REQUESTED_MODEL.value)
     ] = None

litellm/types/mcp.py

@@ -0,0 +1,29 @@
+import enum
+from typing import Literal, Optional
+
+from pydantic import BaseModel, ConfigDict
+from typing_extensions import TypedDict
+
+
+class MCPTransport(str, enum.Enum):
+    sse = "sse"
+    http = "http"
+
+
+class MCPSpecVersion(str, enum.Enum):
+    nov_2024 = "2024-11-05"
+    mar_2025 = "2025-03-26"
+
+class MCPAuth(str, enum.Enum):
+    none = "none"
+    api_key = "api_key"
+    bearer_token = "bearer_token"
+    basic = "basic"
+
+
+# MCP Literals
+MCPTransportType = Literal[MCPTransport.sse, MCPTransport.http]
+MCPSpecVersionType = Literal[MCPSpecVersion.nov_2024, MCPSpecVersion.mar_2025]
+MCPAuthType = Optional[
+    Literal[MCPAuth.none, MCPAuth.api_key, MCPAuth.bearer_token, MCPAuth.basic]
+]

litellm/types/mcp_server/mcp_server_manager.py

@@ -16,9 +16,9 @@ class MCPServer(BaseModel):
     server_id: str
     name: str
     url: str
-    # TODO: alter the types to be the Literal explicit
     transport: MCPTransportType
     spec_version: MCPSpecVersionType
     auth_type: Optional[MCPAuthType] = None
+    authentication_token: Optional[str] = None
     mcp_info: Optional[MCPInfo] = None
     model_config = ConfigDict(arbitrary_types_allowed=True)

