Merge remote-tracking branch 'origin/litellm_internal_staging' into litellm_lit_7022_azure_ai_passthrough_config

# Conflicts:
#	tests/test_litellm/proxy/pass_through_endpoints/test_llm_pass_through_endpoints.py

litellm/exceptions.py

@@ -338,6 +338,7 @@ class Timeout(openai.APITimeoutError):
         num_retries: int | None = None,
         headers: dict | None = None,
         exception_status_code: int | None = None,
+        response: httpx.Response | None = None,
     ):
         request: Final = httpx.Request(
             method="POST",
@@ -352,6 +353,8 @@ class Timeout(openai.APITimeoutError):
         self.max_retries = max_retries
         self.num_retries = num_retries
         self.headers = headers
+        if response is not None:
+            self.response = response
 
     # custom function to convert to str
     def __str__(self):

litellm/litellm_core_utils/exception_mapping_utils.py

@@ -860,6 +860,7 @@ def _map_bedrock_exception(
                 message=mantle_context_window_message,
                 model=model,
                 llm_provider=custom_llm_provider,
+                response=getattr(original_exception, "response", None),
             )
     if (
         "too many tokens" in error_str
@@ -873,6 +874,7 @@ def _map_bedrock_exception(
             message=f"BedrockException: Context Window Error - {error_str}",
             model=model,
             llm_provider="bedrock",
+            response=getattr(original_exception, "response", None),
         )
     elif "Conversation blocks and tool result blocks cannot be provided in the same turn." in error_str:
         raise BadRequestError(
@@ -924,12 +926,14 @@ def _map_bedrock_exception(
             message=f"BedrockException: Timeout Error - {error_str}",
             model=model,
             llm_provider="bedrock",
+            response=getattr(original_exception, "response", None),
         )
     elif "Could not process image" in error_str:
         raise litellm.InternalServerError(
             message=f"BedrockException - {error_str}",
             model=model,
             llm_provider="bedrock",
+            response=getattr(original_exception, "response", None),
         )
     elif hasattr(original_exception, "status_code"):
         if original_exception.status_code == 500:
@@ -937,10 +941,7 @@ def _map_bedrock_exception(
                 message=f"BedrockException - {original_exception.message}",
                 llm_provider="bedrock",
                 model=model,
-                response=httpx.Response(
-                    status_code=500,
-                    request=httpx.Request(method="POST", url="https://api.openai.com/v1/"),
-                ),
+                response=getattr(original_exception, "response", None),
             )
         elif original_exception.status_code == 401:
             raise AuthenticationError(
@@ -969,6 +970,7 @@ def _map_bedrock_exception(
                 model=model,
                 llm_provider=custom_llm_provider,
                 litellm_debug_info=extra_information,
+                response=getattr(original_exception, "response", None),
             )
         elif original_exception.status_code == 422:
             raise BadRequestError(
@@ -1001,6 +1003,7 @@ def _map_bedrock_exception(
                 llm_provider=custom_llm_provider,
                 litellm_debug_info=extra_information,
                 exception_status_code=original_exception.status_code,
+                response=getattr(original_exception, "response", None),
             )
 
 

litellm/litellm_core_utils/llm_response_utils/get_headers.py

@@ -1,7 +1,8 @@
+from collections.abc import Mapping
 from typing import Final
 
 
-def get_response_headers(_response_headers: dict | None = None) -> dict:
+def get_response_headers(_response_headers: Mapping[str, str] | None = None) -> dict:
     """
 
     Sets the Appropriate OpenAI headers for the response and forward all headers as llm_provider-{header}
@@ -31,7 +32,7 @@ def get_response_headers(_response_headers: dict | None = None) -> dict:
     return {**llm_provider_headers, **openai_headers}
 
 
-def _get_llm_provider_headers(response_headers: dict) -> dict:
+def _get_llm_provider_headers(response_headers: Mapping[str, str]) -> dict:
     """
     Adds a llm_provider-{header} to all headers that are not already prefixed with llm_provider
 

litellm/llms/bedrock/chat/agentcore/transformation.py

@@ -667,7 +667,12 @@ class AmazonAgentCoreConfig(BaseConfig, BaseAWSLLM):
         )
 
         if response.status_code != 200:
-            raise BedrockError(status_code=response.status_code, message=str(response.read()))
+            raise BedrockError(
+                status_code=response.status_code,
+                message=str(response.read()),
+                headers=response.headers,
+                response=response,
+            )
 
         # LOGGING
         logging_obj.post_call(
@@ -690,6 +695,7 @@ class AmazonAgentCoreConfig(BaseConfig, BaseAWSLLM):
                 raise BedrockError(
                     status_code=response.status_code,
                     message=f"AgentCore: Failed to read/parse JSON response body: {e}",
+                    headers=response.headers,
                 )
             parsed: Final = self._parse_json_response(response_json)
 
@@ -880,7 +886,12 @@ class AmazonAgentCoreConfig(BaseConfig, BaseAWSLLM):
         )
 
         if response.status_code != 200:
-            raise BedrockError(status_code=response.status_code, message=str(await response.aread()))
+            raise BedrockError(
+                status_code=response.status_code,
+                message=str(await response.aread()),
+                headers=response.headers,
+                response=response,
+            )
 
         # LOGGING
         logging_obj.post_call(
@@ -903,6 +914,7 @@ class AmazonAgentCoreConfig(BaseConfig, BaseAWSLLM):
                 raise BedrockError(
                     status_code=response.status_code,
                     message=f"AgentCore: Failed to read/parse JSON response body: {e}",
+                    headers=response.headers,
                 )
             parsed: Final = self._parse_json_response(response_json)
 
@@ -1031,6 +1043,7 @@ class AmazonAgentCoreConfig(BaseConfig, BaseAWSLLM):
             raise BedrockError(
                 message=f"Error processing response: {e}",
                 status_code=raw_response.status_code,
+                headers=raw_response.headers,
             )
 
     def validate_environment(
@@ -1046,7 +1059,7 @@ class AmazonAgentCoreConfig(BaseConfig, BaseAWSLLM):
         return headers
 
     def get_error_class(self, error_message: str, status_code: int, headers: dict | httpx.Headers) -> BaseLLMException:
-        return BedrockError(status_code=status_code, message=error_message)
+        return BedrockError(status_code=status_code, message=error_message, headers=headers)
 
     def should_fake_stream(
         self,

litellm/llms/bedrock/chat/converse_handler.py

@@ -22,7 +22,7 @@ from litellm.types.utils import ModelResponse
 from litellm.utils import CustomStreamWrapper
 
 from ..base_aws_llm import BaseAWSLLM, Credentials, bedrock_bearer_token
-from ..common_utils import BedrockError, _get_all_bedrock_regions
+from ..common_utils import BedrockError, _get_all_bedrock_regions, error_response_text
 from .invoke_handler import AWSEventStreamDecoder, MockResponseIterator, make_call
 
 
@@ -66,7 +66,12 @@ def make_sync_call(
     )
 
     if response.status_code != 200:
-        raise BedrockError(status_code=response.status_code, message=str(response.read()))
+        raise BedrockError(
+            status_code=response.status_code,
+            message=str(response.read()),
+            headers=response.headers,
+            response=response,
+        )
 
     if fake_stream:
         model_response: Final[ModelResponse] = litellm.AmazonConverseConfig()._transform_response(
@@ -247,7 +252,12 @@ class BedrockConverseLLM(BaseAWSLLM):
             response.raise_for_status()
         except httpx.HTTPStatusError as err:
             error_code: Final = err.response.status_code
-            raise BedrockError(status_code=error_code, message=err.response.text)
+            raise BedrockError(
+                status_code=error_code,
+                message=error_response_text(err.response),
+                headers=err.response.headers,
+                response=err.response,
+            )
         except httpx.TimeoutException:
             raise BedrockError(status_code=408, message="Timeout error occurred.")
 
