diff --git a/docs/my-website/docs/proxy/call_hooks.md b/docs/my-website/docs/proxy/call_hooks.md
index fe865f67e09..17354725fd5 100644
--- a/docs/my-website/docs/proxy/call_hooks.md
+++ b/docs/my-website/docs/proxy/call_hooks.md
@@ -19,6 +19,7 @@ import Image from '@theme/IdealImage';
 | `async_post_call_success_hook` | Modify outgoing response (non-streaming) | After successful LLM API call, for non-streaming responses |
 | `async_post_call_failure_hook` | Transform error responses sent to clients | After failed LLM API call |
 | `async_post_call_streaming_hook` | Modify outgoing response (streaming) | After successful LLM API call, for streaming responses |
+| `async_post_call_response_headers_hook` | Inject custom HTTP response headers | After LLM API call (both success and failure) |
 
 See a complete example with our [parallel request rate limiter](https://github.com/BerriAI/litellm/blob/main/litellm/proxy/hooks/parallel_request_limiter.py)
 
@@ -115,6 +116,18 @@ class MyCustomHandler(CustomLogger): # https://docs.litellm.ai/docs/observabilit
         async for item in response:
             yield item
 
+    async def async_post_call_response_headers_hook(
+        self,
+        data: dict,
+        user_api_key_dict: UserAPIKeyAuth,
+        response: Any,
+        request_headers: Optional[Dict[str, str]] = None,
+    ) -> Optional[Dict[str, str]]:
+        """
+        Inject custom headers into HTTP response (runs for both success and failure).
+        """
+        return {"x-custom-header": "custom-value"}
+
 proxy_handler_instance = MyCustomHandler()
 ```
 
@@ -389,3 +402,31 @@ proxy_handler_instance = MyErrorTransformer()
 ```
 
 **Result:** Clients receive `"Your prompt is too long..."` instead of `"ContextWindowExceededError: Prompt exceeds context window"`.
+
+## Advanced - Inject Custom HTTP Response Headers
+
+Use `async_post_call_response_headers_hook` to inject custom HTTP headers into responses. This hook runs for **both successful and failed** LLM API calls.
+
+```python
+from litellm.integrations.custom_logger import CustomLogger
+from litellm.proxy.proxy_server import UserAPIKeyAuth
+from typing import Any, Dict, Optional
+
+class CustomHeaderLogger(CustomLogger):
+    def __init__(self):
+        super().__init__()
+
+    async def async_post_call_response_headers_hook(
+        self,
+        data: dict,
+        user_api_key_dict: UserAPIKeyAuth,
+        response: Any,
+        request_headers: Optional[Dict[str, str]] = None,
+    ) -> Optional[Dict[str, str]]:
+        """
+        Inject custom headers into all responses (success and failure).
+        """
+        return {"x-custom-header": "custom-value"}
+
+proxy_handler_instance = CustomHeaderLogger()
+```
diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json
index 6a605f460d4..d874e6ba578 100644
--- a/litellm/model_prices_and_context_window_backup.json
+++ b/litellm/model_prices_and_context_window_backup.json
@@ -3726,9 +3726,9 @@
         "cache_read_input_token_cost": 1.75e-07,
         "input_cost_per_token": 1.75e-06,
         "litellm_provider": "azure",
-        "max_input_tokens": 128000,
-        "max_output_tokens": 16384,
-        "max_tokens": 16384,
+        "max_input_tokens": 272000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
         "mode": "responses",
         "output_cost_per_token": 1.4e-05,
         "supported_endpoints": [
@@ -18799,7 +18799,7 @@
         "input_cost_per_token": 1.75e-06,
         "input_cost_per_token_priority": 3.5e-06,
         "litellm_provider": "openai",
-        "max_input_tokens": 400000,
+        "max_input_tokens": 272000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "responses",
@@ -23790,6 +23790,20 @@
         "output_cost_per_token": 6.5e-07,
         "supports_tool_choice": true
     },
+    "openrouter/moonshotai/kimi-k2.5": {
+        "cache_read_input_token_cost": 1e-07,
+        "input_cost_per_token": 6e-07,
+        "litellm_provider": "openrouter",
+        "max_input_tokens": 262144,
+        "max_output_tokens": 262144,
+        "max_tokens": 262144,
+        "mode": "chat",
+        "output_cost_per_token": 3e-06,
+        "source": "https://openrouter.ai/moonshotai/kimi-k2.5",
+        "supports_function_calling": true,
+        "supports_tool_choice": true,
+        "supports_vision": true
+    },
     "openrouter/nousresearch/nous-hermes-llama2-13b": {
         "input_cost_per_token": 2e-07,
         "litellm_provider": "openrouter",
@@ -24003,7 +24017,7 @@
         "cache_read_input_token_cost": 1.75e-07,
         "input_cost_per_token": 1.75e-06,
         "litellm_provider": "openrouter",
-        "max_input_tokens": 400000,
+        "max_input_tokens": 272000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "responses",