model_prices_and_context_window.json

@@ -451,9 +451,9 @@
         "max_input_tokens": 128000,
         "max_output_tokens": 16384,
         "input_cost_per_token": 2.5e-06,
-        "input_cost_per_audio_token": 4.0e-5,
+        "input_cost_per_audio_token": 4e-05,
         "output_cost_per_token": 1e-05,
-        "output_cost_per_audio_token": 8.0e-5,
+        "output_cost_per_audio_token": 8e-05,
         "litellm_provider": "openai",
         "mode": "chat",
         "supports_function_calling": true,
@@ -594,7 +594,7 @@
         "max_output_tokens": 100000,
         "input_cost_per_token": 1.5e-06,
         "output_cost_per_token": 6e-06,
-        "cache_read_input_token_cost": 0.375e-06,
+        "cache_read_input_token_cost": 3.75e-07,
         "litellm_provider": "openai",
         "mode": "responses",
         "supports_pdf_input": true,
@@ -744,10 +744,10 @@
         "max_tokens": 100000,
         "max_input_tokens": 200000,
         "max_output_tokens": 100000,
-        "input_cost_per_token": 20e-06,
-        "input_cost_per_token_batches": 10e-06,
-        "output_cost_per_token_batches": 40e-06,
-        "output_cost_per_token": 80e-06,
+        "input_cost_per_token": 2e-05,
+        "input_cost_per_token_batches": 1e-05,
+        "output_cost_per_token_batches": 4e-05,
+        "output_cost_per_token": 8e-05,
         "litellm_provider": "openai",
         "mode": "responses",
         "supports_function_calling": true,
@@ -774,10 +774,10 @@
         "max_tokens": 100000,
         "max_input_tokens": 200000,
         "max_output_tokens": 100000,
-        "input_cost_per_token": 20e-06,
-        "input_cost_per_token_batches": 10e-06,
-        "output_cost_per_token_batches": 40e-06,
-        "output_cost_per_token": 80e-06,
+        "input_cost_per_token": 2e-05,
+        "input_cost_per_token_batches": 1e-05,
+        "output_cost_per_token_batches": 4e-05,
+        "output_cost_per_token": 8e-05,
         "litellm_provider": "openai",
         "mode": "responses",
         "supports_function_calling": true,
@@ -806,7 +806,7 @@
         "max_output_tokens": 100000,
         "input_cost_per_token": 2e-06,
         "output_cost_per_token": 8e-06,
-        "cache_read_input_token_cost": 0.5e-06,
+        "cache_read_input_token_cost": 5e-07,
         "litellm_provider": "openai",
         "mode": "chat",
         "supports_function_calling": true,
@@ -837,7 +837,7 @@
         "max_output_tokens": 100000,
         "input_cost_per_token": 2e-06,
         "output_cost_per_token": 8e-06,
-        "cache_read_input_token_cost": 0.5e-06,
+        "cache_read_input_token_cost": 5e-07,
         "litellm_provider": "openai",
         "mode": "chat",
         "supports_function_calling": true,
@@ -2685,7 +2685,7 @@
         "max_output_tokens": 100000,
         "input_cost_per_token": 1.5e-06,
         "output_cost_per_token": 6e-06,
-        "cache_read_input_token_cost": 0.375e-06,
+        "cache_read_input_token_cost": 3.75e-07,
         "litellm_provider": "azure",
         "mode": "responses",
         "supports_pdf_input": true,
@@ -4295,8 +4295,8 @@
         "max_tokens": 40000,
         "max_input_tokens": 40000,
         "max_output_tokens": 40000,
-        "input_cost_per_token": 0.5e-6,
-        "output_cost_per_token": 1.5e-6,
+        "input_cost_per_token": 5e-07,
+        "output_cost_per_token": 1.5e-06,
         "litellm_provider": "mistral",
         "mode": "chat",
         "source": "https://mistral.ai/pricing#api-pricing",
@@ -4309,7 +4309,7 @@
         "max_tokens": 40000,
         "max_input_tokens": 40000,
         "max_output_tokens": 40000,
-        "input_cost_per_token": 0.5e-06,
+        "input_cost_per_token": 5e-07,
         "output_cost_per_token": 1.5e-06,
         "litellm_provider": "mistral",
         "mode": "chat",
@@ -4579,9 +4579,9 @@
         "output_cost_per_token": 4e-06,
         "litellm_provider": "xai",
         "mode": "chat",
+        "supports_reasoning": true,
         "supports_function_calling": true,
         "supports_tool_choice": true,
-        "supports_reasoning": true,
         "supports_response_schema": false,
         "source": "https://x.ai/api#pricing",
         "supports_web_search": true
@@ -4616,21 +4616,6 @@
         "source": "https://x.ai/api#pricing",
         "supports_web_search": true
     },
-    "xai/grok-3-mini-fast-latest": {
-        "max_tokens": 131072,
-        "max_input_tokens": 131072,
-        "max_output_tokens": 131072,
-        "input_cost_per_token": 6e-07,
-        "output_cost_per_token": 4e-06,
-        "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",
-        "supports_web_search": true
-    },
     "xai/grok-vision-beta": {
         "max_tokens": 8192,
         "max_input_tokens": 8192,
@@ -5812,9 +5797,9 @@
         "max_output_tokens": 4028,
         "litellm_provider": "meta_llama",
         "mode": "chat",
-        "supports_function_calling": false,
+        "supports_function_calling": true,
         "source": "https://llama.developer.meta.com/docs/models",
-        "supports_tool_choice": false,
+        "supports_tool_choice": true,
         "supported_modalities": [
             "text",
             "image"
@@ -5829,9 +5814,9 @@
         "max_output_tokens": 4028,
         "litellm_provider": "meta_llama",
         "mode": "chat",
-        "supports_function_calling": false,
+        "supports_function_calling": true,
         "source": "https://llama.developer.meta.com/docs/models",
-        "supports_tool_choice": false,
+        "supports_tool_choice": true,
         "supported_modalities": [
             "text",
             "image"
@@ -5846,9 +5831,9 @@
         "max_output_tokens": 4028,
         "litellm_provider": "meta_llama",
         "mode": "chat",
-        "supports_function_calling": false,
+        "supports_function_calling": true,
         "source": "https://llama.developer.meta.com/docs/models",
-        "supports_tool_choice": false,
+        "supports_tool_choice": true,
         "supported_modalities": [
             "text"
         ],
@@ -5862,9 +5847,9 @@
         "max_output_tokens": 4028,
         "litellm_provider": "meta_llama",
         "mode": "chat",
-        "supports_function_calling": false,
+        "supports_function_calling": true,
         "source": "https://llama.developer.meta.com/docs/models",
-        "supports_tool_choice": false,
+        "supports_tool_choice": true,
         "supported_modalities": [
             "text"
         ],
@@ -6735,8 +6720,8 @@
         "output_cost_per_token_above_200k_tokens": 1.5e-05,
         "litellm_provider": "gemini",
         "mode": "chat",
-        "rpm": 2e-3,
-        "tpm": 8e-6,
+        "rpm": 2000,
+        "tpm": 800000,
         "supports_system_messages": true,
         "supports_function_calling": true,
         "supports_vision": true,
@@ -6802,8 +6787,9 @@
         "supports_parallel_function_calling": true,
         "supports_web_search": true,
         "supports_url_context": true,
-        "tpm": 8e-6,
-        "rpm": 1e-5
+        "tpm": 8000000,
+        "rpm": 100000,
+        "supports_pdf_input": true
     },
     "gemini-2.5-flash": {
         "max_tokens": 65535,
@@ -6845,7 +6831,8 @@
         "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview",
         "supports_parallel_function_calling": true,
         "supports_web_search": true,
-        "supports_url_context": true
+        "supports_url_context": true,
+        "supports_pdf_input": true
     },
     "gemini/gemini-2.5-flash-preview-tts": {
         "max_tokens": 65535,
@@ -6896,9 +6883,9 @@
         "max_audio_per_prompt": 1,
         "max_pdf_size_mb": 30,
         "input_cost_per_audio_token": 1e-06,
-        "input_cost_per_token": 1.5e-07,
-        "output_cost_per_token": 6e-07,
-        "output_cost_per_reasoning_token": 3.5e-06,
+        "input_cost_per_token": 3e-07,
+        "output_cost_per_token": 2.5e-06,
+        "output_cost_per_reasoning_token": 2.5e-06,
         "litellm_provider": "gemini",
         "mode": "chat",
         "rpm": 10,
@@ -6925,7 +6912,8 @@
         ],
         "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview",
         "supports_web_search": true,
-        "supports_url_context": true
+        "supports_url_context": true,
+        "supports_pdf_input": true
     },
     "gemini/gemini-2.5-flash-preview-04-17": {
         "max_tokens": 65535,
@@ -6966,7 +6954,53 @@
             "text"
         ],
         "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview",
-        "supports_web_search": true
+        "supports_web_search": true,
+        "supports_pdf_input": true
+    },
+    "gemini/gemini-2.5-flash-lite-preview-06-17": {
+        "max_tokens": 65535,
+        "max_input_tokens": 1048576,
+        "max_output_tokens": 65535,
+        "max_images_per_prompt": 3000,
+        "max_videos_per_prompt": 10,
+        "max_video_length": 1,
+        "max_audio_length_hours": 8.4,
+        "max_audio_per_prompt": 1,
+        "max_pdf_size_mb": 30,
+        "input_cost_per_audio_token": 5e-07,
+        "input_cost_per_token": 1e-07,
+        "output_cost_per_token": 4e-07,
+        "output_cost_per_reasoning_token": 4e-07,
+        "litellm_provider": "gemini",
+        "mode": "chat",
+        "rpm": 15,
+        "tpm": 250000,
+        "supports_reasoning": true,
+        "supports_system_messages": true,
+        "supports_function_calling": true,
+        "supports_vision": true,
+        "supports_response_schema": true,
+        "supports_audio_output": false,
+        "supports_tool_choice": true,
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/completions",
+            "/v1/batch"
+        ],
+        "supported_modalities": [
+            "text",
+            "image",
+            "audio",
+            "video"
+        ],
+        "supported_output_modalities": [
+            "text"
+        ],
+        "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-lite",
+        "supports_parallel_function_calling": true,
+        "supports_web_search": true,
+        "supports_url_context": true,
+        "supports_pdf_input": true
     },
     "gemini-2.5-flash-preview-05-20": {
         "max_tokens": 65535,
@@ -6979,9 +7013,9 @@
         "max_audio_per_prompt": 1,
         "max_pdf_size_mb": 30,
         "input_cost_per_audio_token": 1e-06,
-        "input_cost_per_token": 1.5e-07,
-        "output_cost_per_token": 6e-07,
-        "output_cost_per_reasoning_token": 3.5e-06,
+        "input_cost_per_token": 3e-07,
+        "output_cost_per_token": 2.5e-06,
+        "output_cost_per_reasoning_token": 2.5e-06,
         "litellm_provider": "vertex_ai-language-models",
         "mode": "chat",
         "supports_reasoning": true,
@@ -7008,7 +7042,8 @@
         "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview",
         "supports_parallel_function_calling": true,
         "supports_web_search": true,
-        "supports_url_context": true
+        "supports_url_context": true,
+        "supports_pdf_input": true
     },
     "gemini-2.5-flash-preview-04-17": {
         "max_tokens": 65535,
@@ -7049,7 +7084,8 @@
         ],
         "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview",
         "supports_parallel_function_calling": true,
-        "supports_web_search": true
+        "supports_web_search": true,
+        "supports_pdf_input": true
     },
     "gemini-2.5-flash-lite-preview-06-17": {
         "max_tokens": 65535,
@@ -7061,7 +7097,7 @@
         "max_audio_length_hours": 8.4,
         "max_audio_per_prompt": 1,
         "max_pdf_size_mb": 30,
-        "input_cost_per_audio_token": 1e-06,
+        "input_cost_per_audio_token": 5e-07,
         "input_cost_per_token": 1e-07,
         "output_cost_per_token": 4e-07,
         "output_cost_per_reasoning_token": 4e-07,
@@ -7091,7 +7127,8 @@
         "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview",
         "supports_parallel_function_calling": true,
         "supports_web_search": true,
-        "supports_url_context": true
+        "supports_url_context": true,
+        "supports_pdf_input": true
     },
     "gemini-2.0-flash": {
         "max_tokens": 8192,
@@ -7237,7 +7274,8 @@
         ],
         "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview",
         "supports_parallel_function_calling": true,
-        "supports_web_search": true
+        "supports_web_search": true,
+        "supports_pdf_input": true
     },
     "gemini-2.5-pro-preview-05-06": {
         "max_tokens": 65535,
@@ -7282,7 +7320,8 @@
         ],
         "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview",
         "supports_parallel_function_calling": true,
-        "supports_web_search": true
+        "supports_web_search": true,
+        "supports_pdf_input": true
     },
     "gemini-2.5-pro-preview-03-25": {
         "max_tokens": 65535,
@@ -7324,7 +7363,8 @@
         ],
         "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview",
         "supports_parallel_function_calling": true,
-        "supports_web_search": true
+        "supports_web_search": true,
+        "supports_pdf_input": true
     },
     "gemini-2.0-flash-preview-image-generation": {
         "max_tokens": 8192,
@@ -7649,7 +7689,8 @@
         ],
         "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-pro-preview",
         "supports_web_search": true,
-        "supports_url_context": true
+        "supports_url_context": true,
+        "supports_pdf_input": true
     },
     "gemini/gemini-2.5-pro-preview-05-06": {
         "max_tokens": 65535,
@@ -7687,7 +7728,8 @@
         ],
         "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-pro-preview",
         "supports_web_search": true,
-        "supports_url_context": true
+        "supports_url_context": true,
+        "supports_pdf_input": true
     },
     "gemini/gemini-2.5-pro-preview-03-25": {
         "max_tokens": 65535,
@@ -7724,7 +7766,8 @@
             "text"
         ],
         "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-pro-preview",
-        "supports_web_search": true
+        "supports_web_search": true,
+        "supports_pdf_input": true
     },
     "gemini/gemini-2.0-flash-exp": {
         "max_tokens": 8192,
@@ -8562,13 +8605,13 @@
         "litellm_provider": "vertex_ai-image-models",
         "mode": "image_generation",
         "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing"
-    },    
+    },
     "vertex_ai/imagen-4.0-fast-generate-preview-06-06": {
         "output_cost_per_image": 0.02,
         "litellm_provider": "vertex_ai-image-models",
         "mode": "image_generation",
         "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing"
-    },    
+    },
     "vertex_ai/imagen-3.0-generate-002": {
         "output_cost_per_image": 0.04,
         "litellm_provider": "vertex_ai-image-models",
@@ -10830,6 +10873,46 @@
         "supports_response_schema": true,
         "source": "https://aws.amazon.com/bedrock/pricing/"
     },
+    "apac.amazon.nova-micro-v1:0": {
+        "max_tokens": 10000,
+        "max_input_tokens": 300000,
+        "max_output_tokens": 10000,
+        "input_cost_per_token": 3.7e-08,
+        "output_cost_per_token": 1.48e-07,
+        "litellm_provider": "bedrock_converse",
+        "mode": "chat",
+        "supports_function_calling": true,
+        "supports_prompt_caching": true,
+        "supports_response_schema": true
+    },
+    "apac.amazon.nova-lite-v1:0": {
+        "max_tokens": 10000,
+        "max_input_tokens": 128000,
+        "max_output_tokens": 10000,
+        "input_cost_per_token": 6.3e-08,
+        "output_cost_per_token": 2.52e-07,
+        "litellm_provider": "bedrock_converse",
+        "mode": "chat",
+        "supports_function_calling": true,
+        "supports_vision": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_response_schema": true
+    },
+    "apac.amazon.nova-pro-v1:0": {
+        "max_tokens": 10000,
+        "max_input_tokens": 300000,
+        "max_output_tokens": 10000,
+        "input_cost_per_token": 8.4e-07,
+        "output_cost_per_token": 3.36e-06,
+        "litellm_provider": "bedrock_converse",
+        "mode": "chat",
+        "supports_function_calling": true,
+        "supports_vision": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_response_schema": true
+    },
     "us.amazon.nova-premier-v1:0": {
         "max_tokens": 10000,
         "max_input_tokens": 1000000,
@@ -11315,6 +11398,93 @@
         "supports_reasoning": true,
         "supports_computer_use": true
     },
+    "apac.anthropic.claude-3-haiku-20240307-v1:0": {
+        "max_tokens": 4096,
+        "max_input_tokens": 200000,
+        "max_output_tokens": 4096,
+        "input_cost_per_token": 2.5e-07,
+        "output_cost_per_token": 1.25e-06,
+        "litellm_provider": "bedrock",
+        "mode": "chat",
+        "supports_function_calling": true,
+        "supports_response_schema": true,
+        "supports_vision": true,
+        "supports_pdf_input": true,
+        "supports_tool_choice": true
+    },
+    "apac.anthropic.claude-3-sonnet-20240229-v1:0": {
+        "max_tokens": 4096,
+        "max_input_tokens": 200000,
+        "max_output_tokens": 4096,
+        "input_cost_per_token": 3e-06,
+        "output_cost_per_token": 1.5e-05,
+        "litellm_provider": "bedrock",
+        "mode": "chat",
+        "supports_function_calling": true,
+        "supports_response_schema": true,
+        "supports_vision": true,
+        "supports_pdf_input": true,
+        "supports_tool_choice": true
+    },
+    "apac.anthropic.claude-3-5-sonnet-20240620-v1:0": {
+        "max_tokens": 4096,
+        "max_input_tokens": 200000,
+        "max_output_tokens": 4096,
+        "input_cost_per_token": 3e-06,
+        "output_cost_per_token": 1.5e-05,
+        "litellm_provider": "bedrock",
+        "mode": "chat",
+        "supports_function_calling": true,
+        "supports_response_schema": true,
+        "supports_vision": true,
+        "supports_pdf_input": true,
+        "supports_tool_choice": true
+    },
+    "apac.anthropic.claude-3-5-sonnet-20241022-v2:0": {
+        "max_tokens": 8192,
+        "max_input_tokens": 200000,
+        "max_output_tokens": 8192,
+        "input_cost_per_token": 3e-06,
+        "output_cost_per_token": 1.5e-05,
+        "cache_creation_input_token_cost": 3.75e-06,
+        "cache_read_input_token_cost": 3e-07,
+        "litellm_provider": "bedrock",
+        "mode": "chat",
+        "supports_function_calling": true,
+        "supports_vision": true,
+        "supports_assistant_prefill": true,
+        "supports_computer_use": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_response_schema": true,
+        "supports_tool_choice": true
+    },
+    "apac.anthropic.claude-sonnet-4-20250514-v1:0": {
+        "max_tokens": 64000,
+        "max_input_tokens": 200000,
+        "max_output_tokens": 64000,
+        "input_cost_per_token": 3e-06,
+        "output_cost_per_token": 1.5e-05,
+        "search_context_cost_per_query": {
+            "search_context_size_low": 0.01,
+            "search_context_size_medium": 0.01,
+            "search_context_size_high": 0.01
+        },
+        "cache_creation_input_token_cost": 3.75e-06,
+        "cache_read_input_token_cost": 3e-07,
+        "litellm_provider": "bedrock_converse",
+        "mode": "chat",
+        "supports_function_calling": true,
+        "supports_vision": true,
+        "tool_use_system_prompt_tokens": 159,
+        "supports_assistant_prefill": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_response_schema": true,
+        "supports_tool_choice": true,
+        "supports_reasoning": true,
+        "supports_computer_use": true
+    },
     "eu.anthropic.claude-3-5-haiku-20241022-v1:0": {
         "max_tokens": 8192,
         "max_input_tokens": 200000,
@@ -14770,7 +14940,7 @@
     },
     "deepgram/nova-3": {
         "mode": "audio_transcription",
-        "input_cost_per_second": 0.00007167,
+        "input_cost_per_second": 7.167e-05,
         "output_cost_per_second": 0.0,
         "litellm_provider": "deepgram",
         "supported_endpoints": [
@@ -14784,7 +14954,7 @@
     },
     "deepgram/nova-3-general": {
         "mode": "audio_transcription",
-        "input_cost_per_second": 0.00007167,
+        "input_cost_per_second": 7.167e-05,
         "output_cost_per_second": 0.0,
         "litellm_provider": "deepgram",
         "supported_endpoints": [
@@ -14798,7 +14968,7 @@
     },
     "deepgram/nova-3-medical": {
         "mode": "audio_transcription",
-        "input_cost_per_second": 0.00008667,
+        "input_cost_per_second": 8.667e-05,
         "output_cost_per_second": 0.0,
         "litellm_provider": "deepgram",
         "supported_endpoints": [
@@ -14812,7 +14982,7 @@
     },
     "deepgram/nova-2": {
         "mode": "audio_transcription",
-        "input_cost_per_second": 0.00007167,
+        "input_cost_per_second": 7.167e-05,
         "output_cost_per_second": 0.0,
         "litellm_provider": "deepgram",
         "supported_endpoints": [
@@ -14826,7 +14996,7 @@
     },
     "deepgram/nova-2-general": {
         "mode": "audio_transcription",
-        "input_cost_per_second": 0.00007167,
+        "input_cost_per_second": 7.167e-05,
         "output_cost_per_second": 0.0,
         "litellm_provider": "deepgram",
         "supported_endpoints": [
@@ -14840,7 +15010,7 @@
     },
     "deepgram/nova-2-meeting": {
         "mode": "audio_transcription",
-        "input_cost_per_second": 0.00007167,
+        "input_cost_per_second": 7.167e-05,
         "output_cost_per_second": 0.0,
         "litellm_provider": "deepgram",
         "supported_endpoints": [
@@ -14854,7 +15024,7 @@
     },
     "deepgram/nova-2-phonecall": {
         "mode": "audio_transcription",
-        "input_cost_per_second": 0.00007167,
+        "input_cost_per_second": 7.167e-05,
         "output_cost_per_second": 0.0,
         "litellm_provider": "deepgram",
         "supported_endpoints": [
@@ -14868,7 +15038,7 @@
     },
     "deepgram/nova-2-voicemail": {
         "mode": "audio_transcription",
-        "input_cost_per_second": 0.00007167,
+        "input_cost_per_second": 7.167e-05,
         "output_cost_per_second": 0.0,
         "litellm_provider": "deepgram",
         "supported_endpoints": [
@@ -14882,7 +15052,7 @@
     },
     "deepgram/nova-2-finance": {
         "mode": "audio_transcription",
-        "input_cost_per_second": 0.00007167,
+        "input_cost_per_second": 7.167e-05,
         "output_cost_per_second": 0.0,
         "litellm_provider": "deepgram",
         "supported_endpoints": [
@@ -14896,7 +15066,7 @@
     },
     "deepgram/nova-2-conversationalai": {
         "mode": "audio_transcription",
-        "input_cost_per_second": 0.00007167,
+        "input_cost_per_second": 7.167e-05,
         "output_cost_per_second": 0.0,
         "litellm_provider": "deepgram",
         "supported_endpoints": [
@@ -14910,7 +15080,7 @@
     },
     "deepgram/nova-2-video": {
         "mode": "audio_transcription",
-        "input_cost_per_second": 0.00007167,
+        "input_cost_per_second": 7.167e-05,
         "output_cost_per_second": 0.0,
         "litellm_provider": "deepgram",
         "supported_endpoints": [
@@ -14924,7 +15094,7 @@
     },
     "deepgram/nova-2-drivethru": {
         "mode": "audio_transcription",
-        "input_cost_per_second": 0.00007167,
+        "input_cost_per_second": 7.167e-05,
         "output_cost_per_second": 0.0,
         "litellm_provider": "deepgram",
         "supported_endpoints": [
@@ -14938,7 +15108,7 @@
     },
     "deepgram/nova-2-automotive": {
         "mode": "audio_transcription",
-        "input_cost_per_second": 0.00007167,
+        "input_cost_per_second": 7.167e-05,
         "output_cost_per_second": 0.0,
         "litellm_provider": "deepgram",
         "supported_endpoints": [
@@ -14952,7 +15122,7 @@
     },
     "deepgram/nova-2-atc": {
         "mode": "audio_transcription",
-        "input_cost_per_second": 0.00007167,
+        "input_cost_per_second": 7.167e-05,
         "output_cost_per_second": 0.0,
         "litellm_provider": "deepgram",
         "supported_endpoints": [
@@ -14966,7 +15136,7 @@
     },
     "deepgram/nova": {
         "mode": "audio_transcription",
-        "input_cost_per_second": 0.00007167,
+        "input_cost_per_second": 7.167e-05,
         "output_cost_per_second": 0.0,
         "litellm_provider": "deepgram",
         "supported_endpoints": [
@@ -14980,7 +15150,7 @@
     },
     "deepgram/nova-general": {
         "mode": "audio_transcription",
-        "input_cost_per_second": 0.00007167,
+        "input_cost_per_second": 7.167e-05,
         "output_cost_per_second": 0.0,
         "litellm_provider": "deepgram",
         "supported_endpoints": [
@@ -14994,7 +15164,7 @@
     },
     "deepgram/nova-phonecall": {
         "mode": "audio_transcription",
-        "input_cost_per_second": 0.00007167,
+        "input_cost_per_second": 7.167e-05,
         "output_cost_per_second": 0.0,
         "litellm_provider": "deepgram",
         "supported_endpoints": [
@@ -15266,4 +15436,4 @@
             "notes": "Deepgram's hosted OpenAI Whisper models - pricing may differ from native Deepgram models"
         }
     }
-}
+}