@@ -594,7 +604,12 @@ class BedrockConverseLLM(BaseAWSLLM):
             response.raise_for_status()
         except httpx.HTTPStatusError as err:
             error_code: Final = err.response.status_code
-            raise BedrockError(status_code=error_code, message=err.response.text)
+            raise BedrockError(
+                status_code=error_code,
+                message=error_response_text(err.response),
+                headers=err.response.headers,
+                response=err.response,
+            )
         except httpx.TimeoutException:
             raise BedrockError(status_code=408, message="Timeout error occurred.")
 

litellm/llms/bedrock/chat/converse_transformation.py

@@ -2255,6 +2255,7 @@ class AmazonConverseConfig(BaseConfig):
             raise BedrockError(
                 message=f"Error converting to valid response block={e}. File an issue if litellm error - https://github.com/BerriAI/litellm/issues",
                 status_code=422,
+                headers=response.headers,
             )
 
         """

litellm/llms/bedrock/chat/invoke_agent/transformation.py

@@ -470,6 +470,7 @@ class AmazonInvokeAgentConfig(BaseConfig, BaseAWSLLM):
             raise BedrockError(
                 message=f"Error processing response: {e}",
                 status_code=raw_response.status_code,
+                headers=raw_response.headers,
             )
 
     def validate_environment(
@@ -485,7 +486,7 @@ class AmazonInvokeAgentConfig(BaseConfig, BaseAWSLLM):
         return headers
 
     def get_error_class(self, error_message: str, status_code: int, headers: dict | httpx.Headers) -> BaseLLMException:
-        return BedrockError(status_code=status_code, message=error_message)
+        return BedrockError(status_code=status_code, message=error_message, headers=headers)
 
     def should_fake_stream(
         self,

litellm/llms/bedrock/chat/invoke_handler.py

@@ -42,6 +42,7 @@ from litellm.types.utils import GenericStreamingChunk as GChunk
 from ..common_utils import (
     BedrockError,
     build_bedrock_stream_error,
+    error_response_text,
     get_bedrock_response_stream_shape,
     get_bedrock_tool_name,
 )
@@ -184,7 +185,12 @@ async def make_call(
         )
 
         if response.status_code != 200:
-            raise BedrockError(status_code=response.status_code, message=response.text)
+            raise BedrockError(
+                status_code=response.status_code,
+                message=error_response_text(response),
+                headers=response.headers,
+                response=response,
+            )
 
         if fake_stream:
             model_response: Final[ModelResponse] = litellm.AmazonConverseConfig()._transform_response(
@@ -228,9 +234,16 @@ async def make_call(
         )
 
         return completion_stream, response.headers
+    except BedrockError:
+        raise
     except httpx.HTTPStatusError as err:
         error_code: Final = err.response.status_code
-        raise BedrockError(status_code=error_code, message=err.response.text)
+        raise BedrockError(
+            status_code=error_code,
+            message=error_response_text(err.response),
+            headers=err.response.headers,
+            response=err.response,
+        )
     except httpx.TimeoutException:
         raise BedrockError(status_code=408, message="Timeout error occurred.")
     except Exception as e:
@@ -270,7 +283,12 @@ def make_sync_call(
         )
 
         if response.status_code != 200:
-            raise BedrockError(status_code=response.status_code, message=response.text)
+            raise BedrockError(
+                status_code=response.status_code,
+                message=error_response_text(response),
+                headers=response.headers,
+                response=response,
+            )
 
         if fake_stream:
             model_response: Final[ModelResponse] = litellm.AmazonConverseConfig()._transform_response(
@@ -314,9 +332,16 @@ def make_sync_call(
         )
 
         return completion_stream, response.headers
+    except BedrockError:
+        raise
     except httpx.HTTPStatusError as err:
         error_code: Final = err.response.status_code
-        raise BedrockError(status_code=error_code, message=err.response.text)
+        raise BedrockError(
+            status_code=error_code,
+            message=error_response_text(err.response),
+            headers=err.response.headers,
+            response=err.response,
+        )
     except httpx.TimeoutException:
         raise BedrockError(status_code=408, message="Timeout error occurred.")
     except Exception as e:

litellm/llms/bedrock/chat/invoke_transformations/amazon_moonshot_transformation.py

@@ -247,4 +247,4 @@ class AmazonMoonshotConfig(AmazonInvokeConfig, MoonshotChatConfig):
 
     def get_error_class(self, error_message: str, status_code: int, headers: dict | httpx.Headers) -> BedrockError:
         """Return the appropriate error class for Bedrock."""
-        return BedrockError(status_code=status_code, message=error_message)
+        return BedrockError(status_code=status_code, message=error_message, headers=headers)

litellm/llms/bedrock/chat/invoke_transformations/amazon_openai_transformation.py

@@ -182,4 +182,4 @@ class AmazonBedrockOpenAIConfig(OpenAIGPTConfig, BaseAWSLLM):
 
     def get_error_class(self, error_message: str, status_code: int, headers: dict | httpx.Headers) -> BedrockError:
         """Return the appropriate error class for Bedrock."""
-        return BedrockError(status_code=status_code, message=error_message)
+        return BedrockError(status_code=status_code, message=error_message, headers=headers)

litellm/llms/bedrock/chat/invoke_transformations/amazon_twelvelabs_pegasus_transformation.py

@@ -212,6 +212,7 @@ class AmazonTwelveLabsPegasusConfig(AmazonInvokeConfig, BaseConfig):
             raise BedrockError(
                 message=f"Error parsing response: {raw_response.text}, error: {e}",
                 status_code=raw_response.status_code,
+                headers=raw_response.headers,
             )
 
         verbose_logger.debug(
@@ -241,6 +242,7 @@ class AmazonTwelveLabsPegasusConfig(AmazonInvokeConfig, BaseConfig):
             raise BedrockError(
                 message=f"Error setting response content: {e}. Response: {completion_response}",
                 status_code=raw_response.status_code,
+                headers=raw_response.headers,
             )
 
         # Calculate usage from headers

litellm/llms/bedrock/chat/invoke_transformations/base_invoke_transformation.py

@@ -295,7 +295,11 @@ class AmazonInvokeConfig(BaseConfig, BaseAWSLLM):
         try:
             completion_response: Final = raw_response.json()
         except Exception:
-            raise BedrockError(message=raw_response.text, status_code=raw_response.status_code)
+            raise BedrockError(
+                message=raw_response.text,
+                status_code=raw_response.status_code,
+                headers=raw_response.headers,
+            )
         verbose_logger.debug(
             "bedrock invoke response % s",
             json.dumps(completion_response, indent=4, default=str),
@@ -363,6 +367,7 @@ class AmazonInvokeConfig(BaseConfig, BaseAWSLLM):
             raise BedrockError(
                 message=f"Error processing={raw_response.text}, Received error={e}",
                 status_code=422,
+                headers=raw_response.headers,
             )
 
         try:
@@ -384,6 +389,7 @@ class AmazonInvokeConfig(BaseConfig, BaseAWSLLM):
             raise BedrockError(
                 message=f"Error parsing received text={outputText}.\nError-{e}",
                 status_code=raw_response.status_code,
+                headers=raw_response.headers,
             )
 
         ## CALCULATING USAGE - bedrock returns usage in the headers
@@ -431,7 +437,7 @@ class AmazonInvokeConfig(BaseConfig, BaseAWSLLM):
         return merge_bedrock_invoke_headers(headers, guardrail_headers, metadata_headers, owned_names)
 
     def get_error_class(self, error_message: str, status_code: int, headers: dict | httpx.Headers) -> BaseLLMException:
-        return BedrockError(status_code=status_code, message=error_message)
+        return BedrockError(status_code=status_code, message=error_message, headers=headers)
 
     @track_llm_api_timing()
     async def get_async_custom_stream_wrapper(

litellm/llms/bedrock/claude_platform/common_utils.py

@@ -1,7 +1,10 @@
 from typing import Final
 
+import httpx
+
 import litellm
 from litellm.llms.bedrock.base_aws_llm import BaseAWSLLM
+from litellm.llms.bedrock.common_utils import BedrockError
 from litellm.secret_managers.main import get_secret_str
 
 CLAUDE_PLATFORM_SERVICE_NAME: Final = "aws-external-anthropic"
@@ -15,6 +18,14 @@ def strip_claude_platform_route(model: str) -> str:
 
 
 class BedrockClaudePlatformMixin(BaseAWSLLM):
+    def get_error_class(
+        self,
+        error_message: str,
+        status_code: int,
+        headers: dict[str, object] | httpx.Headers,  # mutable-ok: base passes response headers as a dict
+    ) -> BedrockError:
+        return BedrockError(status_code=status_code, message=error_message, headers=headers)
+
     @staticmethod
     def _get_workspace_id(optional_params: dict, litellm_params: dict) -> str | None:
         workspace_id = (

litellm/llms/bedrock/common_utils.py

@@ -33,8 +33,53 @@ if TYPE_CHECKING:
     from litellm.types.llms.openai import AllMessageValues
 
 
+_ERROR_REQUEST_URL: Final = "https://docs.litellm.ai/docs"
+
+
+def error_response_text(response: httpx.Response) -> str:
+    try:
+        return response.text
+    except httpx.ResponseNotRead:
+        return response.reason_phrase
+
+
+def _synthesize_error_response(
+    *, status_code: int, headers: dict[str, object] | httpx.Headers, request: httpx.Request | None
+) -> tuple[httpx.Request, httpx.Response]:
+    error_request: Final = request or httpx.Request(method="POST", url=_ERROR_REQUEST_URL)
+    safe_headers: Final = (
+        headers
+        if isinstance(headers, httpx.Headers)
+        else tuple((key, value) for key, value in headers.items() if isinstance(value, (str, bytes)))
+    )
+    return error_request, httpx.Response(status_code=status_code, headers=safe_headers, request=error_request)
+
+
 class BedrockError(BaseLLMException):
-    pass
+    def __init__(
+        self,
+        status_code: int,
+        message: str,
+        headers: dict[str, object] | httpx.Headers | None = None,
+        request: httpx.Request | None = None,
+        response: httpx.Response | None = None,
+        body: dict[str, object] | None = None,
+        status_code_is_synthesized: bool = False,
+    ) -> None:
+        error_request, error_response = (
+            _synthesize_error_response(status_code=status_code, headers=headers, request=request)
+            if response is None and headers
+            else (request, response)
+        )
+        super().__init__(
+            status_code=status_code,
+            message=message,
+            headers=headers,
+            request=error_request,
+            response=error_response,
+            body=body,
+            status_code_is_synthesized=status_code_is_synthesized,
+        )
 
