fix(health.md): add rerank model health check information (#7295)

* fix(health.md): add rerank model health check information

* build(model_prices_and_context_window.json): add gemini 2.0 for google ai studio - pricing + commercial rate limits

* build(model_prices_and_context_window.json): add gemini-2.0 supports audio output = true

* docs(team_model_add.md): clarify allowing teams to add models is an enterprise feature

* fix(o1_transformation.py): add support for 'n', 'response_format' and 'stop' params for o1 and 'stream_options' param for o1-mini

* build(model_prices_and_context_window.json): add 'supports_system_message' to supporting openai models

needed as o1-preview, and o1-mini models don't support 'system message

* fix(o1_transformation.py): translate system message based on if o1 model supports it

* fix(o1_transformation.py): return 'stream' param support if o1-mini/o1-preview

o1 currently doesn't support streaming, but the other model versions do

Fixes https://github.com/BerriAI/litellm/issues/7292

* fix(o1_transformation.py): return tool calling/response_format in supported params if model map says so

Fixes https://github.com/BerriAI/litellm/issues/7292

* fix: fix linting errors

* fix: update '_transform_messages'

* fix(o1_transformation.py): fix provider passed for supported param checks

* test(base_llm_unit_tests.py): skip test if api takes >5s to respond

* fix(utils.py): return false in 'supports_factory' if can't find value

* fix(o1_transformation.py): always return stream + stream_options as supported params + handle stream options being passed in for azure o1

* feat(openai.py): support stream faking natively in openai handler

Allows o1 calls to be faked for just the "o1" model, allows native streaming for o1-mini, o1-preview

 Fixes https://github.com/BerriAI/litellm/issues/7292

* fix(openai.py): use inference param instead of original optional param

litellm/llms/openai/chat/o1_transformation.py

@@ -15,7 +15,14 @@ import types
 from typing import Any, List, Optional, Union
 
 import litellm
+from litellm import verbose_logger
+from litellm.litellm_core_utils.get_llm_provider_logic import get_llm_provider
 from litellm.types.llms.openai import AllMessageValues, ChatCompletionUserMessage
+from litellm.utils import (
+    supports_function_calling,
+    supports_response_schema,
+    supports_system_messages,
+)
 
 from .gpt_transformation import OpenAIGPTConfig
 
@@ -29,6 +36,15 @@ class OpenAIO1Config(OpenAIGPTConfig):
     def get_config(cls):
         return super().get_config()
 
+    def should_fake_stream(
+        self, model: str, custom_llm_provider: Optional[str] = None
+    ) -> bool:
+        supported_stream_models = ["o1-mini", "o1-preview"]
+        for supported_model in supported_stream_models:
+            if supported_model in model:
+                return False
+        return True
+
     def get_supported_openai_params(self, model: str) -> list:
         """
         Get the supported OpenAI params for the given model
@@ -38,21 +54,37 @@ class OpenAIO1Config(OpenAIGPTConfig):
         all_openai_params = super().get_supported_openai_params(model=model)
         non_supported_params = [
             "logprobs",
-            "tools",
-            "tool_choice",
-            "parallel_tool_calls",
-            "function_call",
-            "functions",
             "top_p",
-            "n",
             "presence_penalty",
             "frequency_penalty",
             "top_logprobs",
-            "response_format",
-            "stop",
-            "stream_options",
         ]
 
+        try:
+            model, custom_llm_provider, api_base, api_key = get_llm_provider(
+                model=model
+            )
+        except Exception:
+            verbose_logger.debug(
+                f"Unable to infer model provider for model={model}, defaulting to openai for o1 supported param check"
+            )
+            custom_llm_provider = "openai"
+
+        _supports_function_calling = supports_function_calling(
+            model, custom_llm_provider
+        )
+        _supports_response_schema = supports_response_schema(model, custom_llm_provider)
+
+        if not _supports_function_calling:
+            non_supported_params.append("tools")
+            non_supported_params.append("tool_choice")
+            non_supported_params.append("parallel_tool_calls")
+            non_supported_params.append("function_call")
+            non_supported_params.append("functions")
+
+        if not _supports_response_schema:
+            non_supported_params.append("response_format")
+
         return [
             param for param in all_openai_params if param not in non_supported_params
         ]
@@ -95,16 +127,16 @@ class OpenAIO1Config(OpenAIGPTConfig):
         return False
 
     def _transform_messages(
-        self, messages: List[AllMessageValues]
+        self, messages: List[AllMessageValues], model: str
     ) -> List[AllMessageValues]:
         """
         Handles limitations of O-1 model family.
         - modalities: image => drop param (if user opts in to dropping param)
         - role: system ==> translate to role 'user'
         """
-
+        _supports_system_messages = supports_system_messages(model, "openai")
         for i, message in enumerate(messages):
-            if message["role"] == "system":
+            if message["role"] == "system" and not _supports_system_messages:
                 new_message = ChatCompletionUserMessage(
                     content=message["content"], role="user"
                 )