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "litellm"
-version = "1.72.7"
+version = "1.72.9"
 description = "Library to easily interface with LLM API providers"
 authors = ["BerriAI"]
 license = "MIT"
@@ -141,7 +141,7 @@ requires = ["poetry-core", "wheel"]
 build-backend = "poetry.core.masonry.api"
 
 [tool.commitizen]
-version = "1.72.7"
+version = "1.72.9"
 version_files = [
     "pyproject.toml:^version"
 ]

requirements.txt

@@ -1,7 +1,7 @@
 # LITELLM PROXY DEPENDENCIES #
 anyio==4.5.0 # openai + http req.
 httpx==0.27.0 # Pin Httpx dependency
-openai==1.81.0  # openai req. 
+openai==1.81.0  # openai req.
 fastapi==0.115.5 # server dep
 backoff==2.2.1 # server dep
 pyyaml==6.0.2 # server dep
@@ -14,7 +14,7 @@ prisma==0.11.0 # for db
 mangum==0.17.0 # for aws lambda functions
 pynacl==1.5.0 # for encrypting keys
 google-cloud-aiplatform==1.47.0 # for vertex ai calls
-anthropic[vertex]==0.21.3
+anthropic[vertex]==0.54.0
 mcp==1.9.3    # for MCP server
 google-generativeai==0.5.0 # for vertex ai calls
 async_generator==1.10.0 # for async ollama calls
@@ -22,7 +22,7 @@ langfuse==2.45.0 # for langfuse self-hosted logging
 prometheus_client==0.20.0 # for /metrics endpoint on proxy
 ddtrace==2.19.0      # for advanced DD tracing / profiling
 orjson==3.10.12 # fast /embedding responses
-apscheduler==3.10.4 # for resetting budget in background 
+apscheduler==3.10.4 # for resetting budget in background
 fastapi-sso==0.16.0 # admin UI, SSO
 pyjwt[crypto]==2.9.0
 python-multipart==0.0.18 # admin UI
@@ -39,12 +39,12 @@ cryptography==43.0.1
 tzdata==2025.1 # IANA time zone database
 litellm-proxy-extras==0.2.5 # for proxy extras - e.g. prisma migrations
 ### LITELLM PACKAGE DEPENDENCIES
-python-dotenv==1.0.0 # for env 
+python-dotenv==1.0.0 # for env
 tiktoken==0.8.0 # for calculating usage
 importlib-metadata==6.8.0 # for random utils
 tokenizers==0.20.2 # for calculating usage
-click==8.1.7 # for proxy cli 
-rich==13.7.1 # for litellm proxy cli 
+click==8.1.7 # for proxy cli
+rich==13.7.1 # for litellm proxy cli
 jinja2==3.1.6 # for prompt templates
 aiohttp==3.10.2 # for network calls
 aioboto3==12.3.0 # for async sagemaker calls

test_script.py

@@ -4,10 +4,21 @@ import json
 gemini_model_cost_map = json.load(open("model_prices_and_context_window.json"))
 
 for model, model_info in gemini_model_cost_map.items():
-    if model_info.get("litellm_provider") == "gemini" and model_info.get("mode") == "chat" and "gemini-2" in model:
+    if (
+        (
+            model_info.get("litellm_provider") == "gemini"
+            or model_info.get("litellm_provider") == "vertex_ai-language-models"
+        )
+        and model_info.get("mode") == "chat"
+        and ("gemini-2.5" in model and "tts" not in model)
+        and model_info.get("supports_pdf_input") is None
+    ):
         """
-        Update all gemini chat models to support web search
+        Update all gemini chat models to support pdf input
         """
-        model_info["supports_web_search"] = True
+        model_info["supports_pdf_input"] = True
+        print(f"Updated {model} to support pdf input")
 