 
 _BEDROCK_AWS_AUTH_PARAMETER_KEYS: Final[tuple[str, ...]] = (

litellm/llms/bedrock/count_tokens/handler.py

@@ -102,6 +102,8 @@ class BedrockCountTokensHandler(BedrockCountTokensConfig):
                 raise BedrockError(
                     status_code=response.status_code,
                     message=error_text,
+                    headers=response.headers,
+                    response=response,
                 )
 
             bedrock_response: Final = response.json()
@@ -124,6 +126,8 @@ class BedrockCountTokensHandler(BedrockCountTokensConfig):
             raise BedrockError(
                 status_code=e.response.status_code,
                 message=e.response.text,
+                headers=e.response.headers,
+                response=e.response,
             )
         except Exception as e:
             verbose_logger.error("Error in CountTokens handler: %s", e)

litellm/llms/bedrock/embed/embedding.py

@@ -132,7 +132,12 @@ class BedrockEmbedding(BaseAWSLLM):
             response.raise_for_status()
         except httpx.HTTPStatusError as err:
             error_code: Final = err.response.status_code
-            raise BedrockError(status_code=error_code, message=err.response.text)
+            raise BedrockError(
+                status_code=error_code,
+                message=err.response.text,
+                headers=err.response.headers,
+                response=err.response,
+            )
         except httpx.TimeoutException:
             raise BedrockError(status_code=408, message="Timeout error occurred.")
 
@@ -161,7 +166,12 @@ class BedrockEmbedding(BaseAWSLLM):
             response.raise_for_status()
         except httpx.HTTPStatusError as err:
             error_code: Final = err.response.status_code
-            raise BedrockError(status_code=error_code, message=err.response.text)
+            raise BedrockError(
+                status_code=error_code,
+                message=err.response.text,
+                headers=err.response.headers,
+                response=err.response,
+            )
         except httpx.TimeoutException:
             raise BedrockError(status_code=408, message="Timeout error occurred.")
 

litellm/llms/bedrock/image_edit/amazon_nova_canvas_image_edit_transformation.py

@@ -20,6 +20,7 @@ import httpx
 
 from litellm._logging import verbose_logger
 from litellm.llms.base_llm.image_edit.transformation import BaseImageEditConfig
+from litellm.llms.bedrock.common_utils import BedrockError
 from litellm.types.images.main import ImageEditOptionalRequestParams
 from litellm.types.router import GenericLiteLLMParams
 from litellm.types.utils import FileTypes, ImageObject, ImageResponse
@@ -228,6 +229,14 @@ class BedrockAmazonNovaCanvasImageEditConfig(BaseImageEditConfig):
         """
         return _supports_nova_canvas_image_edit_from_model_cost(model or "")
 
+    def get_error_class(
+        self,
+        error_message: str,
+        status_code: int,
+        headers: dict[str, object] | httpx.Headers,  # mutable-ok: base passes response headers as a dict
+    ) -> BedrockError:
+        return BedrockError(status_code=status_code, message=error_message, headers=headers)
+
     def get_supported_openai_params(self, model: str) -> list:
         return [
             "n",

litellm/llms/bedrock/image_edit/handler.py

@@ -114,7 +114,12 @@ class BedrockImageEdit(BaseAWSLLM):
             response.raise_for_status()
         except httpx.HTTPStatusError as err:
             error_code: Final = err.response.status_code
-            raise BedrockError(status_code=error_code, message=err.response.text)
+            raise BedrockError(
+                status_code=error_code,
+                message=err.response.text,
+                headers=err.response.headers,
+                response=err.response,
+            )
         except httpx.TimeoutException:
             raise BedrockError(status_code=408, message="Timeout error occurred.")
 
@@ -156,7 +161,12 @@ class BedrockImageEdit(BaseAWSLLM):
             response.raise_for_status()
         except httpx.HTTPStatusError as err:
             error_code: Final = err.response.status_code
-            raise BedrockError(status_code=error_code, message=err.response.text)
+            raise BedrockError(
+                status_code=error_code,
+                message=err.response.text,
+                headers=err.response.headers,
+                response=err.response,
+            )
         except httpx.TimeoutException:
             raise BedrockError(status_code=408, message="Timeout error occurred.")
 

litellm/llms/bedrock/image_edit/stability_transformation.py

@@ -27,6 +27,7 @@ from typing import TYPE_CHECKING, Any, Final
 import httpx
 
 from litellm.llms.base_llm.image_edit.transformation import BaseImageEditConfig
+from litellm.llms.bedrock.common_utils import BedrockError
 from litellm.types.images.main import ImageEditOptionalRequestParams
 from litellm.types.llms.stability import (
     OPENAI_SIZE_TO_STABILITY_ASPECT_RATIO,
@@ -84,6 +85,14 @@ class BedrockStabilityImageEditConfig(BaseImageEditConfig):
                 return True
         return False
 
+    def get_error_class(
+        self,
+        error_message: str,
+        status_code: int,
+        headers: dict[str, object] | httpx.Headers,  # mutable-ok: base passes response headers as a dict
+    ) -> BedrockError:
+        return BedrockError(status_code=status_code, message=error_message, headers=headers)
+
     def get_supported_openai_params(self, model: str) -> list:
         """
         Return list of OpenAI params supported by Bedrock Stability.

litellm/llms/bedrock/image_generation/image_handler.py

@@ -119,7 +119,12 @@ class BedrockImageGeneration(BaseAWSLLM):
             response.raise_for_status()
         except httpx.HTTPStatusError as err:
             error_code: Final = err.response.status_code
-            raise BedrockError(status_code=error_code, message=err.response.text)
+            raise BedrockError(
+                status_code=error_code,
+                message=err.response.text,
+                headers=err.response.headers,
+                response=err.response,
+            )
         except httpx.TimeoutException:
             raise BedrockError(status_code=408, message="Timeout error occurred.")
         ### FORMAT RESPONSE TO OPENAI FORMAT ###
@@ -162,7 +167,12 @@ class BedrockImageGeneration(BaseAWSLLM):
             response.raise_for_status()
         except httpx.HTTPStatusError as err:
             error_code: Final = err.response.status_code
-            raise BedrockError(status_code=error_code, message=err.response.text)
+            raise BedrockError(
+                status_code=error_code,
+                message=err.response.text,
+                headers=err.response.headers,
+                response=err.response,
+            )
         except httpx.TimeoutException:
             raise BedrockError(status_code=408, message="Timeout error occurred.")
 

litellm/llms/bedrock/messages/invoke_transformations/anthropic_claude3_transformation.py

@@ -29,6 +29,7 @@ from litellm.llms.bedrock.chat.invoke_transformations.base_invoke_transformation
     AmazonInvokeConfig,
 )
 from litellm.llms.bedrock.common_utils import (
+    BedrockError,
     apply_bedrock_invoke_structured_output,
     ensure_bedrock_anthropic_messages_tool_names,
     get_anthropic_beta_from_headers,
@@ -79,6 +80,14 @@ class AmazonAnthropicClaudeMessagesConfig(
 
     BEDROCK_INVOKE_ALLOWED_TOP_LEVEL_FIELDS = frozenset(BedrockInvokeAnthropicMessagesRequest.__annotations__.keys())
 
+    def get_error_class(
+        self,
+        error_message: str,
+        status_code: int,
+        headers: dict[str, object] | httpx.Headers,  # mutable-ok: base passes response headers as a dict
+    ) -> BedrockError:
+        return BedrockError(status_code=status_code, message=error_message, headers=headers)
+
     def __init__(self, **kwargs):
         BaseAnthropicMessagesConfig.__init__(self, **kwargs)
         AmazonInvokeConfig.__init__(self, **kwargs)

litellm/llms/bedrock/passthrough/transformation.py

@@ -2,13 +2,14 @@ import json
 from collections.abc import Mapping
 from typing import TYPE_CHECKING, Final, Optional, cast
 
+import httpx
 from httpx import Response
 
 from litellm.litellm_core_utils.litellm_logging import Logging
 from litellm.llms.base_llm.passthrough.transformation import BasePassthroughConfig
 
 from ..base_aws_llm import BaseAWSLLM
-from ..common_utils import BedrockEventStreamDecoderBase, BedrockModelInfo
+from ..common_utils import BedrockError, BedrockEventStreamDecoderBase, BedrockModelInfo
 
 if TYPE_CHECKING:
     from httpx import URL
@@ -18,6 +19,14 @@ if TYPE_CHECKING:
 
 
 class BedrockPassthroughConfig(BaseAWSLLM, BedrockModelInfo, BedrockEventStreamDecoderBase, BasePassthroughConfig):
+    def get_error_class(
+        self,
+        error_message: str,
+        status_code: int,
+        headers: dict[str, object] | httpx.Headers,  # mutable-ok: base passes response headers as a dict
+    ) -> BedrockError:
+        return BedrockError(status_code=status_code, message=error_message, headers=headers)
+
     def is_streaming_request(self, endpoint: str, request_data: dict) -> bool:
         return "stream" in endpoint
 

litellm/llms/bedrock/realtime/transformation.py

@@ -9,12 +9,14 @@ import json
 import uuid as uuid_lib
 from typing import Final, cast
 
