Finetuned openai azure models cost calculation (#12267)

**Description:**
Add cost calculation for fine tuned **Azure** with relevant unit tests.
see
https://learn.microsoft.com/en-us/azure/ai-services/openai/how-to/fine-tuning?tabs=turbo&pivots=programming-language-studio
for more information.
this PR is the result of this PR:
https://github.com/langchain-ai/langchain/pull/12190

Twitter handle: @nirkopler

libs/langchain/langchain/callbacks/openai_info.py

@@ -65,6 +65,14 @@ MODEL_COST_PER_1K_TOKENS = {
     "babbage-002-finetuned-completion": 0.0016,
     "davinci-002-finetuned-completion": 0.012,
     "gpt-3.5-turbo-0613-finetuned-completion": 0.016,
+    # Azure Fine Tuned input
+    "babbage-002-azure-finetuned": 0.0004,
+    "davinci-002-azure-finetuned": 0.002,
+    "gpt-35-turbo-0613-azure-finetuned": 0.0015,
+    # Azure Fine Tuned output
+    "babbage-002-azure-finetuned-completion": 0.0004,
+    "davinci-002-azure-finetuned-completion": 0.002,
+    "gpt-35-turbo-0613-azure-finetuned-completion": 0.002,
     # Legacy fine-tuned models
     "ada-finetuned-legacy": 0.0016,
     "babbage-finetuned-legacy": 0.0024,
@@ -90,7 +98,9 @@ def standardize_model_name(
 
     """
     model_name = model_name.lower()
-    if "ft-" in model_name:
+    if ".ft-" in model_name:
+        return model_name.split(".ft-")[0] + "-azure-finetuned"
+    if ":ft-" in model_name:
         return model_name.split(":")[0] + "-finetuned-legacy"
     if "ft:" in model_name:
         return model_name.split(":")[1] + "-finetuned"

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

@@ -59,6 +59,9 @@ def test_on_llm_end_custom_model(handler: OpenAICallbackHandler) -> None:
         "ft:babbage-002:your-org:custom-model-name:1abcdefg",
         "ft:davinci-002:your-org:custom-model-name:1abcdefg",
         "ft:gpt-3.5-turbo-0613:your-org:custom-model-name:1abcdefg",
+        "babbage-002.ft-0123456789abcdefghijklmnopqrstuv",
+        "davinci-002.ft-0123456789abcdefghijklmnopqrstuv",
+        "gpt-35-turbo-0613.ft-0123456789abcdefghijklmnopqrstuv",
     ],
 )
 def test_on_llm_end_finetuned_model(