-json.dump(gemini_model_cost_map, open("model_prices_and_context_window.json", "w"), indent=4)
+json.dump(
+    gemini_model_cost_map, open("model_prices_and_context_window.json", "w"), indent=4
+)

tests/llm_responses_api_testing/test_google_ai_studio_responses_api.py

@@ -0,0 +1,94 @@
+import os
+import sys
+import pytest
+from unittest.mock import patch, AsyncMock
+sys.path.insert(0, os.path.abspath("../.."))
+import litellm
+import json
+
+@pytest.mark.asyncio
+async def test_basic_google_ai_studio_responses_api_with_tools():
+    litellm._turn_on_debug()
+    litellm.set_verbose = True
+    request_model = "gemini/gemini-2.5-flash"
+    response = await litellm.aresponses(
+        model=request_model,
+        input="what is the latest version of supabase python package and when was it released?",
+        tools=[
+            {
+                "type": "web_search_preview",
+                "search_context_size": "low"
+            }
+        ]
+    )
+    print("litellm response=", json.dumps(response, indent=4, default=str))
+
+
+@pytest.mark.asyncio
+async def test_mock_basic_google_ai_studio_responses_api_with_tools():
+    """
+    - Ensure that this is the request that litellm.completion gets when we pass web search options 
+
+    litellm.acompletion(messages=[{'role': 'user', 'content': 'what is the latest version of supabase python package and when was it released?'}], model='gemini-2.5-flash', tools=[], web_search_options={'search_context_size': 'low', 'user_location': None})
+    """
+    # Mock the acompletion function
+    litellm._turn_on_debug()
+    mock_response = litellm.ModelResponse(
+        id="test-id",
+        created=1234567890,
+        model="gemini/gemini-2.5-flash",
+        object="chat.completion",
+        choices=[
+            litellm.utils.Choices(
+                index=0,
+                message=litellm.utils.Message(
+                    role="assistant",
+                    content="Test response"
+                ),
+                finish_reason="stop"
+            )
+        ]
+    )
+    
+    with patch('litellm.acompletion', new_callable=AsyncMock) as mock_acompletion:
+        mock_acompletion.return_value = mock_response
+        
+        request_model = "gemini/gemini-2.5-flash"
+        await litellm.aresponses(
+            model=request_model,
+            input="what is the latest version of supabase python package and when was it released?",
+            tools=[
+                {
+                    "type": "web_search_preview",
+                    "search_context_size": "low"
+                }
+            ]
+        )
+        
+        # Verify that acompletion was called
+        assert mock_acompletion.called
+        
+        # Get the call arguments
+        call_args, call_kwargs = mock_acompletion.call_args
+        
+        # Verify the expected parameters were passed
+        print("call kwargs to litellm.completion=", json.dumps(call_kwargs, indent=4, default=str))
+        assert "web_search_options" in call_kwargs
+        assert call_kwargs["web_search_options"] is not None
+        assert call_kwargs["web_search_options"]["search_context_size"] == "low"
+        assert call_kwargs["web_search_options"]["user_location"] is None
+        
+        # Verify other expected parameters
+        assert call_kwargs["model"] == "gemini-2.5-flash"
+        assert len(call_kwargs["messages"]) == 1
+        assert call_kwargs["messages"][0]["role"] == "user"
+        assert call_kwargs["messages"][0]["content"] == "what is the latest version of supabase python package and when was it released?"
+        assert call_kwargs["tools"] == []  # web search tools are converted to web_search_options, not kept as tools
+
+
+    
+
+
+    
+
+

tests/llm_translation/test_mistral_api.py

@@ -35,4 +35,4 @@ class TestMistralCompletion(BaseLLMChatTest):
 
     def test_tool_call_no_arguments(self, tool_call_no_arguments):
         """Test that tool calls with no arguments is translated correctly. Relevant issue: https://github.com/BerriAI/litellm/issues/6833"""
-        pass
+        pass

tests/logging_callback_tests/test_prometheus_unit_tests.py

@@ -219,7 +219,14 @@ def test_increment_token_metrics(prometheus_logger):
     )
 
     prometheus_logger.litellm_tokens_metric.labels.assert_called_once_with(
-        end_user=None, user=None, hashed_api_key='test_hash', api_key_alias='test_alias', team='test_team', team_alias='test_team_alias', requested_model=None, model='gpt-3.5-turbo'
+        end_user=None,
+        user=None,
+        hashed_api_key="test_hash",
+        api_key_alias="test_alias",
+        team="test_team",
+        team_alias="test_team_alias",
+        requested_model=None,
+        model="gpt-3.5-turbo",
     )
     prometheus_logger.litellm_tokens_metric.labels().inc.assert_called_once_with(100)
 
@@ -836,12 +843,12 @@ def test_set_llm_deployment_success_metrics(prometheus_logger):
 
     # Verify remaining requests metric
     prometheus_logger.litellm_remaining_requests_metric.labels.assert_called_once_with(
-        api_base="https://api.openai.com",
-        api_key_alias=standard_logging_payload["metadata"]["user_api_key_alias"],
-        api_provider="openai",
+        model_group="my_custom_model_group",  # model_group / requested model from create_standard_logging_payload()
+        api_provider="openai",  # llm provider
+        api_base="https://api.openai.com",  # api base
+        litellm_model_name="gpt-3.5-turbo",  # actual model used - litellm model name
         hashed_api_key=standard_logging_payload["metadata"]["user_api_key_hash"],
-        litellm_model_name="gpt-3.5-turbo",
-        requested_model="my_custom_model_group",
+        api_key_alias=standard_logging_payload["metadata"]["user_api_key_alias"],
     )
 
     prometheus_logger.litellm_remaining_requests_metric.labels().set.assert_called_once_with(
@@ -855,7 +862,7 @@ def test_set_llm_deployment_success_metrics(prometheus_logger):
         api_provider="openai",
         hashed_api_key=standard_logging_payload["metadata"]["user_api_key_hash"],
         litellm_model_name="gpt-3.5-turbo",
-        requested_model="my_custom_model_group",
+        model_group="my_custom_model_group",
     )
 
     prometheus_logger.litellm_remaining_tokens_metric.labels().set.assert_called_once_with(
@@ -915,7 +922,7 @@ def test_set_llm_deployment_success_metrics(prometheus_logger):
         api_provider="openai",
         hashed_api_key=standard_logging_payload["metadata"]["user_api_key_hash"],
         litellm_model_name="gpt-3.5-turbo",
-        requested_model="my_custom_model_group",
+        model_group="my_custom_model_group",
     )
 
     # Calculate expected latency per token (1 second / 10 tokens = 0.1 seconds per token)
@@ -1499,60 +1506,66 @@ def test_get_exception_class_name(prometheus_logger):
     """
     # Test case 1: Exception with llm_provider
     rate_limit_error = litellm.RateLimitError(
-        message="Rate limit exceeded",
-        llm_provider="openai",
-        model="gpt-3.5-turbo"
+        message="Rate limit exceeded", llm_provider="openai", model="gpt-3.5-turbo"
+    )
+    assert (
+        prometheus_logger._get_exception_class_name(rate_limit_error)
+        == "Openai.RateLimitError"
     )
-    assert prometheus_logger._get_exception_class_name(rate_limit_error) == "Openai.RateLimitError"
 
     # Test case 2: Exception with empty llm_provider
     auth_error = litellm.AuthenticationError(
-        message="Invalid API key",
-        llm_provider="",
-        model="gpt-4"
+        message="Invalid API key", llm_provider="", model="gpt-4"
+    )
+    assert (
+        prometheus_logger._get_exception_class_name(auth_error) == "AuthenticationError"
     )
-    assert prometheus_logger._get_exception_class_name(auth_error) == "AuthenticationError"
 
     # Test case 3: Exception with None llm_provider
     context_window_error = litellm.ContextWindowExceededError(
-        message="Context length exceeded",
-        llm_provider=None,
-        model="gpt-4"
+        message="Context length exceeded", llm_provider=None, model="gpt-4"
+    )
+    assert (
+        prometheus_logger._get_exception_class_name(context_window_error)
+        == "ContextWindowExceededError"
     )
-    assert prometheus_logger._get_exception_class_name(context_window_error) == "ContextWindowExceededError"
 
 
 def test_set_llm_deployment_success_metrics_with_label_filtering():
     """
-    Test that set_llm_deployment_success_metrics correctly uses prometheus_label_factory 
+    Test that set_llm_deployment_success_metrics correctly uses prometheus_label_factory
     and respects label filtering configuration to prevent "Incorrect label names" errors.
     """
     from litellm.types.integrations.prometheus import PrometheusMetricsConfig
-    
+
     # Create a prometheus logger with label filtering configuration
     config = [
         PrometheusMetricsConfig(
             group="test_group",
             metrics=[
                 "litellm_overhead_latency_metric",
-                "litellm_remaining_requests_metric", 
+                "litellm_remaining_requests_metric",
                 "litellm_remaining_tokens_metric",
                 "litellm_deployment_success_responses",
-                "litellm_deployment_total_requests"
+                "litellm_deployment_total_requests",
             ],
-            include_labels=["requested_model", "api_provider", "hashed_api_key"]  # Limited labels
+            include_labels=[
+                "requested_model",
+                "api_provider",
+                "hashed_api_key",
+            ],  # Limited labels
         )
     ]
-    
+
     # Mock litellm.prometheus_metrics_config
-    with patch('litellm.prometheus_metrics_config', config):
+    with patch("litellm.prometheus_metrics_config", config):
         # Clear registry before creating new logger
         collectors = list(REGISTRY._collector_to_names.keys())
         for collector in collectors:
             REGISTRY.unregister(collector)
-            
+
         prometheus_logger = PrometheusLogger()
-        
+
         # Mock all the metrics used in the method
         prometheus_logger.litellm_overhead_latency_metric = MagicMock()
         prometheus_logger.litellm_remaining_requests_metric = MagicMock()
@@ -1607,46 +1620,59 @@ def test_set_llm_deployment_success_metrics_with_label_filtering():
 
