diff --git a/litellm/llms/mistral/mistral_chat_transformation.py b/litellm/llms/mistral/mistral_chat_transformation.py
index 7f93ddcc29..3e7a97c92f 100644
--- a/litellm/llms/mistral/mistral_chat_transformation.py
+++ b/litellm/llms/mistral/mistral_chat_transformation.py
@@ -28,9 +28,7 @@ class MistralConfig(OpenAIGPTConfig):
 
     - `top_p` (number or null): An alternative to sampling with temperature, used for nucleus sampling. API Default - 1.
 
-    - `max_tokens` [DEPRECATED - use max_completion_tokens] (integer or null): This optional parameter helps to set the maximum number of tokens to generate in the chat completion. API Default - null.
-
-    - `max_completion_tokens` (integer or null): This optional parameter helps to set the maximum number of tokens to generate in the chat completion. API Default - null.
+    - `max_tokens` (integer or null): This optional parameter helps to set the maximum number of tokens to generate in the chat completion. API Default - null.
 
     - `tools` (list or null): A list of available tools for the model. Use this to specify functions for which the model can generate JSON inputs.
 
@@ -48,7 +46,6 @@ class MistralConfig(OpenAIGPTConfig):
     temperature: Optional[int] = None
     top_p: Optional[int] = None
     max_tokens: Optional[int] = None
-    max_completion_tokens: Optional[int] = None
     tools: Optional[list] = None
     tool_choice: Optional[Literal["auto", "any", "none"]] = None
     random_seed: Optional[int] = None
@@ -61,7 +58,6 @@ class MistralConfig(OpenAIGPTConfig):
         temperature: Optional[int] = None,
         top_p: Optional[int] = None,
         max_tokens: Optional[int] = None,
-        max_completion_tokens: Optional[int] = None,
         tools: Optional[list] = None,
         tool_choice: Optional[Literal["auto", "any", "none"]] = None,
         random_seed: Optional[int] = None,
@@ -84,7 +80,6 @@ class MistralConfig(OpenAIGPTConfig):
             "temperature",
             "top_p",
             "max_tokens",
-            "max_completion_tokens"
             "tools",
             "tool_choice",
             "seed",
@@ -110,8 +105,6 @@ class MistralConfig(OpenAIGPTConfig):
         for param, value in non_default_params.items():
             if param == "max_tokens":
                 optional_params["max_tokens"] = value
-            if param == "max_completion_tokens": # max_completion_tokens should take priority
-                optional_params["max_tokens"] = value
             if param == "tools":
                 optional_params["tools"] = value
             if param == "stream" and value is True:
diff --git a/tests/litellm/llms/mistral/test_mistral_transformation.py b/tests/litellm/llms/mistral/test_mistral_transformation.py
deleted file mode 100644
index 4594e8ca2a..0000000000
--- a/tests/litellm/llms/mistral/test_mistral_transformation.py
+++ /dev/null
@@ -1,45 +0,0 @@
-import os
-import sys
-from unittest.mock import MagicMock
-
-
-sys.path.insert(
-    0, os.path.abspath("../../../../..")
-)  # Adds the parent directory to the system path
-
-from litellm.llms.mistral.mistral_chat_transformation import MistralConfig
-
-
-class TestMistralTransform:
-    def setup_method(self):
-        self.config = MistralConfig()
-        self.model = "mistral-small-latest"
-        self.logging_obj = MagicMock()
-
-    def test_map_mistral_params(self):
-        """Test that parameters are correctly mapped"""
-        test_params = {"temperature": 0.7, "max_tokens": 200, "max_completion_tokens": 256}
-
-        result = self.config.map_openai_params(
-            non_default_params=test_params,
-            optional_params={},
-            model=self.model,
-            drop_params=False,
-        )
-
-        # The function should properly map max_completion_tokens to max_tokens and override max_tokens
-        assert result == {"temperature": 0.7, "max_tokens": 256}
-
-    def test_mistral_max_tokens_backward_compat(self):
-        """Test that parameters are correctly mapped"""
-        test_params = {"temperature": 0.7, "max_tokens": 200,}
-
-        result = self.config.map_openai_params(
-            non_default_params=test_params,
-            optional_params={},
-            model=self.model,
-            drop_params=False,
-        )
-
-        # The function should properly map max_tokens if max_completion_tokens is not provided
-        assert result == {"temperature": 0.7, "max_tokens": 200}