Community : Add OpenAI prompt caching and reasoning tokens tracking (#27135)

Added Token tracking for OpenAI's prompt caching and reasoning tokens
Costs updated from https://openai.com/api/pricing/

usage example
```python
from langchain_community.callbacks import get_openai_callback
from langchain_openai import ChatOpenAI
llm = ChatOpenAI(model_name="o1-mini",temperature=1)

with get_openai_callback() as cb:
    response = llm.invoke("hi "*1500)
    print(cb)
```
Output
```
Tokens Used: 1720
	Prompt Tokens: 1508
		Prompt Tokens Cached: 1408
	Completion Tokens: 212
		Reasoning Tokens: 192
Successful Requests: 1
Total Cost (USD): $0.0049559999999999995
```

---------

Co-authored-by: Chester Curme <chester.curme@gmail.com>

libs/community/tests/unit_tests/callbacks/test_openai_info.py

@@ -3,7 +3,8 @@ from uuid import uuid4
 
 import numpy as np
 import pytest
-from langchain_core.outputs import LLMResult
+from langchain_core.messages import AIMessage
+from langchain_core.outputs import ChatGeneration, LLMResult
 from langchain_core.utils.pydantic import get_fields
 
 from langchain_community.callbacks import OpenAICallbackHandler
@@ -35,6 +36,43 @@ def test_on_llm_end(handler: OpenAICallbackHandler) -> None:
     assert handler.total_cost > 0
 
 
+def test_on_llm_end_with_chat_generation(handler: OpenAICallbackHandler) -> None:
+    response = LLMResult(
+        generations=[
+            [
+                ChatGeneration(
+                    text="Hello, world!",
+                    message=AIMessage(
+                        content="Hello, world!",
+                        usage_metadata={
+                            "input_tokens": 2,
+                            "output_tokens": 2,
+                            "total_tokens": 4,
+                            "input_token_details": {
+                                "cache_read": 1,
+                            },
+                            "output_token_details": {
+                                "reasoning": 1,
+                            },
+                        },
+                    ),
+                )
+            ]
+        ],
+        llm_output={
+            "model_name": get_fields(BaseOpenAI)["model_name"].default,
+        },
+    )
+    handler.on_llm_end(response)
+    assert handler.successful_requests == 1
+    assert handler.total_tokens == 4
+    assert handler.prompt_tokens == 2
+    assert handler.prompt_tokens_cached == 1
+    assert handler.completion_tokens == 2
+    assert handler.reasoning_tokens == 1
+    assert handler.total_cost > 0
+
+
 def test_on_llm_end_custom_model(handler: OpenAICallbackHandler) -> None:
     response = LLMResult(
         generations=[],