         # Verify that metrics were called with filtered labels (only the configured ones)
         # The exact labels depend on what get_labels_for_metric returns for each metric
-        
+
         # Verify overhead latency metric was called with filtered labels
         prometheus_logger.litellm_overhead_latency_metric.labels.assert_called_once()
-        overhead_labels = prometheus_logger.litellm_overhead_latency_metric.labels.call_args[1]
-        
+        overhead_labels = (
+            prometheus_logger.litellm_overhead_latency_metric.labels.call_args[1]
+        )
+
         # Should only contain the filtered labels that are supported for this metric
         expected_filtered_labels = {"requested_model", "api_provider", "hashed_api_key"}
         actual_labels = set(k for k in overhead_labels.keys() if k is not None)
-        
+
         # Verify that only expected labels are present (subset of configured labels)
         assert actual_labels <= expected_filtered_labels
-        
-        # Verify remaining requests metric was called with filtered labels  
+
+        # Verify remaining requests metric was called with filtered labels
         prometheus_logger.litellm_remaining_requests_metric.labels.assert_called_once()
-        requests_labels = prometheus_logger.litellm_remaining_requests_metric.labels.call_args[1]
+        requests_labels = (
+            prometheus_logger.litellm_remaining_requests_metric.labels.call_args[1]
+        )
         actual_labels = set(k for k in requests_labels.keys() if k is not None)
         assert actual_labels <= expected_filtered_labels
-        
+
         # Verify remaining tokens metric was called with filtered labels
         prometheus_logger.litellm_remaining_tokens_metric.labels.assert_called_once()
-        tokens_labels = prometheus_logger.litellm_remaining_tokens_metric.labels.call_args[1]
+        tokens_labels = (
+            prometheus_logger.litellm_remaining_tokens_metric.labels.call_args[1]
+        )
         actual_labels = set(k for k in tokens_labels.keys() if k is not None)
         assert actual_labels <= expected_filtered_labels
-        
+
         # Verify deployment success responses metric was called with filtered labels
         prometheus_logger.litellm_deployment_success_responses.labels.assert_called_once()
-        success_labels = prometheus_logger.litellm_deployment_success_responses.labels.call_args[1]
+        success_labels = (
+            prometheus_logger.litellm_deployment_success_responses.labels.call_args[1]
+        )
         actual_labels = set(k for k in success_labels.keys() if k is not None)
         assert actual_labels <= expected_filtered_labels
-        
+
         # Verify deployment total requests metric was called with filtered labels
         prometheus_logger.litellm_deployment_total_requests.labels.assert_called_once()
-        total_labels = prometheus_logger.litellm_deployment_total_requests.labels.call_args[1]
+        total_labels = (
+            prometheus_logger.litellm_deployment_total_requests.labels.call_args[1]
+        )
         actual_labels = set(total_labels.keys())
         assert actual_labels.issubset(expected_filtered_labels.union({None}))
-        
+
         # Verify all metrics were actually called (no exceptions were raised)
         prometheus_logger.litellm_overhead_latency_metric.labels().observe.assert_called_once()
-        prometheus_logger.litellm_remaining_requests_metric.labels().set.assert_called_once_with(123)
-        prometheus_logger.litellm_remaining_tokens_metric.labels().set.assert_called_once_with(4321)
+        prometheus_logger.litellm_remaining_requests_metric.labels().set.assert_called_once_with(
+            123
+        )
+        prometheus_logger.litellm_remaining_tokens_metric.labels().set.assert_called_once_with(
+            4321
+        )
         prometheus_logger.litellm_deployment_success_responses.labels().inc.assert_called_once()
         prometheus_logger.litellm_deployment_total_requests.labels().inc.assert_called_once()
-

tests/mcp_tests/test_mcp_client_unit.py

@@ -0,0 +1,169 @@
+"""
+Unit tests for the MCPClient class - critical functionality only.
+"""
+import base64
+import os
+import sys
+import pytest
+from unittest.mock import AsyncMock, MagicMock, patch
+
+# Add the project root to the path
+sys.path.insert(0, os.path.abspath("../../.."))
+
+from litellm.experimental_mcp_client.client import MCPClient
+from litellm.types.mcp import MCPAuth, MCPTransport
+from mcp.types import Tool as MCPTool, CallToolResult as MCPCallToolResult
+
+
+class TestMCPClientUnitTests:
+    """Unit tests for MCPClient functionality."""
+    
+    def test_init_with_auth(self):
+        """Test initialization with authentication."""
+        client = MCPClient(
+            server_url="http://example.com",
+            transport_type=MCPTransport.sse,
+            auth_type=MCPAuth.bearer_token,
+            auth_value="test_token",
+            timeout=30.0
+        )
+        assert client.server_url == "http://example.com"
+        assert client.transport_type == MCPTransport.sse
+        assert client.auth_type == MCPAuth.bearer_token
+        assert client.timeout == 30.0
+        assert client._mcp_auth_value == "test_token"
+    
+    def test_get_auth_headers(self):
+        """Test authentication header generation for different auth types."""
+        # Bearer token
+        client = MCPClient(
+            "http://example.com", 
+            auth_type=MCPAuth.bearer_token,
+            auth_value="test_token"
+        )
+        headers = client._get_auth_headers()
+        assert headers == {"Authorization": "Bearer test_token"}
+        
+        # Basic auth
+        client = MCPClient(
+            "http://example.com",
+            auth_type=MCPAuth.basic,
+            auth_value="user:pass"
+        )
+        expected_encoded = base64.b64encode("user:pass".encode("utf-8")).decode()
+        headers = client._get_auth_headers()
+        assert headers == {"Authorization": f"Basic {expected_encoded}"}
+        
+        # API key
+        client = MCPClient(
+            "http://example.com",
+            auth_type=MCPAuth.api_key,
+            auth_value="api_key_123"
+        )
+        headers = client._get_auth_headers()
+        assert headers == {"X-API-Key": "api_key_123"}
+    
+    @pytest.mark.asyncio
+    @patch('litellm.experimental_mcp_client.client.streamablehttp_client')
+    @patch('litellm.experimental_mcp_client.client.ClientSession')
+    async def test_connect(self, mock_session_class, mock_transport):
+        """Test connecting to MCP server with authentication."""
+        # Setup mocks
+        mock_transport_ctx = AsyncMock()
+        mock_transport.return_value = mock_transport_ctx
+        mock_transport_instance = MagicMock()
+        mock_transport_ctx.__aenter__ = AsyncMock(return_value=mock_transport_instance)
+        
+        mock_session_ctx = AsyncMock()
+        mock_session_class.return_value = mock_session_ctx
+        mock_session_instance = AsyncMock()
+        mock_session_ctx.__aenter__ = AsyncMock(return_value=mock_session_instance)
+        
+        client = MCPClient(
+            "http://example.com",
+            auth_type=MCPAuth.bearer_token,
+            auth_value="test_token"
+        )
+        await client.connect()
+        
+        # Verify transport was created with auth headers
+        call_args = mock_transport.call_args
+        assert call_args[1]['headers'] == {"Authorization": "Bearer test_token"}
+        
+        # Verify session was initialized
+        mock_session_instance.initialize.assert_called_once()
+        assert client._session == mock_session_instance
+    
+    @pytest.mark.asyncio
+    @patch('litellm.experimental_mcp_client.client.streamablehttp_client')
+    @patch('litellm.experimental_mcp_client.client.ClientSession')
+    async def test_list_tools(self, mock_session_class, mock_transport):
+        """Test listing tools from the server."""
+        # Setup mocks
+        mock_transport_ctx = AsyncMock()
+        mock_transport.return_value = mock_transport_ctx
+        mock_transport_instance = MagicMock()
+        mock_transport_ctx.__aenter__ = AsyncMock(return_value=mock_transport_instance)
+        
+        mock_session_ctx = AsyncMock()
+        mock_session_class.return_value = mock_session_ctx
+        mock_session_instance = AsyncMock()
+        mock_session_ctx.__aenter__ = AsyncMock(return_value=mock_session_instance)
+        
+        mock_tools = [
+            MCPTool(
+                name="test_tool", 
+                description="Test tool",
+                inputSchema={
+                    "type": "object",
+                    "properties": {"arg1": {"type": "string"}},
+                    "required": ["arg1"]
+                }
+            )
+        ]
+        mock_result = MagicMock()
+        mock_result.tools = mock_tools
+        mock_session_instance.list_tools.return_value = mock_result
+        
+        client = MCPClient("http://example.com")
+        result = await client.list_tools()
+        
+        assert result == mock_tools
+        mock_session_instance.initialize.assert_called_once()
+        mock_session_instance.list_tools.assert_called_once()
+    
+    @pytest.mark.asyncio
+    @patch('litellm.experimental_mcp_client.client.streamablehttp_client')
+    @patch('litellm.experimental_mcp_client.client.ClientSession')
+    async def test_call_tool(self, mock_session_class, mock_transport):
+        """Test calling a tool."""
+        from mcp.types import CallToolRequestParams
+        
+        # Setup mocks
+        mock_transport_ctx = AsyncMock()
+        mock_transport.return_value = mock_transport_ctx
+        mock_transport_instance = MagicMock()
+        mock_transport_ctx.__aenter__ = AsyncMock(return_value=mock_transport_instance)
+        
+        mock_session_ctx = AsyncMock()
+        mock_session_class.return_value = mock_session_ctx
+        mock_session_instance = AsyncMock()
+        mock_session_ctx.__aenter__ = AsyncMock(return_value=mock_session_instance)
+        
+        mock_result = MCPCallToolResult(content=[])
+        mock_session_instance.call_tool.return_value = mock_result
+        
+        client = MCPClient("http://example.com")
+        params = CallToolRequestParams(name="test_tool", arguments={"arg1": "value1"})
+        result = await client.call_tool(params)
+        
+        assert result == mock_result
+        mock_session_instance.initialize.assert_called_once()
+        mock_session_instance.call_tool.assert_called_once_with(
+            name="test_tool", 
+            arguments={"arg1": "value1"}
+        )
+
+
+if __name__ == "__main__":
+    pytest.main([__file__, "-v"]) 

tests/mcp_tests/test_mcp_server.py

@@ -101,26 +101,17 @@ async def test_mcp_http_transport_list_tools_mock():
         )
     ]
     