+import httpx
 from pydantic import BaseModel
 
 from litellm._logging import verbose_logger
 from litellm._uuid import uuid
 from litellm.litellm_core_utils.litellm_logging import Logging as LiteLLMLoggingObj
 from litellm.llms.base_llm.realtime.transformation import BaseRealtimeConfig
+from litellm.llms.bedrock.common_utils import BedrockError
 from litellm.llms.bedrock.realtime.trigger_audio import ready_trigger_pcm
 from litellm.types.llms.openai import (
     OpenAIRealtimeContentPartDone,
@@ -121,6 +123,14 @@ class BedrockRealtimeConfig(BaseRealtimeConfig):
         self._cumulative_usage = BedrockUsageEvent()
         self._reported_usage = BedrockUsageEvent()
 
+    def get_error_class(
+        self,
+        error_message: str,
+        status_code: int,
+        headers: dict[str, object] | httpx.Headers,  # mutable-ok: base passes response headers as a dict
+    ) -> BedrockError:
+        return BedrockError(status_code=status_code, message=error_message, headers=headers)
+
     def validate_environment(self, headers: dict, model: str, api_key: str | None = None) -> dict:
         """Validate environment - no special validation needed for Bedrock."""
         return headers

litellm/llms/bedrock/rerank/handler.py

@@ -46,7 +46,12 @@ class BedrockRerankHandler(BaseAWSLLM):
             response.raise_for_status()
         except httpx.HTTPStatusError as err:
             error_code: Final = err.response.status_code
-            raise BedrockError(status_code=error_code, message=err.response.text)
+            raise BedrockError(
+                status_code=error_code,
+                message=err.response.text,
+                headers=err.response.headers,
+                response=err.response,
+            )
         except httpx.TimeoutException:
             raise BedrockError(status_code=408, message="Timeout error occurred.")
 
@@ -117,7 +122,12 @@ class BedrockRerankHandler(BaseAWSLLM):
             response.raise_for_status()
         except httpx.HTTPStatusError as err:
             error_code: Final = err.response.status_code
-            raise BedrockError(status_code=error_code, message=err.response.text)
+            raise BedrockError(
+                status_code=error_code,
+                message=err.response.text,
+                headers=err.response.headers,
+                response=err.response,
+            )
         except httpx.TimeoutException:
             raise BedrockError(status_code=408, message="Timeout error occurred.")
 

litellm/llms/bedrock/search/transformation.py

@@ -39,7 +39,6 @@ from typing import Final
 import httpx
 
 from litellm.litellm_core_utils.litellm_logging import Logging as LiteLLMLoggingObj
-from litellm.llms.base_llm.chat.transformation import BaseLLMException
 from litellm.llms.base_llm.search.transformation import (
     BaseSearchConfig,
     SearchResponse,
@@ -380,6 +379,7 @@ class AgentCoreSearchConfig(BaseSearchConfig, BaseAWSLLM):
             raise BedrockError(
                 status_code=raw_response.status_code if raw_response.status_code >= 400 else 502,
                 message=f"AgentCore gateway MCP error: {error}",
+                headers=raw_response.headers,
             )
 
         # A failed tools/call is reported in-band, as HTTP 200 with result.isError
@@ -389,6 +389,7 @@ class AgentCoreSearchConfig(BaseSearchConfig, BaseAWSLLM):
             raise BedrockError(
                 status_code=raw_response.status_code if raw_response.status_code >= 400 else 502,
                 message=f"AgentCore web search tool error: {self._tool_error_message(response_json)}",
+                headers=raw_response.headers,
             )
 
         text_items: Final = tuple(
@@ -440,6 +441,7 @@ class AgentCoreSearchConfig(BaseSearchConfig, BaseAWSLLM):
         raise BedrockError(
             status_code=502,
             message=f"AgentCore gateway returned SSE without a JSON data frame: {text[:200]}",
+            headers=raw_response.headers,
         )
 
     def get_error_class(
@@ -448,7 +450,7 @@ class AgentCoreSearchConfig(BaseSearchConfig, BaseAWSLLM):
         status_code: int,
         headers: dict,  # mutable-ok: BaseSearchConfig.get_error_class takes the response headers as a dict
     ) -> Exception:
-        return BaseLLMException(
+        return BedrockError(
             status_code=status_code,
             message=error_message,
             headers=headers,

litellm/llms/bedrock/vector_stores/transformation.py

@@ -8,6 +8,7 @@ from litellm._logging import verbose_logger
 from litellm.litellm_core_utils.url_utils import encode_url_path_segment
 from litellm.llms.base_llm.vector_store.transformation import BaseVectorStoreConfig
 from litellm.llms.bedrock.base_aws_llm import BaseAWSLLM
+from litellm.llms.bedrock.common_utils import BedrockError
 from litellm.types.integrations.rag.bedrock_knowledgebase import (
     BedrockKBContent,
     BedrockKBResponse,
@@ -38,6 +39,14 @@ class BedrockVectorStoreConfig(BaseVectorStoreConfig, BaseAWSLLM):
         BaseVectorStoreConfig.__init__(self)
         BaseAWSLLM.__init__(self)
 
+    def get_error_class(
+        self,
+        error_message: str,
+        status_code: int,
+        headers: dict[str, object] | httpx.Headers,  # mutable-ok: base passes response headers as a dict
+    ) -> BedrockError:
+        return BedrockError(status_code=status_code, message=error_message, headers=headers)
+
     def get_auth_credentials(self, litellm_params: dict) -> BaseVectorStoreAuthCredentials:
         return {}
 

litellm/llms/bedrock_mantle/chat/transformation.py

@@ -13,6 +13,8 @@ Auth: Bearer token (litellm_params.api_key, BEDROCK_MANTLE_API_KEY, or the
 from collections.abc import AsyncIterator, Iterator
 from typing import Any, Final
 
+import httpx
+
 import litellm
 from litellm._logging import verbose_logger
 from litellm.llms.bedrock.base_aws_llm import BaseAWSLLM
@@ -24,6 +26,8 @@ from litellm.secret_managers.main import get_secret_str
 from litellm.types.llms.openai import AllMessageValues
 from litellm.types.router import GenericLiteLLMParams
 
+from ...base_llm.chat.transformation import BaseLLMException
+from ...bedrock.common_utils import BedrockError
 from ...openai_like.chat.transformation import OpenAILikeChatConfig
 from ..common_utils import mantle_base_segment
 
@@ -45,6 +49,11 @@ class BedrockMantleChatConfig(BedrockMantleAuthMixin, OpenAILikeChatConfig):
     def get_config(cls):
         return super().get_config()
 
+    def get_error_class(
+        self, error_message: str, status_code: int, headers: dict[str, object] | httpx.Headers
+    ) -> BaseLLMException:
+        return BedrockError(status_code=status_code, message=error_message, headers=headers)
+
     def _get_openai_compatible_provider_info(
         self,
         api_base: str | None,

litellm/llms/bedrock_mantle/responses/transformation.py

@@ -19,11 +19,14 @@ import json
 from collections.abc import Mapping
 from typing import Any, Final
 
+import httpx
 from typing_extensions import ReadOnly, TypedDict
 
 import litellm
 from litellm._logging import verbose_logger
+from litellm.llms.base_llm.chat.transformation import BaseLLMException
 from litellm.llms.bedrock.base_aws_llm import BaseAWSLLM
+from litellm.llms.bedrock.common_utils import BedrockError
 from litellm.llms.bedrock_mantle.common_utils import (
     MANTLE_HOST_RE,
     BedrockMantleAuthMixin,
@@ -98,6 +101,11 @@ class BedrockMantleResponsesAPIConfig(BedrockMantleAuthMixin, OpenAIResponsesAPI
     def custom_llm_provider(self) -> LlmProviders:
         return LlmProviders.BEDROCK_MANTLE
 
+    def get_error_class(
+        self, error_message: str, status_code: int, headers: dict[str, object] | httpx.Headers
+    ) -> BaseLLMException:
+        return BedrockError(status_code=status_code, message=error_message, headers=headers)
+
     def get_complete_url(
         self,
         api_base: str | None,

litellm/proxy/common_request_processing.py

@@ -3508,9 +3508,13 @@ class ProxyBaseLLMRequestProcessing:
             error_body: Final = await http_status_error.response.aread()
             error_text: Final = error_body.decode("utf-8")
 
+            error_headers: Final = {  # mutable-ok: HTTPException takes a plain header dict
+                k: v if isinstance(v, str) else str(v) for k, v in safe_headers.items()
+            }
             raise HTTPException(
                 status_code=http_status_error.response.status_code,
                 detail={"error": error_text},
+                headers=error_headers,
             )
         error_msg: Final = f"{e}"
         # Check for AttributeError in the exception chain.

