fix(moonshot): preserve image_url blocks in multimodal messages

Moonshot's _transform_messages unconditionally flattened content arrays
to plain text, dropping image_url blocks. Vision models like kimi-k2.5
accept the standard OpenAI content array format.

Now checks for image_url blocks before flattening — if any message
contains images the content array is preserved intact.

Fixes #20862

docs/my-website/docs/providers/moonshot.md

@@ -219,6 +219,37 @@ curl http://localhost:4000/v1/chat/completions \
 
 For more detailed information on using the LiteLLM Proxy, see the [LiteLLM Proxy documentation](../providers/litellm_proxy).
 
+## Image / Vision Support
+
+Moonshot vision models (`kimi-k2.5`, `kimi-latest`, `moonshot-v1-*-vision-preview`, etc.) accept the standard OpenAI content array with `image_url` blocks.
+
+LiteLLM automatically detects when your messages contain images and preserves the content array so the image payload reaches the Moonshot API. For text-only requests the content is flattened to a plain string, as required by Moonshot text models.
+
+```python showLineNumbers title="Moonshot Vision Example"
+import os
+import litellm
+
+os.environ["MOONSHOT_API_KEY"] = ""
+
+response = litellm.completion(
+    model="moonshot/kimi-k2.5",
+    messages=[
+        {
+            "role": "user",
+            "content": [
+                {"type": "text", "text": "What is in this image?"},
+                {
+                    "type": "image_url",
+                    "image_url": {"url": "https://example.com/image.png"},
+                },
+            ],
+        }
+    ],
+)
+
+print(response.choices[0].message.content)
+```
+
 ## Moonshot AI Limitations & LiteLLM Handling
 
 LiteLLM automatically handles the following [Moonshot AI limitations](https://platform.moonshot.ai/docs/guide/migrating-from-openai-to-kimi#about-api-compatibility) to provide seamless OpenAI compatibility:

litellm/llms/moonshot/chat/transformation.py

@@ -33,9 +33,25 @@ class MoonshotChatConfig(OpenAIGPTConfig):
         self, messages: List[AllMessageValues], model: str, is_async: bool = False
     ) -> Union[List[AllMessageValues], Coroutine[Any, Any, List[AllMessageValues]]]:
         """
-        Moonshot AI does not support content in list format.
+        Moonshot text-only models don't support content in list format.
+        Multimodal models (kimi-k2.5, kimi-latest, etc.) accept the
+        standard OpenAI content array with non-text blocks (image_url,
+        input_audio, video_url, file, etc.).
+
+        If any message contains a non-text content part, skip flattening
+        so the multimodal payload is preserved.
         """
-        messages = handle_messages_with_content_list_to_str_conversion(messages)
+        has_non_text = False
+        for m in messages:
+            _content = m.get("content")
+            if _content and isinstance(_content, list):
+                if any(c.get("type") != "text" for c in _content):
+                    has_non_text = True
+                    break
+
+        if not has_non_text:
+            messages = handle_messages_with_content_list_to_str_conversion(messages)
+
         if is_async:
             return super()._transform_messages(
                 messages=messages, model=model, is_async=True

tests/test_litellm/llms/moonshot/test_moonshot_chat_transformation.py

@@ -309,4 +309,99 @@ class TestMoonshotConfig:
             
             # Check that no extra message was added
             assert len(result["messages"]) == 1
-            assert result["messages"][0]["content"] == "What's the weather?"
+            assert result["messages"][0]["content"] == "What's the weather?"
+
+    def test_transform_messages_preserves_image_url_content(self):
+        """Test that messages with image_url blocks are NOT flattened to strings.
+
+        Multimodal models like kimi-k2.5 accept the standard OpenAI content
+        array with non-text blocks. When any message contains a non-text part,
+        the content array must be preserved so the payload reaches the API.
+        """
+        config = MoonshotChatConfig()
+
+        messages = [
+            {
+                "role": "user",
+                "content": [
+                    {"type": "text", "text": "What is in this image?"},
+                    {
+                        "type": "image_url",
+                        "image_url": {"url": "https://example.com/image.png"},
+                    },
+                ],
+            }
+        ]
+
+        result = config.transform_request(
+            model="kimi-k2.5",
+            messages=messages,
+            optional_params={},
+            litellm_params={},
+            headers={},
+        )
+
+        # Content must remain a list (not flattened to a string)
+        assert isinstance(result["messages"][0]["content"], list)
+        assert len(result["messages"][0]["content"]) == 2
+        assert result["messages"][0]["content"][0]["type"] == "text"
+        assert result["messages"][0]["content"][1]["type"] == "image_url"
+
+    def test_transform_messages_preserves_non_text_content(self):
+        """Test that any non-text content type (input_audio, video_url, file,
+        etc.) also prevents flattening, matching the OpenAI content spec."""
+        config = MoonshotChatConfig()
+
+        messages = [
+            {
+                "role": "user",
+                "content": [
+                    {"type": "text", "text": "Transcribe this audio"},
+                    {
+                        "type": "input_audio",
+                        "input_audio": {"data": "base64data", "format": "wav"},
+                    },
+                ],
+            }
+        ]
+
+        result = config.transform_request(
+            model="kimi-k2.5",
+            messages=messages,
+            optional_params={},
+            litellm_params={},
+            headers={},
+        )
+
+        assert isinstance(result["messages"][0]["content"], list)
+        assert len(result["messages"][0]["content"]) == 2
+        assert result["messages"][0]["content"][1]["type"] == "input_audio"
+
+    def test_transform_messages_flattens_text_only_content(self):
+        """Test that text-only content arrays ARE flattened to strings.
+
+        For text-only requests, Moonshot expects plain string content.
+        The content list should be converted to a single string.
+        """
+        config = MoonshotChatConfig()
+
+        messages = [
+            {
+                "role": "user",
+                "content": [
+                    {"type": "text", "text": "Hello, how are you?"},
+                ],
+            }
+        ]
+
+        result = config.transform_request(
+            model="moonshot-v1-8k",
+            messages=messages,
+            optional_params={},
+            litellm_params={},
+            headers={},
+        )
+
+        # Content should be flattened to a plain string
+        assert isinstance(result["messages"][0]["content"], str)
+        assert result["messages"][0]["content"] == "Hello, how are you?"