-    # Mock the session and its methods
-    mock_session = AsyncMock()
-    mock_session.initialize = AsyncMock()
-    mock_session.list_tools = AsyncMock(return_value=ListToolsResult(tools=mock_tools))
+    # Create a mock MCPClient that returns our test tools
+    mock_client = AsyncMock()
+    mock_client.list_tools = AsyncMock(return_value=mock_tools)
+    mock_client.__aenter__ = AsyncMock(return_value=mock_client)
+    mock_client.__aexit__ = AsyncMock(return_value=None)
     
-    # Create an async context manager mock for streamablehttp_client
-    @asynccontextmanager
-    async def mock_streamablehttp_client(url):
-        read_stream = AsyncMock()
-        write_stream = AsyncMock()
-        get_session_id = MagicMock(return_value="test-session-123")
-        yield (read_stream, write_stream, get_session_id)
+    # Mock the MCPClient constructor to return our mock
+    def mock_client_constructor(*args, **kwargs):
+        return mock_client
     
-    # Create an async context manager mock for ClientSession
-    @asynccontextmanager
-    async def mock_client_session(read_stream, write_stream):
-        yield mock_session
-    
-    with patch('litellm.proxy._experimental.mcp_server.mcp_server_manager.streamablehttp_client', mock_streamablehttp_client), \
-         patch('litellm.proxy._experimental.mcp_server.mcp_server_manager.ClientSession', mock_client_session):
+    with patch('litellm.proxy._experimental.mcp_server.mcp_server_manager.MCPClient', mock_client_constructor):
         
         # Load server config with HTTP transport
         test_manager.load_servers_from_config({
@@ -139,9 +130,9 @@ async def test_mcp_http_transport_list_tools_mock():
         assert tools[0].name == "gmail_send_email"
         assert tools[1].name == "calendar_create_event"
         
-        # Verify session methods were called
-        mock_session.initialize.assert_called_once()
-        mock_session.list_tools.assert_called_once()
+        # Verify client methods were called
+        mock_client.__aenter__.assert_called()
+        mock_client.list_tools.assert_called_once()
         
         # Verify tool mapping was updated
         assert test_manager.tool_name_to_mcp_server_name_mapping["gmail_send_email"] == "test_http_server"
@@ -166,26 +157,17 @@ async def test_mcp_http_transport_call_tool_mock():
         isError=False
     )
     
-    # Mock the session and its methods
-    mock_session = AsyncMock()
-    mock_session.initialize = AsyncMock()
-    mock_session.call_tool = AsyncMock(return_value=mock_result)
+    # Create a mock MCPClient that returns our test result
+    mock_client = AsyncMock()
+    mock_client.call_tool = AsyncMock(return_value=mock_result)
+    mock_client.__aenter__ = AsyncMock(return_value=mock_client)
+    mock_client.__aexit__ = AsyncMock(return_value=None)
     
-    # Create an async context manager mock for streamablehttp_client
-    @asynccontextmanager
-    async def mock_streamablehttp_client(url):
-        read_stream = AsyncMock()
-        write_stream = AsyncMock()
-        get_session_id = MagicMock(return_value="test-session-456")
-        yield (read_stream, write_stream, get_session_id)
+    # Mock the MCPClient constructor to return our mock
+    def mock_client_constructor(*args, **kwargs):
+        return mock_client
     
-    # Create an async context manager mock for ClientSession
-    @asynccontextmanager
-    async def mock_client_session(read_stream, write_stream):
-        yield mock_session
-    
-    with patch('litellm.proxy._experimental.mcp_server.mcp_server_manager.streamablehttp_client', mock_streamablehttp_client), \
-         patch('litellm.proxy._experimental.mcp_server.mcp_server_manager.ClientSession', mock_client_session):
+    with patch('litellm.proxy._experimental.mcp_server.mcp_server_manager.MCPClient', mock_client_constructor):
         
         # Load server config with HTTP transport
         test_manager.load_servers_from_config({
@@ -216,16 +198,9 @@ async def test_mcp_http_transport_call_tool_mock():
         assert isinstance(result.content[0], TextContent)
         assert result.content[0].text == "Email sent successfully to test@example.com"
         
-        # Verify session methods were called
-        mock_session.initialize.assert_called_once()
-        mock_session.call_tool.assert_called_once_with(
-            "gmail_send_email",
-            {
-                "to": "test@example.com", 
-                "subject": "Test Subject",
-                "body": "Test email body"
-            }
-        )
+        # Verify client methods were called
+        mock_client.__aenter__.assert_called()
+        mock_client.call_tool.assert_called_once()
 
 
 @pytest.mark.asyncio
@@ -246,26 +221,17 @@ async def test_mcp_http_transport_call_tool_error_mock():
         isError=True
     )
     
-    # Mock the session and its methods
-    mock_session = AsyncMock()
-    mock_session.initialize = AsyncMock()
-    mock_session.call_tool = AsyncMock(return_value=mock_error_result)
+    # Create a mock MCPClient that returns our test error result
+    mock_client = AsyncMock()
+    mock_client.call_tool = AsyncMock(return_value=mock_error_result)
+    mock_client.__aenter__ = AsyncMock(return_value=mock_client)
+    mock_client.__aexit__ = AsyncMock(return_value=None)
     
-    # Create an async context manager mock for streamablehttp_client
-    @asynccontextmanager
-    async def mock_streamablehttp_client(url):
-        read_stream = AsyncMock()
-        write_stream = AsyncMock()
-        get_session_id = MagicMock(return_value="test-session-789")
-        yield (read_stream, write_stream, get_session_id)
+    # Mock the MCPClient constructor to return our mock
+    def mock_client_constructor(*args, **kwargs):
+        return mock_client
     
-    # Create an async context manager mock for ClientSession
-    @asynccontextmanager
-    async def mock_client_session(read_stream, write_stream):
-        yield mock_session
-    
-    with patch('litellm.proxy._experimental.mcp_server.mcp_server_manager.streamablehttp_client', mock_streamablehttp_client), \
-         patch('litellm.proxy._experimental.mcp_server.mcp_server_manager.ClientSession', mock_client_session):
+    with patch('litellm.proxy._experimental.mcp_server.mcp_server_manager.MCPClient', mock_client_constructor):
         
         # Load server config with HTTP transport
         test_manager.load_servers_from_config({
@@ -292,9 +258,9 @@ async def test_mcp_http_transport_call_tool_error_mock():
         assert isinstance(result.content[0], TextContent)
         assert "Error: Invalid email address" in result.content[0].text
         
-        # Verify session methods were called
-        mock_session.initialize.assert_called_once()
-        mock_session.call_tool.assert_called_once()
+        # Verify client methods were called
+        mock_client.__aenter__.assert_called()
+        mock_client.call_tool.assert_called_once()
 
 
 @pytest.mark.asyncio

tests/test_litellm/integrations/test_langfuse_otel.py

@@ -1,6 +1,8 @@
 import os
+from unittest.mock import MagicMock, patch
+
 import pytest
-from unittest.mock import patch, MagicMock
+
 from litellm.integrations.langfuse.langfuse_otel import LangfuseOtelLogger
 from litellm.types.integrations.langfuse_otel import LangfuseOtelConfig
 

tests/test_litellm/litellm_core_utils/prompt_templates/test_litellm_core_utils_prompt_templates_factory.py

@@ -308,3 +308,20 @@ def test_vertex_ai_transform_empty_function_call_arguments():
     assert result["args"] == {
         "type": "object",
     }
+
+
+@pytest.mark.asyncio
+async def test_bedrock_process_image_async_factory():
+    """
+    Test that the _process_image_async_factory method handles image input correctly
+    """
+    from litellm.litellm_core_utils.prompt_templates.factory import (
+        BedrockImageProcessor,
+    )
+
+    image_url = "data:application/pdf; qs=0.001;base64,JVBERi0xLjQKJcOkw7zDtsOfCjIgMCBvYmoKPDwvTGVuZ3RoIDMgMCBSL0ZpbHRlci9GbGF0ZURlY29kZT4"
+
+    content_block = await BedrockImageProcessor.process_image_async(
+        image_url=image_url, format=None
+    )
+    print(f"content_block: {content_block}")

tests/test_litellm/llms/anthropic/chat/test_anthropic_chat_transformation.py

@@ -218,6 +218,7 @@ def test_map_tool_choice():
     assert result["type"] == "none"
     print(result)
 
+
 def test_transform_response_with_prefix_prompt():
     import httpx
 
@@ -262,3 +263,8 @@ def test_transform_response_with_prefix_prompt():
         == "You are a helpful assistant. The grass is green."
     )
 
+
+def test_get_supported_params_thinking():
+    config = AnthropicConfig()
+    params = config.get_supported_openai_params(model="claude-sonnet-4-20250514")
+    assert "thinking" in params

tests/test_litellm/llms/bedrock/chat/invoke_transformations/test_bedrock_chat_invoke_transformations_anthropic_claude3_transformation.py

@@ -0,0 +1,22 @@
+import asyncio
+import json
+import os
+import sys
+
+import pytest
+
+# Ensure the project root is on the import path so `litellm` can be imported when
+# tests are executed from any working directory.
+sys.path.insert(0, os.path.abspath("../../../../../.."))
+
+from litellm.llms.bedrock.chat.invoke_transformations.anthropic_claude3_transformation import (
+    AmazonAnthropicClaude3Config,
+)
+
+
+def test_get_supported_params_thinking():
+    config = AmazonAnthropicClaude3Config()
+    params = config.get_supported_openai_params(
+        model="anthropic.claude-sonnet-4-20250514-v1:0"
+    )
+    assert "thinking" in params

tests/test_litellm/llms/custom_httpx/test_http_handler.py

@@ -5,6 +5,7 @@ import ssl
 import sys
 from unittest.mock import MagicMock, patch
 