litellm/proxy/pass_through_endpoints/llm_passthrough_endpoints.py

@@ -947,7 +947,14 @@ async def handle_bedrock_count_tokens(
     except BedrockError as e:
         # Convert BedrockError to HTTPException for FastAPI
         verbose_proxy_logger.error("BedrockError in handle_bedrock_count_tokens: %s", e)
-        raise HTTPException(status_code=e.status_code, detail={"error": e.message})
+        from litellm.litellm_core_utils.llm_response_utils.get_headers import get_response_headers
+
+        provider_headers: Final = getattr(getattr(e, "response", None), "headers", None)
+        raise HTTPException(
+            status_code=e.status_code,
+            detail={"error": e.message},
+            headers=get_response_headers(provider_headers) if provider_headers else None,
+        )
     except HTTPException:
         # Re-raise HTTP exceptions as-is
         raise

tests/test_litellm/litellm_core_utils/test_exception_mapping_utils.py

@@ -9,9 +9,11 @@ import litellm
 from litellm.litellm_core_utils.exception_mapping_utils import (
     ExceptionCheckers,
     _get_body_error_code,
+    _get_response_headers,
     exception_type,
     extract_and_raise_litellm_exception,
 )
+from litellm.llms.bedrock.common_utils import BedrockError
 from litellm.llms.openai.common_utils import OpenAIError
 from litellm.types.utils import LlmProviders
 
@@ -1254,3 +1256,156 @@ def test_handle_error_marks_only_a_status_code_it_never_received():
         raise handler._handle_error(e=upstream, provider_config=None)
     assert received.value.status_code == 500
     assert received.value.status_code_is_synthesized is False
+
+
+def test_bedrock_500_preserves_provider_response_headers():
+    """A Bedrock 5xx must keep x-amzn-RequestId so AWS support can trace it (LIT-5428)."""
+    provider_response = httpx.Response(
+        status_code=500,
+        headers={"x-amzn-RequestId": "req-map-500"},
+        text='{"message":"Amazon Bedrock is unable to process your request."}',
+        request=httpx.Request("POST", "https://bedrock-runtime.us-east-1.amazonaws.com/"),
+    )
+    original_exception = BedrockError(
+        status_code=500,
+        message=provider_response.text,
+        headers=provider_response.headers,
+        response=provider_response,
+    )
+
+    with pytest.raises(litellm.ServiceUnavailableError) as exc_info:
+        exception_type(
+            model="anthropic.claude-haiku-4-5-20251001-v1:0",
+            original_exception=original_exception,
+            custom_llm_provider="bedrock",
+            completion_kwargs={},
+            extra_kwargs={},
+        )
+
+    assert exc_info.value.response.headers["x-amzn-requestid"] == "req-map-500"
+
+
+@pytest.mark.parametrize(
+    "custom_llm_provider, status_code, provider_message, expected_exception",
+    [
+        (
+            "bedrock_mantle",
+            400,
+            (
+                '{"error":{"code":"validation_error",'
+                '"message":"prompt tokens (1055489) exceed model maximum (1050000) for openai.gpt-5.6-sol",'
+                '"param":null,"type":"invalid_request_error"}}'
+            ),
+            litellm.ContextWindowExceededError,
+        ),
+        (
+            "bedrock",
+            400,
+            '{"message":"Input is too long for requested model."}',
+            litellm.ContextWindowExceededError,
+        ),
+        (
+            "bedrock",
+            400,
+            '{"message":"Could not process image"}',
+            litellm.InternalServerError,
+        ),
+    ],
+)
+def test_bedrock_classified_errors_preserve_provider_response_headers(
+    custom_llm_provider, status_code, provider_message, expected_exception
+):
+    """Branches that classify a Bedrock error by its text must keep x-amzn-RequestId (LIT-5428)."""
+    provider_response = httpx.Response(
+        status_code=status_code,
+        headers={"x-amzn-RequestId": "req-classified"},
+        text=provider_message,
+        request=httpx.Request("POST", "https://bedrock-runtime.us-east-1.amazonaws.com/"),
+    )
+    original_exception = BedrockError(
+        status_code=status_code,
+        message=provider_message,
+        headers=provider_response.headers,
+        response=provider_response,
+    )
+
+    with pytest.raises(expected_exception) as exc_info:
+        exception_type(
+            model="anthropic.claude-haiku-4-5-20251001-v1:0",
+            original_exception=original_exception,
+            custom_llm_provider=custom_llm_provider,
+            completion_kwargs={},
+            extra_kwargs={},
+        )
+
+    assert exc_info.value.response.headers["x-amzn-requestid"] == "req-classified"
+
+
+@pytest.mark.parametrize(
+    "status_code, provider_message",
+    [
+        (504, '{"message":"Gateway timeout"}'),
+        (408, '{"message":"Bedrock did not answer in time"}'),
+        (408, '{"message":"Connect timeout on endpoint URL"}'),
+    ],
+)
+def test_bedrock_timeout_mapping_preserves_provider_headers(status_code, provider_message):
+    """A mapped bedrock timeout keeps the upstream response, like every other mapped bedrock error.
+
+    The proxy prefixes those headers on the way out, while retry and cooldown
+    logic still reads the raw retry-after off the response.
+    """
+    provider_response = httpx.Response(
+        status_code=status_code,
+        headers={"x-amzn-RequestId": "req-timeout", "set-cookie": "session=attacker"},
+        text=provider_message,
+        request=httpx.Request("POST", "https://bedrock-runtime.us-east-1.amazonaws.com/"),
+    )
+    original_exception = BedrockError(
+        status_code=status_code,
+        message=provider_message,
+        headers=provider_response.headers,
+        response=provider_response,
+    )
+
+    with pytest.raises(litellm.Timeout) as exc_info:
+        exception_type(
+            model="anthropic.claude-haiku-4-5-20251001-v1:0",
+            original_exception=original_exception,
+            custom_llm_provider="bedrock",
+            completion_kwargs={},
+            extra_kwargs={},
+        )
+
+    assert exc_info.value.response.headers["x-amzn-requestid"] == "req-timeout"
+    assert exc_info.value.headers is None
+
+
+@pytest.mark.parametrize("status_code", [504, 408])
+def test_bedrock_timeout_mapping_keeps_retry_after_readable(status_code):
+    """Cooldown and retry timing read retry-after through _get_response_headers."""
+    provider_response = httpx.Response(
+        status_code=status_code,
+        headers={"x-amzn-RequestId": "req-retry-after", "retry-after": "7"},
+        text='{"message":"Bedrock did not answer in time"}',
+        request=httpx.Request("POST", "https://bedrock-runtime.us-east-1.amazonaws.com/"),
+    )
+    original_exception = BedrockError(
+        status_code=status_code,
+        message='{"message":"Bedrock did not answer in time"}',
+        headers=provider_response.headers,
+        response=provider_response,
+    )
+
+    with pytest.raises(litellm.Timeout) as exc_info:
+        exception_type(
+            model="anthropic.claude-haiku-4-5-20251001-v1:0",
+            original_exception=original_exception,
+            custom_llm_provider="bedrock",
+            completion_kwargs={},
+            extra_kwargs={},
+        )
+
+    exception_headers = _get_response_headers(original_exception=exc_info.value)
+    assert exception_headers is not None
+    assert litellm.utils._get_retry_after_from_exception_header(response_headers=exception_headers) == 7

tests/test_litellm/llms/bedrock/chat/invoke_transformations/test_base_invoke_transformation.py

@@ -177,3 +177,16 @@ def test_guardrail_config_flows_to_headers_not_request_body(model):
     assert headers["X-Amzn-Bedrock-GuardrailIdentifier"] == "ff6ujrregl1q"
     assert headers["X-Amzn-Bedrock-GuardrailVersion"] == "DRAFT"
     assert headers["X-Amzn-Bedrock-Trace"] == "DISABLED"
+
+
+def test_get_error_class_preserves_provider_headers():
+    """The invoke handler path hands real provider headers to get_error_class (LIT-5428)."""
+    error = AmazonInvokeConfig().get_error_class(
+        error_message="Amazon Bedrock is unable to process your request.",
+        status_code=500,
+        headers={"x-amzn-RequestId": "req-invoke-500"},
+    )
+
+    assert isinstance(error, BedrockError)
+    assert error.headers == {"x-amzn-RequestId": "req-invoke-500"}
+    assert error.response.headers["x-amzn-requestid"] == "req-invoke-500"

tests/test_litellm/llms/bedrock/chat/test_converse_transformation.py

@@ -2,6 +2,7 @@ import asyncio
 import json
 import os
 
+import httpx
 import pytest
 from fastapi.testclient import TestClient
 
@@ -6039,6 +6040,8 @@ def test_transform_response_does_not_leak_body_on_parse_failure():
     leaky_body = {"output": {"message": {"content": [{"text": "secret content"}]}}}
 
     class MockResponse:
+        headers = httpx.Headers({"x-amzn-RequestId": "req-parse-failure"})
+
         def json(self):
             return leaky_body
 
