Add /vllm/* and /mistral/* passthrough endpoints (adds support for Mistral OCR via passthrough)

* feat(llm_passthrough_endpoints.py): support mistral passthrough

Closes https://github.com/BerriAI/litellm/issues/9051

* feat(llm_passthrough_endpoints.py): initial commit for adding vllm passthrough route

* feat(vllm/common_utils.py): add new vllm model info route

make it possible to use vllm passthrough route via factory function

* fix(llm_passthrough_endpoints.py): add all methods to vllm passthrough route

* fix: fix linting error

* fix: fix linting error

* fix: fix ruff check

* fix(proxy/_types.py): add new passthrough routes

* docs(config_settings.md): add mistral env vars to docs

litellm/llms/anthropic/common_utils.py

@@ -2,7 +2,7 @@
 This file contains common utils for anthropic calls.
 """
 
-from typing import List, Optional, Union
+from typing import Dict, List, Optional, Union
 
 import httpx
 
@@ -10,6 +10,8 @@ import litellm
 from litellm.llms.base_llm.base_utils import BaseLLMModelInfo
 from litellm.llms.base_llm.chat.transformation import BaseLLMException
 from litellm.secret_managers.main import get_secret_str
+from litellm.types.llms.anthropic import AllAnthropicToolsValues
+from litellm.types.llms.openai import AllMessageValues
 
 
 class AnthropicError(BaseLLMException):
@@ -23,6 +25,128 @@ class AnthropicError(BaseLLMException):
 
 
 class AnthropicModelInfo(BaseLLMModelInfo):
+    def is_cache_control_set(self, messages: List[AllMessageValues]) -> bool:
+        """
+        Return if {"cache_control": ..} in message content block
+
+        Used to check if anthropic prompt caching headers need to be set.
+        """
+        for message in messages:
+            if message.get("cache_control", None) is not None:
+                return True
+            _message_content = message.get("content")
+            if _message_content is not None and isinstance(_message_content, list):
+                for content in _message_content:
+                    if "cache_control" in content:
+                        return True
+
+        return False
+
+    def is_computer_tool_used(
+        self, tools: Optional[List[AllAnthropicToolsValues]]
+    ) -> bool:
+        if tools is None:
+            return False
+        for tool in tools:
+            if "type" in tool and tool["type"].startswith("computer_"):
+                return True
+        return False
+
+    def is_pdf_used(self, messages: List[AllMessageValues]) -> bool:
+        """
+        Set to true if media passed into messages.
+
+        """
+        for message in messages:
+            if (
+                "content" in message
+                and message["content"] is not None
+                and isinstance(message["content"], list)
+            ):
+                for content in message["content"]:
+                    if "type" in content and content["type"] != "text":
+                        return True
+        return False
+
+    def _get_user_anthropic_beta_headers(
+        self, anthropic_beta_header: Optional[str]
+    ) -> Optional[List[str]]:
+        if anthropic_beta_header is None:
+            return None
+        return anthropic_beta_header.split(",")
+
+    def get_anthropic_headers(
+        self,
+        api_key: str,
+        anthropic_version: Optional[str] = None,
+        computer_tool_used: bool = False,
+        prompt_caching_set: bool = False,
+        pdf_used: bool = False,
+        is_vertex_request: bool = False,
+        user_anthropic_beta_headers: Optional[List[str]] = None,
+    ) -> dict:
+        betas = set()
+        if prompt_caching_set:
+            betas.add("prompt-caching-2024-07-31")
+        if computer_tool_used:
+            betas.add("computer-use-2024-10-22")
+        if pdf_used:
+            betas.add("pdfs-2024-09-25")
+        headers = {
+            "anthropic-version": anthropic_version or "2023-06-01",
+            "x-api-key": api_key,
+            "accept": "application/json",
+            "content-type": "application/json",
+        }
+
+        if user_anthropic_beta_headers is not None:
+            betas.update(user_anthropic_beta_headers)
+
+        # Don't send any beta headers to Vertex, Vertex has failed requests when they are sent
+        if is_vertex_request is True:
+            pass
+        elif len(betas) > 0:
+            headers["anthropic-beta"] = ",".join(betas)
+
+        return headers
+
+    def validate_environment(
+        self,
+        headers: dict,
+        model: str,
+        messages: List[AllMessageValues],
+        optional_params: dict,
+        litellm_params: dict,
+        api_key: Optional[str] = None,
+        api_base: Optional[str] = None,
+    ) -> Dict:
+        if api_key is None:
+            raise litellm.AuthenticationError(
+                message="Missing Anthropic API Key - A call is being made to anthropic but no key is set either in the environment variables or via params. Please set `ANTHROPIC_API_KEY` in your environment vars",
+                llm_provider="anthropic",
+                model=model,
+            )
+
+        tools = optional_params.get("tools")
+        prompt_caching_set = self.is_cache_control_set(messages=messages)
+        computer_tool_used = self.is_computer_tool_used(tools=tools)
+        pdf_used = self.is_pdf_used(messages=messages)
+        user_anthropic_beta_headers = self._get_user_anthropic_beta_headers(
+            anthropic_beta_header=headers.get("anthropic-beta")
+        )
+        anthropic_headers = self.get_anthropic_headers(
+            computer_tool_used=computer_tool_used,
+            prompt_caching_set=prompt_caching_set,
+            pdf_used=pdf_used,
+            api_key=api_key,
+            is_vertex_request=optional_params.get("is_vertex_request", False),
+            user_anthropic_beta_headers=user_anthropic_beta_headers,
+        )
+
+        headers = {**headers, **anthropic_headers}
+
+        return headers
+
     @staticmethod
     def get_api_base(api_base: Optional[str] = None) -> Optional[str]:
         return (