+import certifi
 import httpx
 import pytest
 from aiohttp import ClientSession, TCPConnector
@@ -120,3 +121,34 @@ async def test_ssl_verification_with_aiohttp_transport():
 
     # assert both litellm transport and aiohttp session have ssl_verify=False
     assert transport_connector._ssl == aiohttp_session.connector._ssl
+
+
+def test_get_ssl_context():
+    """Test that _get_ssl_context() returns a proper SSL context with certifi CA bundle"""
+    with patch('ssl.create_default_context') as mock_create_context:
+        # Mock the return value
+        mock_ssl_context = MagicMock(spec=ssl.SSLContext)
+        mock_create_context.return_value = mock_ssl_context
+        
+        # Call the static method
+        result = AsyncHTTPHandler._get_ssl_context()
+        
+        # Verify ssl.create_default_context was called with certifi's CA file
+        expected_ca_file = certifi.where()
+        mock_create_context.assert_called_once_with(cafile=expected_ca_file)
+        
+        # Verify it returns the mocked SSL context
+        assert result == mock_ssl_context
+
+
+def test_get_ssl_context_integration():
+    """Integration test that _get_ssl_context() returns a working SSL context"""
+    # Call the static method without mocking
+    ssl_context = AsyncHTTPHandler._get_ssl_context()
+    
+    # Verify it returns an SSLContext instance
+    assert isinstance(ssl_context, ssl.SSLContext)
+    
+    # Verify it has basic SSL context properties
+    assert ssl_context.protocol is not None
+    assert ssl_context.verify_mode is not None

tests/test_litellm/llms/litellm_proxy/chat/test_litellm_proxy_chat_transformation.py

@@ -0,0 +1,32 @@
+from typing import Optional
+from unittest.mock import patch
+
+import pytest
+
+import litellm
+from litellm.llms.litellm_proxy.chat.transformation import LiteLLMProxyChatConfig
+
+
+def test_litellm_proxy_chat_transformation():
+    """
+    Assert messages are not transformed when calling litellm proxy
+    """
+    config = LiteLLMProxyChatConfig()
+    file_content = [
+        {"type": "text", "text": "What is this document about?"},
+        {
+            "type": "file",
+            "file": {
+                "file_id": "https://www.w3.org/WAI/ER/tests/xhtml/testfiles/resources/pdf/dummy.pdf",
+                "format": "application/pdf",
+            },
+        },
+    ]
+    messages = [{"role": "user", "content": file_content}]
+    assert config.transform_request(
+        model="model",
+        messages=messages,
+        optional_params={},
+        litellm_params={},
+        headers={},
+    ) == {"model": "model", "messages": messages}

tests/test_litellm/llms/meta_llama/test_meta_llama_chat_transformation.py

@@ -11,18 +11,6 @@ sys.path.insert(
 from litellm.llms.meta_llama.chat.transformation import LlamaAPIConfig
 
 
-def test_get_supported_openai_params():
-    """Test that LlamaAPIConfig correctly filters unsupported parameters"""
-    config = LlamaAPIConfig()
-
-    # Test error handling
-    with patch("litellm.get_model_info", side_effect=Exception("Test error")):
-        params = config.get_supported_openai_params("llama-3.3-8B-instruct")
-        assert "function_call" not in params
-        assert "tools" not in params
-        assert "tool_choice" not in params
-
-
 def test_map_openai_params():
     """Test that LlamaAPIConfig correctly maps OpenAI parameters"""
     config = LlamaAPIConfig()

tests/test_litellm/llms/mistral/test_mistral_chat_transformation.py

@@ -349,3 +349,67 @@ class TestMistralReasoningSupport:
         assert result["messages"][1]["content"] == "Solve for x: 2x + 5 = 13"
         assert result.get("temperature") == 0.7
         assert "_add_reasoning_prompt" not in result
+
+
+
+class TestMistralNameHandling:
+    """Test suite for Mistral name handling in messages."""
+
+    def test_handle_name_in_message_tool_role_empty_name_removes_name(self):
+        """Test that empty name is removed for tool messages."""
+        # Test with empty string
+        tool_message = {"role": "tool", "content": "Function result", "name": ""}
+        result = MistralConfig._handle_name_in_message(tool_message)
+        assert "name" not in result
+        assert result["role"] == "tool"
+        assert result["content"] == "Function result"
+
+    def test_handle_name_in_message_tool_role_valid_name_keeps_name(self):
+        """Test that valid name is kept for tool messages."""
+        # Test with normal function name
+        tool_message = {"role": "tool", "content": "Function result", "name": "get_weather"}
+        result = MistralConfig._handle_name_in_message(tool_message)
+        assert "name" in result
+        assert result["name"] == "get_weather"
+        assert result["role"] == "tool"
+        assert result["content"] == "Function result"
+
+    def test_handle_name_in_message_no_name_field(self):
+        """Test that messages without name field are unchanged."""
+        # Test with user role
+        user_message = {"role": "user", "content": "Hello"}
+        result = MistralConfig._handle_name_in_message(user_message)
+        assert "name" not in result
+        assert result["role"] == "user"
+        assert result["content"] == "Hello"
+
+
+class TestMistralParallelToolCalls:
+    """Test suite for Mistral parallel tool calls functionality."""
+
+    def test_get_supported_openai_params_includes_parallel_tool_calls(self):
+        """Test that parallel_tool_calls is in supported parameters."""
+        mistral_config = MistralConfig()
+        supported_params = mistral_config.get_supported_openai_params("mistral/mistral-large-latest")
+        assert "parallel_tool_calls" in supported_params
+
+    def test_transform_request_preserves_parallel_tool_calls(self):
+        """Test that transform_request preserves parallel_tool_calls parameter."""
+        mistral_config = MistralConfig()
+        
+        messages = [
+            {"role": "user", "content": "What's the weather like?"}
+        ]
+        optional_params = {"parallel_tool_calls": True}
+        
+        result = mistral_config.transform_request(
+            model="mistral/mistral-large-latest",
+            messages=messages,
+            optional_params=optional_params,
+            litellm_params={},
+            headers={}
+        )
+        
+        assert result.get("parallel_tool_calls") is True
+        assert len(result["messages"]) == 1
+        assert result["messages"][0]["role"] == "user"

tests/test_litellm/llms/vertex_ai/gemini/test_vertex_and_google_ai_studio_gemini.py

@@ -713,3 +713,31 @@ def test_vertex_ai_transform_parts():
     assert function["name"] == "simple_function"
     assert function["arguments"] == "{}"
     assert tools is None
+
+
+def test_vertex_ai_usage_metadata_missing_token_count():
+    """Test that missing tokenCount in responseTokensDetails defaults to 0"""
+    from litellm.types.utils import PromptTokensDetailsWrapper
+
+    v = VertexGeminiConfig()
+    usage_metadata = {
+        "promptTokenCount": 57,
+        "responseTokenCount": 74,
+        "totalTokenCount": 131,
+        "promptTokensDetails": [{"modality": "TEXT", "tokenCount": 57}],
+        "responseTokensDetails": [
+            {"modality": "TEXT"},  # Missing tokenCount
+            {"modality": "AUDIO"},  # Missing tokenCount
+        ],
+    }
+    usage_metadata = UsageMetadata(**usage_metadata)
+    result = v._calculate_usage(completion_response={"usageMetadata": usage_metadata})
+    
+    # Should not crash and should default missing tokenCount to 0
+    assert result.prompt_tokens == 57
+    assert result.completion_tokens == 74
+    assert result.total_tokens == 131
+    assert result.completion_tokens_details.text_tokens == 0  # Default value for missing tokenCount
+    assert result.completion_tokens_details.audio_tokens == 0  # Default value for missing tokenCount
+
+

tests/test_litellm/llms/vertex_ai/test_vertex_llm_base.py

@@ -243,6 +243,98 @@ class TestVertexBase:
             assert token == "refreshed-token"
             assert project == not_quota_project_id
 
+    @pytest.mark.parametrize("is_async", [True, False], ids=["async", "sync"])
+    @pytest.mark.asyncio
+    async def test_identity_pool_credentials(self, is_async):
+        vertex_base = VertexBase()
+
+        # Test case: Using Workload Identity Federation for Microsoft Azure and
+        # OIDC identity providers (default behavior)
+        credentials = {
+            "project_id": "test-project",
+            "refresh_token": "fake-refresh-token",
+            "type": "external_account",
+        }
+        mock_creds = MagicMock()
+        mock_creds.token = "token-1"
+        mock_creds.expired = False
+        mock_creds.project_id = "test-project"
+
+        with patch.object(
+            vertex_base, "_credentials_from_identity_pool", return_value=mock_creds
+        ) as mock_credentials_from_identity_pool, patch.object(
+            vertex_base, "refresh_auth"
+        ) as mock_refresh:
+
+            def mock_refresh_impl(creds):
+                creds.token = "refreshed-token"
+
+            mock_refresh.side_effect = mock_refresh_impl
+
+            if is_async:
+                token, _ = await vertex_base._ensure_access_token_async(
+                    credentials=credentials,
+                    project_id=None,
+                    custom_llm_provider="vertex_ai",
+                )
+            else:
+                token, _ = vertex_base._ensure_access_token(
+                    credentials=credentials,
+                    project_id=None,
+                    custom_llm_provider="vertex_ai",
+                )
+
+            assert mock_credentials_from_identity_pool.called
+            assert token == "refreshed-token"
+
+    @pytest.mark.parametrize("is_async", [True, False], ids=["async", "sync"])
+    @pytest.mark.asyncio
+    async def test_identity_pool_credentials_with_aws(self, is_async):
+        vertex_base = VertexBase()
+
+        # Test case: Using Workload Identity Federation for Microsoft Azure and
+        # OIDC identity providers (default behavior)
+        credentials = {
+            "project_id": "test-project",
+            "refresh_token": "fake-refresh-token",
+            "type": "external_account",
+            "credential_source": {
+                "environment_id": "aws1"
+            }
+        }
+        mock_creds = MagicMock()
+        mock_creds.token = "token-1"
+        mock_creds.expired = False
+        mock_creds.project_id = "test-project"
+
+        with patch.object(
+            vertex_base, "_credentials_from_identity_pool_with_aws", return_value=mock_creds
+        ) as mock_credentials_from_identity_pool_with_aws, patch.object(
+            vertex_base, "refresh_auth"
+        ) as mock_refresh:
+
+            def mock_refresh_impl(creds):
+                creds.token = "refreshed-token"
+
+            mock_refresh.side_effect = mock_refresh_impl
+
+            if is_async:
+                token, _ = await vertex_base._ensure_access_token_async(
+                    credentials=credentials,
+                    project_id=None,
+                    custom_llm_provider="vertex_ai",
+                )
+            else:
+                token, _ = vertex_base._ensure_access_token(
+                    credentials=credentials,
+                    project_id=None,
+                    custom_llm_provider="vertex_ai",
+                )
+
+            assert mock_credentials_from_identity_pool_with_aws.called
+            assert token == "refreshed-token"
+
+
     @pytest.mark.parametrize(
         "api_base, vertex_location, expected",
         [
@@ -270,6 +362,7 @@ class TestVertexBase:
             ),
         ],
     )
+
     def test_get_api_base(self, api_base, vertex_location, expected):
         vertex_base = VertexBase()
         assert (