@@ -6067,6 +6070,7 @@ def test_transform_response_does_not_leak_body_on_parse_failure():
     msg = str(exc_info.value)
     assert "secret content" not in msg
     assert "Error converting to valid response block" in msg
+    assert exc_info.value.response.headers["x-amzn-requestid"] == "req-parse-failure"
 
 
 def test_converse_drops_sampling_params_for_models_that_removed_them():

tests/test_litellm/llms/bedrock/chat/test_invoke_handler.py

@@ -496,3 +496,171 @@ async def test_async_invoke_streaming_forwards_bedrock_response_headers():
 
     assert stream._hidden_params["additional_headers"]["llm_provider-x-amzn-requestid"] == "req-987"
 
+
+def _bedrock_stream_error_response(status_code: int, request_id: str) -> httpx.Response:
+    return httpx.Response(
+        status_code=status_code,
+        headers={
+            "x-amzn-RequestId": request_id,
+            "x-amzn-ErrorType": "InternalServerException",
+        },
+        text='{"message":"Amazon Bedrock is unable to process your request."}',
+        request=httpx.Request("POST", "https://bedrock-runtime.us-east-1.amazonaws.com/"),
+    )
+
+
+def test_invoke_streaming_error_forwards_bedrock_response_headers():
+    error_response = _bedrock_stream_error_response(500, "req-stream-err-1")
+    client = HTTPHandler()
+    client.post = MagicMock(
+        side_effect=httpx.HTTPStatusError(
+            "server error",
+            request=error_response.request,
+            response=error_response,
+        )
+    )
+
+    with pytest.raises(litellm.ServiceUnavailableError) as exc_info:
+        litellm.completion(
+            model="bedrock/invoke/anthropic.claude-haiku-4-5-20251001-v1:0",
+            messages=[{"role": "user", "content": "hi"}],
+            stream=True,
+            client=client,
+            aws_access_key_id="fake",
+            aws_secret_access_key="fake",
+            aws_region_name="us-east-1",
+        )
+
+    assert exc_info.value.response.headers["x-amzn-requestid"] == "req-stream-err-1"
+
+
+@pytest.mark.asyncio
+async def test_async_invoke_streaming_error_forwards_bedrock_response_headers():
+    error_response = _bedrock_stream_error_response(500, "req-stream-err-2")
+    client = AsyncHTTPHandler()
+    client.post = AsyncMock(
+        side_effect=httpx.HTTPStatusError(
+            "server error",
+            request=error_response.request,
+            response=error_response,
+        )
+    )
+
+    with pytest.raises(litellm.ServiceUnavailableError) as exc_info:
+        await litellm.acompletion(
+            model="bedrock/invoke/anthropic.claude-haiku-4-5-20251001-v1:0",
+            messages=[{"role": "user", "content": "hi"}],
+            stream=True,
+            client=client,
+            aws_access_key_id="fake",
+            aws_secret_access_key="fake",
+            aws_region_name="us-east-1",
+        )
+
+    assert exc_info.value.response.headers["x-amzn-requestid"] == "req-stream-err-2"
+
+
+def _unread_bedrock_stream_error_response(status_code: int, request_id: str) -> httpx.Response:
+    return httpx.Response(
+        status_code=status_code,
+        headers={
+            "x-amzn-RequestId": request_id,
+            "x-amzn-ErrorType": "InternalServerException",
+        },
+        stream=httpx.ByteStream(b'{"message":"Amazon Bedrock is unable to process your request."}'),
+        request=httpx.Request("POST", "https://bedrock-runtime.us-east-1.amazonaws.com/"),
+    )
+
+
+def test_invoke_streaming_error_forwards_headers_when_body_was_never_read():
+    """A retried streamed request raises HTTPStatusError over a body nobody read, so
+    reading it for the error message throws and loses the request id (LIT-5428)."""
+    error_response = _unread_bedrock_stream_error_response(500, "req-unread-sync")
+    client = HTTPHandler()
+    client.post = MagicMock(
+        side_effect=httpx.HTTPStatusError(
+            "server error",
+            request=error_response.request,
+            response=error_response,
+        )
+    )
+
+    with pytest.raises(litellm.ServiceUnavailableError) as exc_info:
+        litellm.completion(
+            model="bedrock/invoke/anthropic.claude-haiku-4-5-20251001-v1:0",
+            messages=[{"role": "user", "content": "hi"}],
+            stream=True,
+            client=client,
+            aws_access_key_id="fake",
+            aws_secret_access_key="fake",
+            aws_region_name="us-east-1",
+        )
+
+    assert exc_info.value.response.headers["x-amzn-requestid"] == "req-unread-sync"
+
+
+@pytest.mark.asyncio
+async def test_async_invoke_streaming_error_forwards_headers_when_body_was_never_read():
+    error_response = _unread_bedrock_stream_error_response(500, "req-unread-async")
+    client = AsyncHTTPHandler()
+    client.post = AsyncMock(
+        side_effect=httpx.HTTPStatusError(
+            "server error",
+            request=error_response.request,
+            response=error_response,
+        )
+    )
+
+    with pytest.raises(litellm.ServiceUnavailableError) as exc_info:
+        await litellm.acompletion(
+            model="bedrock/invoke/anthropic.claude-haiku-4-5-20251001-v1:0",
+            messages=[{"role": "user", "content": "hi"}],
+            stream=True,
+            client=client,
+            aws_access_key_id="fake",
+            aws_secret_access_key="fake",
+            aws_region_name="us-east-1",
+        )
+
+    assert exc_info.value.response.headers["x-amzn-requestid"] == "req-unread-async"
+
+
+def test_invoke_streaming_non_200_forwards_bedrock_response_headers():
+    """A caller-supplied client that returns a failure instead of raising still reaches the
+    provider's headers, and reading the streamed body for the message must not throw (LIT-5428)."""
+    error_response = _unread_bedrock_stream_error_response(500, "req-non200-sync")
+    client = HTTPHandler()
+    client.post = MagicMock(return_value=error_response)
+
+    with pytest.raises(litellm.ServiceUnavailableError) as exc_info:
+        litellm.completion(
+            model="bedrock/invoke/anthropic.claude-haiku-4-5-20251001-v1:0",
+            messages=[{"role": "user", "content": "hi"}],
+            stream=True,
+            client=client,
+            aws_access_key_id="fake",
+            aws_secret_access_key="fake",
+            aws_region_name="us-east-1",
+        )
+
+    assert exc_info.value.response.headers["x-amzn-requestid"] == "req-non200-sync"
+
+
+@pytest.mark.asyncio
+async def test_async_invoke_streaming_non_200_forwards_bedrock_response_headers():
+    error_response = _unread_bedrock_stream_error_response(500, "req-non200-async")
+    client = AsyncHTTPHandler()
+    client.post = AsyncMock(return_value=error_response)
+
+    with pytest.raises(litellm.ServiceUnavailableError) as exc_info:
+        await litellm.acompletion(
+            model="bedrock/invoke/anthropic.claude-haiku-4-5-20251001-v1:0",
+            messages=[{"role": "user", "content": "hi"}],
+            stream=True,
+            client=client,
+            aws_access_key_id="fake",
+            aws_secret_access_key="fake",
+            aws_region_name="us-east-1",
+        )
+
+    assert exc_info.value.response.headers["x-amzn-requestid"] == "req-non200-async"

