diff --git a/litellm/llms/chatgpt/image_generation/transformation.py b/litellm/llms/chatgpt/image_generation/transformation.py
index 72e69eeb337..74a85ee3a47 100644
--- a/litellm/llms/chatgpt/image_generation/transformation.py
+++ b/litellm/llms/chatgpt/image_generation/transformation.py
@@ -1,5 +1,4 @@
 import json
-import re
 import base64
 from io import BufferedReader, BytesIO
 from os import PathLike
@@ -42,11 +41,6 @@ from ..common_utils import (
 )
 
 GPT_IMAGE_MODEL_PREFIX = "gpt-image-"
-GPT_IMAGE_2_MODEL_PREFIX = "gpt-image-2"
-GPT_IMAGE_2_MIN_PIXELS = 655_360
-GPT_IMAGE_2_MAX_PIXELS = 8_294_400
-GPT_IMAGE_2_MAX_EDGE = 3840
-GPT_IMAGE_2_MAX_RATIO = 3.0
 
 ALLOWED_OUTPUT_FORMATS = {"png", "jpeg", "webp"}
 INTERNAL_OPTIONAL_PARAMS = {"chatgpt_responses_model"}
@@ -231,46 +225,6 @@ class ChatGPTImageGenerationConfig(BaseImageGenerationConfig):
         if output_format is not None and output_format not in ALLOWED_OUTPUT_FORMATS:
             raise ValueError("output_format must be one of png, jpeg, or webp")
 
-        size = optional_params.get("size")
-        if size is not None and model.startswith(GPT_IMAGE_2_MODEL_PREFIX):
-            self._validate_gpt_image_2_size(size)
-
-    @staticmethod
-    def _parse_size(size: str) -> Optional[Tuple[int, int]]:
-        match = re.fullmatch(r"([1-9][0-9]*)x([1-9][0-9]*)", size)
-        if not match:
-            return None
-        return int(match.group(1)), int(match.group(2))
-
-    def _validate_gpt_image_2_size(self, size: str) -> None:
-        if size == "auto":
-            return
-
-        parsed = self._parse_size(size)
-        if parsed is None:
-            raise ValueError("size must be auto or WIDTHxHEIGHT, for example 1024x1024")
-
-        width, height = parsed
-        max_edge = max(width, height)
-        min_edge = min(width, height)
-        total_pixels = width * height
-
-        if max_edge > GPT_IMAGE_2_MAX_EDGE:
-            raise ValueError("gpt-image-2 size maximum edge length must be <= 3840px")
-        if width % 16 != 0 or height % 16 != 0:
-            raise ValueError(
-                "gpt-image-2 size width and height must be multiples of 16px"
-            )
-        if max_edge / min_edge > GPT_IMAGE_2_MAX_RATIO:
-            raise ValueError("gpt-image-2 size ratio must not exceed 3:1")
-        if (
-            total_pixels < GPT_IMAGE_2_MIN_PIXELS
-            or total_pixels > GPT_IMAGE_2_MAX_PIXELS
-        ):
-            raise ValueError(
-                "gpt-image-2 total pixels must be between 655,360 and 8,294,400"
-            )
-
     def transform_image_generation_response(
         self,
         model: str,
diff --git a/tests/image_gen_tests/test_chatgpt_image_generation.py b/tests/image_gen_tests/test_chatgpt_image_generation.py
index 66bda02f053..4bcba270cd5 100644
--- a/tests/image_gen_tests/test_chatgpt_image_generation.py
+++ b/tests/image_gen_tests/test_chatgpt_image_generation.py
@@ -107,10 +107,6 @@ def test_chatgpt_image_generation_forwards_supported_generate_params(
     "optional_params, error",
     [
         ({"output_format": "jpg"}, "output_format must be one of png, jpeg, or webp"),
-        ({"size": "1535x1024"}, "multiples of 16px"),
-        ({"size": "4096x1024"}, "maximum edge length"),
-        ({"size": "1024x256"}, "ratio must not exceed 3:1"),
-        ({"size": "512x512"}, "total pixels must be between"),
     ],
 )
 def test_chatgpt_image_generation_validates_params(
@@ -489,7 +485,7 @@ def test_chatgpt_image_generation_uses_optional_responses_model(monkeypatch, tmp
         ("dall-e-3", {}, "requires a GPT Image model"),
         ("gpt-image-1.5", {"size": "auto"}, None),
         ("gpt-image-2", {"size": "auto"}, None),
-        ("gpt-image-2", {"size": "bad-size"}, "size must be auto or WIDTHxHEIGHT"),
+        ("gpt-image-2", {"size": "bad-size"}, None),
     ],
 )
 def test_chatgpt_image_generation_validates_additional_param_paths(
@@ -518,6 +514,23 @@ def test_chatgpt_image_generation_validates_additional_param_paths(
         )
 
 
+def test_chatgpt_image_generation_forwards_size_without_local_constraints(
+    monkeypatch, tmp_path
+):
+    monkeypatch.setenv("CHATGPT_TOKEN_DIR", str(tmp_path))
+    config = ChatGPTImageGenerationConfig()
+
+    request = config.transform_image_generation_request(
+        model="gpt-image-2",
+        prompt="draw a cat",
+        optional_params={"size": "bad-size"},
+        litellm_params={},
+        headers={},
+    )
+
+    assert request["tools"][0]["size"] == "bad-size"
+
+
 def test_chatgpt_image_generation_extracts_b64_from_deep_nested_payload(
     monkeypatch, tmp_path
 ):