tests/test_litellm/llms/vertex_ai/vertex_ai_partner_models/anthropic/test_vertex_ai_partner_models_anthropic_transformation.py

@@ -1,5 +1,5 @@
-import sys
 import os
+import sys
 
 import pytest
 
@@ -14,15 +14,21 @@ from litellm.llms.vertex_ai.vertex_ai_partner_models.anthropic.transformation im
 @pytest.mark.parametrize(
     "model, expected_thinking",
     [
-        ("claude-sonnet-4@20250514", True), 
+        ("claude-sonnet-4@20250514", True),
     ],
 )
 def test_vertex_ai_anthropic_thinking_param(model, expected_thinking):
     supported_openai_params = VertexAIAnthropicConfig().get_supported_openai_params(
-            model=model
-        )
-    
+        model=model
+    )
+
     if expected_thinking:
         assert "thinking" in supported_openai_params
     else:
         assert "thinking" not in supported_openai_params
+
+
+def test_get_supported_params_thinking():
+    config = VertexAIAnthropicConfig()
+    params = config.get_supported_openai_params(model="claude-sonnet-4")
+    assert "thinking" in params

tests/test_litellm/proxy/_experimental/mcp_server/auth/test_user_api_key_auth_mcp.py

@@ -116,17 +116,19 @@ class TestUserAPIKeyAuthMCP:
                     mock_find_unique.assert_not_called()
 
     @pytest.mark.parametrize(
-        "headers,expected_api_key",
+        "headers,expected_api_key,expected_mcp_auth_header",
         [
             # Test case 1: x-litellm-api-key header present
             (
                 [(b"x-litellm-api-key", b"test-api-key-123")],
                 "test-api-key-123",
+                None,
             ),
             # Test case 2: Authorization header present (fallback)
             (
                 [(b"authorization", b"Bearer test-auth-token")],
                 "Bearer test-auth-token",
+                None,
             ),
             # Test case 3: Both headers present (primary should win)
             (
@@ -135,22 +137,40 @@ class TestUserAPIKeyAuthMCP:
                     (b"authorization", b"Bearer fallback-token"),
                 ],
                 "primary-key",
+                None,
             ),
             # Test case 4: Case insensitive headers
             (
                 [(b"X-LITELLM-API-KEY", b"case-insensitive-key")],
                 "case-insensitive-key",
+                None,
             ),
             # Test case 5: No relevant headers
             (
                 [(b"content-type", b"application/json")],
                 "",
+                None,
             ),
             # Test case 6: Empty headers
-            ([], ""),
+            ([], "", None),
+            # Test case 7: MCP auth header present
+            (
+                [
+                    (b"x-litellm-api-key", b"test-api-key-123"),
+                    (b"x-mcp-auth", b"mcp-auth-token"),
+                ],
+                "test-api-key-123",
+                "mcp-auth-token",
+            ),
+            # Test case 8: Only MCP auth header present (no API key)
+            (
+                [(b"x-mcp-auth", b"mcp-auth-token")],
+                "",
+                "mcp-auth-token",
+            ),
         ],
     )
-    async def test_user_api_key_auth_mcp(self, headers, expected_api_key):
+    async def test_user_api_key_auth_mcp(self, headers, expected_api_key, expected_mcp_auth_header):
         """Test user_api_key_auth_mcp method with various header scenarios"""
 
         # Create ASGI scope with headers
@@ -174,10 +194,11 @@ class TestUserAPIKeyAuthMCP:
             mock_user_api_key_auth.return_value = mock_auth_result
 
             # Call the method
-            result = await UserAPIKeyAuthMCP.user_api_key_auth_mcp(scope)
+            auth_result, mcp_auth_header = await UserAPIKeyAuthMCP.user_api_key_auth_mcp(scope)
 
-            # Assert the result
-            assert result == mock_auth_result
+            # Assert the results
+            assert auth_result == mock_auth_result
+            assert mcp_auth_header == expected_mcp_auth_header
 
             # Verify user_api_key_auth was called with correct parameters
             mock_user_api_key_auth.assert_called_once()

tests/test_litellm/proxy/management_endpoints/test_mcp_management_endpoints.py

@@ -18,11 +18,11 @@ from typing import Optional
 from litellm.proxy._types import (
     LiteLLM_MCPServerTable,
     LitellmUserRoles,
-    MCPAuth,
     MCPSpecVersion,
     MCPTransport,
     UserAPIKeyAuth,
 )
+from litellm.types.mcp import MCPAuth
 from litellm.types.mcp_server.mcp_server_manager import MCPInfo, MCPServer
 
 

tests/test_litellm/proxy/management_endpoints/test_tag_management_endpoints.py

@@ -26,6 +26,8 @@ async def test_create_and_get_tag():
     """
     # Mock the prisma client and _get_tags_config and _save_tags_config
     with patch("litellm.proxy.proxy_server.prisma_client") as mock_prisma, patch(
+        "litellm.proxy.proxy_server.llm_router"
+    ) as mock_router, patch(
         "litellm.proxy.management_endpoints.tag_management_endpoints._get_tags_config"
     ) as mock_get_tags, patch(
         "litellm.proxy.management_endpoints.tag_management_endpoints._save_tags_config"
@@ -50,6 +52,7 @@ async def test_create_and_get_tag():
 
         # Test tag creation
         response = client.post("/tag/new", json=tag_data, headers=headers)
+        print(f"response: {response.text}")
         assert response.status_code == 200
         result = response.json()
         assert result["message"] == "Tag test-tag created successfully"
@@ -158,3 +161,93 @@ async def test_delete_tag():
 
         # Verify _save_tags_config was called without the deleted tag
         mock_save_tags.assert_called_once()
+
+
+@pytest.mark.asyncio
+async def test_get_deployments_by_model_id():
+    """
+    Test get_deployments_by_model when model is found by model_id
+    """
+    from unittest.mock import Mock
+
+    from litellm.proxy.management_endpoints.tag_management_endpoints import (
+        get_deployments_by_model,
+    )
+    from litellm.types.router import Deployment, LiteLLM_Params, ModelInfo
+
+    # Create a mock router
+    mock_router = Mock()
+
+    # Setup mock to return deployment by model_id
+    mock_deployment = Deployment(
+        model_name="gpt-3.5-turbo",
+        litellm_params=LiteLLM_Params(model="gpt-3.5-turbo"),
+        model_info=ModelInfo(),
+    )
+    mock_router.get_deployment.return_value = mock_deployment
+
+    result = await get_deployments_by_model("model-123", mock_router)
+
+    assert len(result) == 1
+    assert result[0] == mock_deployment
+    mock_router.get_deployment.assert_called_once_with(model_id="model-123")
+
+
+@pytest.mark.asyncio
+async def test_get_deployments_by_model_name():
+    """
+    Test get_deployments_by_model when model is found by model_name
+    """
+    from unittest.mock import Mock
+
+    from litellm.proxy.management_endpoints.tag_management_endpoints import (
+        get_deployments_by_model,
+    )
+    from litellm.types.router import Deployment
+
+    # Create a mock router
+    mock_router = Mock()
+
+    # Setup mock to not find by model_id but find by model_name
+    mock_router.get_deployment.return_value = None
+    mock_router.get_model_list.return_value = [
+        {
+            "model_name": "gpt-3.5-turbo",
+            "litellm_params": {"model": "gpt-3.5-turbo", "api_key": "test-key"},
+            "model_info": {"id": "model-1", "description": "Test model"},
+        }
+    ]
+
+    result = await get_deployments_by_model("gpt-3.5-turbo", mock_router)
+
+    assert len(result) == 1
+    assert result[0].model_name == "gpt-3.5-turbo"
+    assert isinstance(result[0], Deployment)
+    mock_router.get_deployment.assert_called_once_with(model_id="gpt-3.5-turbo")
+    mock_router.get_model_list.assert_called_once_with(model_name="gpt-3.5-turbo")
+
+
+@pytest.mark.asyncio
+async def test_get_deployments_by_model_not_found():
+    """
+    Test get_deployments_by_model when model is not found
+    """
+    from unittest.mock import Mock
+
+    from litellm.proxy.management_endpoints.tag_management_endpoints import (
+        get_deployments_by_model,
+    )
+
+    # Create a mock router
+    mock_router = Mock()
+
+    # Setup mock to not find model by either method
+    mock_router.get_deployment.return_value = None
+    mock_router.get_model_list.return_value = None
+
+    result = await get_deployments_by_model("nonexistent-model", mock_router)
+
+    assert len(result) == 0
+    assert result == []
+    mock_router.get_deployment.assert_called_once_with(model_id="nonexistent-model")
+    mock_router.get_model_list.assert_called_once_with(model_name="nonexistent-model")