tests/test_litellm/llms/bedrock/test_bedrock_common_utils.py

@@ -614,3 +614,260 @@ def test_sign_aws_request_assumes_role_with_external_id(monkeypatch):
     authorization = {key.lower(): value for key, value in signed_headers.items()}["authorization"]
     assert "ASIABATCHSIGNROLE" in authorization
     assert signed_data == b'{"jobName": "litellm-batch-job"}'
+
+
+# --------------------------------------------------------------------------- #
+# Provider error headers (LIT-5428)                                            #
+# --------------------------------------------------------------------------- #
+
+
+def _bedrock_chat_error_configs():
+    from litellm.llms.bedrock.chat.agentcore.transformation import AmazonAgentCoreConfig
+    from litellm.llms.bedrock.chat.converse_transformation import AmazonConverseConfig
+    from litellm.llms.bedrock.chat.invoke_agent.transformation import AmazonInvokeAgentConfig
+    from litellm.llms.bedrock.chat.invoke_transformations.amazon_moonshot_transformation import (
+        AmazonMoonshotConfig,
+    )
+    from litellm.llms.bedrock.chat.invoke_transformations.amazon_openai_transformation import (
+        AmazonBedrockOpenAIConfig,
+    )
+    from litellm.llms.bedrock.chat.invoke_transformations.base_invoke_transformation import (
+        AmazonInvokeConfig,
+    )
+
+    return [
+        AmazonInvokeConfig,
+        AmazonConverseConfig,
+        AmazonMoonshotConfig,
+        AmazonBedrockOpenAIConfig,
+        AmazonAgentCoreConfig,
+        AmazonInvokeAgentConfig,
+    ]
+
+
+@pytest.mark.parametrize("config", _bedrock_chat_error_configs())
+def test_bedrock_chat_get_error_class_keeps_provider_headers(config):
+    """Every Bedrock chat route must carry x-amzn-RequestId out to the caller (LIT-5428).
+
+    A config that drops the headers it is handed shadows the fix for its own models.
+    """
+    error = config().get_error_class(
+        error_message="Amazon Bedrock is unable to process your request.",
+        status_code=500,
+        headers={"x-amzn-RequestId": "req-chat-500"},
+    )
+
+    assert error.response.headers["x-amzn-requestid"] == "req-chat-500"
+
+
+def test_error_response_text_reads_a_read_response():
+    import httpx
+
+    from litellm.llms.bedrock.common_utils import error_response_text
+
+    response = httpx.Response(status_code=500, text="Amazon Bedrock is unable to process your request.")
+
+    assert error_response_text(response) == "Amazon Bedrock is unable to process your request."
+
+
+def test_error_response_text_falls_back_when_a_streamed_response_was_never_read():
+    """A retried streamed request raises HTTPStatusError over an unread body; reading it
+    throws ResponseNotRead and would lose the status and headers this fix preserves."""
+    import httpx
+
+    from litellm.llms.bedrock.common_utils import error_response_text
+
+    request = httpx.Request(method="POST", url="https://bedrock-runtime.amazonaws.com")
+    response = httpx.Response(
+        status_code=500,
+        headers={"x-amzn-RequestId": "req-unread-500"},
+        stream=httpx.ByteStream(b"never read"),
+        request=request,
+    )
+
+    with pytest.raises(httpx.ResponseNotRead):
+        _ = response.text
+
+    assert error_response_text(response) == "Internal Server Error"
+
+
+def test_bedrock_error_skips_header_values_httpx_cannot_carry():
+    """The shared HTTP handler copies an arbitrary exception's header values in verbatim,
+    so a non-str value must not take down the whole error (LIT-5428)."""
+    import httpx
+
+    from litellm.llms.bedrock.common_utils import BedrockError
+
+    error = BedrockError(
+        status_code=500,
+        message="boom",
+        headers={"x-amzn-RequestId": "req-mixed-500", "x-retry-count": 3, "x-nothing": None},
+    )
+
+    assert error.response.headers["x-amzn-requestid"] == "req-mixed-500"
+    assert "x-retry-count" not in error.response.headers
+    assert isinstance(error.response, httpx.Response)
+
+
+def test_bedrock_error_keeps_duplicate_httpx_header_values():
+    import httpx
+
+    from litellm.llms.bedrock.common_utils import BedrockError
+
+    error = BedrockError(
+        status_code=500,
+        message="boom",
+        headers=httpx.Headers([("x-amzn-RequestId", "req-dup-500"), ("set-cookie", "a=1"), ("set-cookie", "b=2")]),
+    )
+
+    assert error.response.headers.get_list("set-cookie") == ["a=1", "b=2"]
+
+
+def _bedrock_httpx_status_error_sites():
+    """Every `except httpx.HTTPStatusError as err` that raises a BedrockError, across bedrock."""
+    import ast
+    import pathlib
+
+    sites = []
+    for path in sorted(pathlib.Path("litellm/llms/bedrock").rglob("*.py")):
+        tree = ast.parse(path.read_text())
+        for handler in (n for n in ast.walk(tree) if isinstance(n, ast.ExceptHandler)):
+            caught = ast.unparse(handler.type) if handler.type is not None else ""
+            if "HTTPStatusError" not in caught or handler.name is None:
+                continue
+            for call in (
+                n
+                for n in ast.walk(handler)
+                if isinstance(n, ast.Call) and isinstance(n.func, ast.Name) and n.func.id == "BedrockError"
+            ):
+                sites.append((str(path), call.lineno, handler.name, {k.arg for k in call.keywords}))
+    return sites
+
+
+def test_every_bedrock_httpx_status_error_site_keeps_provider_headers():
+    """A raise site holding the provider's failed response must hand its headers on (LIT-5428).
+
+    These sites are the only place x-amzn-RequestId still exists; a site that drops it
+    silently shadows the fix for that whole surface.
+    """
+    sites = _bedrock_httpx_status_error_sites()
+
+    assert len(sites) >= 12
+    dropped = [f"{path}:{lineno}" for path, lineno, _, kwargs in sites if "headers" not in kwargs]
+    assert dropped == []
+
+
+@pytest.mark.parametrize("is_async", [False, True])
+@pytest.mark.asyncio
+async def test_bedrock_embedding_call_keeps_provider_headers(is_async):
+    """The embeddings surface raises from the same shape as chat and lost the same header."""
+    import httpx
+
+    from litellm.llms.bedrock.common_utils import BedrockError
+    from litellm.llms.bedrock.embed.embedding import BedrockEmbedding
+    from litellm.llms.custom_httpx.http_handler import AsyncHTTPHandler, HTTPHandler
+
+    failure = httpx.Response(
+        status_code=500,
+        headers={"x-amzn-RequestId": "req-embed-500"},
+        text='{"message":"Amazon Bedrock is unable to process your request."}',
+        request=httpx.Request("POST", "https://bedrock-runtime.us-east-1.amazonaws.com/"),
+    )
+
+    class _SyncUpstream(HTTPHandler):
+        def post(self, *args, **kwargs):
+            return failure
+
+    class _AsyncUpstream(AsyncHTTPHandler):
+        async def post(self, *args, **kwargs):
+            return failure
+
+    async def _drive():
+        embedding = BedrockEmbedding()
+        kwargs = dict(
+            timeout=None,
+            api_base="https://bedrock-runtime.us-east-1.amazonaws.com/",
+            headers={},
+            data={},
+        )
+        if is_async:
+            return await embedding._make_async_call(client=_AsyncUpstream(), **kwargs)
+        return embedding._make_sync_call(client=_SyncUpstream(), **kwargs)
+
+    with pytest.raises(BedrockError) as exc_info:
+        await _drive()
+
+    assert exc_info.value.response.headers["x-amzn-requestid"] == "req-embed-500"
+
+
+def _bedrock_mantle_error_configs():
+    from litellm.llms.bedrock_mantle.chat.transformation import BedrockMantleChatConfig
+    from litellm.llms.bedrock_mantle.responses.transformation import BedrockMantleResponsesAPIConfig
+
+    return [BedrockMantleChatConfig, BedrockMantleResponsesAPIConfig]
+
+
+@pytest.mark.parametrize("config", _bedrock_mantle_error_configs())
+def test_bedrock_mantle_get_error_class_keeps_provider_headers(config):
+    """bedrock_mantle rides the OpenAI-compatible surfaces, whose errors drop the headers.
+
+    A chat request for a responses-API model is bridged onto the responses config, so
+    fixing only the chat one leaves the model the customer actually calls uncovered.
+    """
+    error = config().get_error_class(
+        error_message="prompt tokens exceed model maximum",
+        status_code=400,
+        headers={"x-amzn-RequestId": "req-mantle-400"},
+    )
+
+    assert error.response.headers["x-amzn-requestid"] == "req-mantle-400"
+
+
+def _bedrock_configs_with_get_error_class():
+    import importlib
+    import inspect
+    import pathlib
+
+    import litellm
+
+    llms_root = pathlib.Path(inspect.getfile(litellm)).parent / "llms"
+    configs = []
+    for package in ("bedrock", "bedrock_mantle"):
+        for path in sorted((llms_root / package).rglob("*.py")):
+            module_name = "litellm.llms." + ".".join(path.relative_to(llms_root).with_suffix("").parts)
+            module = importlib.import_module(module_name)
+            for name, obj in vars(module).items():
+                if not inspect.isclass(obj) or obj.__module__ != module_name:
+                    continue
+                if getattr(obj, "get_error_class", None) is None:
+                    continue
+                configs.append(pytest.param(obj, id=f"{module_name}.{name}"))
+    return configs
+
+
+@pytest.mark.parametrize("config", _bedrock_configs_with_get_error_class())
+def test_every_bedrock_config_get_error_class_keeps_provider_headers(config):
+    """Every bedrock surface must classify errors through BedrockError, not a header-dropping base.
+
+    A config that inherits get_error_class from a provider-agnostic base builds a blank
+    response, so the request id is gone before the proxy ever reads it.
+    """
+    try:
+        instance = config()
+    except Exception:
+        instance = config.__new__(config)
+
+    try:
+        error = instance.get_error_class(
+            error_message="boom",
+            status_code=500,
+            headers={"x-amzn-RequestId": "req-audit-500"},
+        )
+    except Exception as raised:  # some bases raise the exception instead of returning it
+        error = raised
+
+    assert error.response.headers["x-amzn-requestid"] == "req-audit-500"
+
+
+def test_bedrock_get_error_class_audit_covers_every_surface():
+    assert len(_bedrock_configs_with_get_error_class()) >= 30

tests/test_litellm/llms/chat/test_converse_handler.py

@@ -308,3 +308,64 @@ def test_completion_plumbs_stream_chunk_size_through_converse():
         stream_chunk_size=2048,
     )
     iter_bytes_spy.assert_called_once_with(chunk_size=2048)
+
+
+def _bedrock_error_response(status_code: int, request_id: str) -> httpx.Response:
+    return httpx.Response(
+        status_code=status_code,
+        headers={
+            "x-amzn-RequestId": request_id,
+            "x-amzn-ErrorType": "InternalServerException",
+        },
+        text=json.dumps({"message": "Amazon Bedrock is unable to process your request."}),
+        request=httpx.Request("POST", "https://bedrock-runtime.us-east-1.amazonaws.com/"),
+    )
+
+
+def test_converse_completion_error_forwards_bedrock_response_headers():
+    error_response = _bedrock_error_response(500, "req-err-123")
+    client = HTTPHandler()
+    client.post = MagicMock(
+        side_effect=httpx.HTTPStatusError(
+            "server error",
+            request=error_response.request,
+            response=error_response,
+        )
+    )
+
+    with pytest.raises(litellm.ServiceUnavailableError) as exc_info:
+        litellm.completion(
+            model="bedrock/converse/anthropic.claude-haiku-4-5-20251001-v1:0",
+            messages=[{"role": "user", "content": "hi"}],
+            client=client,
+            aws_access_key_id="fake",
+            aws_secret_access_key="fake",
+            aws_region_name="us-east-1",
+        )
+
+    assert exc_info.value.response.headers["x-amzn-requestid"] == "req-err-123"
+
+
+@pytest.mark.asyncio
+async def test_async_converse_completion_error_forwards_bedrock_response_headers():
+    error_response = _bedrock_error_response(500, "req-err-456")
+    client = AsyncHTTPHandler()
+    client.post = AsyncMock(
+        side_effect=httpx.HTTPStatusError(
+            "server error",
+            request=error_response.request,
+            response=error_response,
+        )
+    )
+
+    with pytest.raises(litellm.ServiceUnavailableError) as exc_info:
+        await litellm.acompletion(
+            model="bedrock/converse/anthropic.claude-haiku-4-5-20251001-v1:0",
+            messages=[{"role": "user", "content": "hi"}],
+            client=client,
+            aws_access_key_id="fake",
+            aws_secret_access_key="fake",
+            aws_region_name="us-east-1",
+        )
+
+    assert exc_info.value.response.headers["x-amzn-requestid"] == "req-err-456"

tests/test_litellm/proxy/pass_through_endpoints/test_llm_pass_through_endpoints.py

@@ -5293,3 +5293,37 @@ class TestRouterModelRelayUpstreamContract:
         assert result.status_code == 404
         assert json.loads(result.body) == upstream_body
         assert result.headers["x-ms-request-id"] == "req-1"
+
+
+@pytest.mark.asyncio
+async def test_bedrock_count_tokens_error_forwards_provider_headers():
+    """The count tokens route converts BedrockError into an HTTPException, and dropping the
+    headers there loses x-amzn-RequestId after the handler went to the trouble of keeping it."""
+    from fastapi import HTTPException
+
+    from litellm.llms.bedrock.common_utils import BedrockError
+    from litellm.proxy.pass_through_endpoints.llm_passthrough_endpoints import (
+        handle_bedrock_count_tokens,
+    )
+
+    failure = BedrockError(
+        status_code=500,
+        message="Amazon Bedrock is unable to process your request.",
+        headers={"x-amzn-RequestId": "req-count-tokens-500"},
+    )
+
+    with patch(  # test-quality-ok: the route's BedrockError branch is only reachable when the handler raises
+        "litellm.llms.bedrock.count_tokens.handler.BedrockCountTokensHandler.handle_count_tokens_request",
+        new=AsyncMock(side_effect=failure),
+    ):
+        with pytest.raises(HTTPException) as exc_info:
+            await handle_bedrock_count_tokens(
+                endpoint="v1/messages/count_tokens",
+                request=MagicMock(),
+                fastapi_response=MagicMock(),
+                user_api_key_dict=MagicMock(),
+                request_body={"model": "anthropic.claude-haiku-4-5-20251001-v1:0"},
+            )
+
+    assert exc_info.value.status_code == 500
+    assert exc_info.value.headers["llm_provider-x-amzn-requestid"] == "req-count-tokens-500"

tests/test_litellm/proxy/test_common_request_processing.py

@@ -8259,3 +8259,38 @@ class TestPassthroughHeadersAcceptImmutableMappings:
         assert merged["content-type"] == "text/event-stream"
         # the excluded hop-by-hop header is still dropped
         assert "transfer-encoding" not in merged
+
+
+@pytest.mark.asyncio
+async def test_handle_llm_api_exception_forwards_provider_headers_on_http_status_error():
+    """The httpx.HTTPStatusError branch dropped the headers its sibling branches forward.
+
+    A Bedrock passthrough failure reaches this branch, so the request id was gone
+    before the client saw the response.
+    """
+    import httpx
+
+    from litellm.proxy._types import UserAPIKeyAuth
+
+    request = httpx.Request("POST", "https://bedrock-runtime.us-east-1.amazonaws.com/model/m/converse")
+    response = httpx.Response(
+        status_code=500,
+        headers={"x-amzn-RequestId": "req-passthrough-500"},
+        content=b'{"message": "Amazon Bedrock is unable to process your request."}',
+        request=request,
+    )
+
+    processor = ProxyBaseLLMRequestProcessing(data={})
+    proxy_logging_obj = MagicMock()
+    proxy_logging_obj.post_call_failure_hook = AsyncMock(return_value=None)
+    proxy_logging_obj.post_call_response_headers_hook = AsyncMock(return_value={})
+
+    with pytest.raises(HTTPException) as exc_info:
+        await processor._handle_llm_api_exception(
+            e=httpx.HTTPStatusError("boom", request=request, response=response),
+            user_api_key_dict=UserAPIKeyAuth(api_key="sk-test"),
+            proxy_logging_obj=proxy_logging_obj,
+        )
+
+    assert exc_info.value.headers is not None
+    assert exc_info.value.headers["llm_provider-x-amzn-requestid"] == "req-passthrough-500"

tests/test_litellm/test_exception_header_preservation.py

@@ -18,6 +18,7 @@ from litellm.exceptions import (
     ImageFetchError,
     MidStreamFallbackError,
     RateLimitError,
+    ServiceUnavailableError,
 )
 
 
@@ -312,3 +313,85 @@ class TestProxyHeaderExtraction:
         # Verify headers are extracted and prefixed correctly
         assert headers.get("llm_provider-x-request-id") == "req-abc123"
         assert headers.get("llm_provider-x-ms-region") == "eastus"
+
+
+class TestBedrockErrorHeaders:
+    """A BedrockError built with headers but no response still exposes them (LIT-5428)."""
+
+    def test_synthesized_response_carries_headers(self):
+        from litellm.llms.bedrock.common_utils import BedrockError
+
+        error = BedrockError(
+            status_code=500,
+            message="Amazon Bedrock is unable to process your request.",
+            headers={"x-amzn-RequestId": "req-base-500"},
+        )
+
+        assert error.response.headers["x-amzn-requestid"] == "req-base-500"
+        assert str(error.request.url) == str(BedrockError(status_code=500, message="boom").request.url)
+        assert str(error.response.request.url) == str(error.request.url)
+
+    def test_synthesized_response_without_headers_stays_empty(self):
+        from litellm.llms.bedrock.common_utils import BedrockError
+
+        error = BedrockError(status_code=500, message="boom")
+
+        assert dict(error.response.headers) == {}
+
+    def test_explicit_response_is_kept(self):
+        from litellm.llms.bedrock.common_utils import BedrockError
+
+        provider_response = httpx.Response(
+            status_code=500,
+            headers={"x-amzn-RequestId": "from-response"},
+            request=httpx.Request("POST", "https://bedrock-runtime.us-east-1.amazonaws.com/"),
+        )
+        error = BedrockError(
+            status_code=500,
+            message="boom",
+            headers={"x-amzn-RequestId": "from-headers"},
+            response=provider_response,
+        )
+
+        assert error.response is provider_response
+
+    def test_proxy_extraction_surfaces_bedrock_request_id(self):
+        """End-to-end shape the proxy error handler returns to the caller."""
+        from litellm.litellm_core_utils.exception_mapping_utils import exception_type
+        from litellm.litellm_core_utils.llm_response_utils.get_headers import (
+            get_response_headers,
+        )
+        from litellm.llms.bedrock.common_utils import BedrockError
+
+        provider_response = httpx.Response(
+            status_code=500,
+            headers={"x-amzn-RequestId": "req-proxy-500"},
+            text='{"message":"Amazon Bedrock is unable to process your request."}',
+            request=httpx.Request("POST", "https://bedrock-runtime.us-east-1.amazonaws.com/"),
+        )
+
+        with pytest.raises(ServiceUnavailableError) as exc_info:
+            exception_type(
+                model="anthropic.claude-haiku-4-5-20251001-v1:0",
+                original_exception=BedrockError(
+                    status_code=500,
+                    message=provider_response.text,
+                    headers=provider_response.headers,
+                    response=provider_response,
+                ),
+                custom_llm_provider="bedrock",
+                completion_kwargs={},
+                extra_kwargs={},
+            )
+
+        # Mirrors ProxyBaseLLMRequestProcessing._handle_llm_api_exception
+        error = exc_info.value
+        headers = getattr(error, "headers", None) or {}
+        if not headers:
+            _response = getattr(error, "response", None)
+            if _response is not None:
+                _response_headers = getattr(_response, "headers", None)
+                if _response_headers:
+                    headers = get_response_headers(dict(_response_headers))
+
+        assert headers.get("llm_provider-x-amzn-requestid") == "req-proxy-500"