diff --git a/docs/guides/backends.md b/docs/guides/backends.md
index 4f9d79b98..f810420c1 100644
--- a/docs/guides/backends.md
+++ b/docs/guides/backends.md
@@ -129,11 +129,34 @@ guidellm run \
 
 This will include `temperature`, `top_p`, and `top_k` in every request body sent to the server.
 
+## Structured Chat Content Payloads
+
+Some chat templates require metadata alongside the text in each structured content object. Pass these fields through `extras.content` in the `openai_http` backend configuration. GuideLLM adds them to every generated text content object for Chat Completions and Responses API requests.
+
+```bash
+guidellm run \
+  --backend '{
+    "kind": "openai_http",
+    "target": "http://localhost:8000",
+    "model": "google/translategemma-12b-it",
+    "request_format": "/v1/chat/completions",
+    "extras": {
+      "content": {
+        "source_lang_code": "en",
+        "target_lang_code": "es"
+      }
+    }
+  }' \
+  --data kind=synthetic_text,prompt_tokens=1000,output_tokens=1000 \
+  --constraint kind=max_duration,seconds=60
+```
+
 ### How It Works
 
 The `--backend` config is parsed into keyword arguments for the backend constructor. The `extras` field within that config maps to a `GenerationRequestArguments` object that supports the following sub-fields:
 
 - `body`: A dictionary of key-value pairs merged into the HTTP request body. Use this for sampling parameters like `temperature`, `top_p`, `top_k`, `repetition_penalty`, etc.
+- `content`: A dictionary of fields merged into each generated text content object.
 - `headers`: A dictionary of additional HTTP headers to include in requests.
 - `params`: A dictionary of query parameters to append to the request URL.
 
diff --git a/src/guidellm/backends/openai/request_handlers.py b/src/guidellm/backends/openai/request_handlers.py
index 1a0451682..ed9ba11bf 100644
--- a/src/guidellm/backends/openai/request_handlers.py
+++ b/src/guidellm/backends/openai/request_handlers.py
@@ -707,7 +707,10 @@ def _ensure_tool_format(tool: dict[str, Any]) -> dict[str, Any]:
         return tool
 
     def _format_prompts(
-        self, column_data: list[dict[str, Any]], column_type: str
+        self,
+        column_data: list,
+        column_type: str,
+        content_extras: dict[str, Any] | None = None,
     ) -> list[dict[str, Any]]:
         """
         Helper method to format different types of data columns
@@ -716,7 +719,10 @@ def _format_prompts(
         formatted_data = []
         for item in column_data:
             if column_type == "text_column":
-                formatted_data.append({"type": "text", "text": item})
+                content = {"type": "text", "text": item}
+                if content_extras:
+                    content.update(content_extras)
+                formatted_data.append(content)
             elif column_type == "image_column":
                 formatted_data.append(
                     {
@@ -910,8 +916,14 @@ def _build_turn_messages(  # noqa: C901
             if prefix:
                 messages.append({"role": "system", "content": prefix})
 
+            extras = kwargs.get("extras")
+            content_extras = extras.content if extras is not None else None
             prompts = [
-                self._format_prompts(req.columns.get(col, []), col)
+                self._format_prompts(
+                    req.columns.get(col, []),
+                    col,
+                    content_extras,
+                )
                 for col in (
                     "text_column",
                     "image_column",
@@ -1018,8 +1030,14 @@ def format(  # noqa: C901, PLR0912, PLR0915
             if prefix:
                 arguments.body["messages"].append({"role": "system", "content": prefix})
 
+            extras = kwargs.get("extras")
+            content_extras = extras.content if extras is not None else None
             prompts = [
-                self._format_prompts(data.columns.get(col, []), col)
+                self._format_prompts(
+                    data.columns.get(col, []),
+                    col,
+                    content_extras,
+                )
                 for col in (
                     "text_column",
                     "image_column",
@@ -1497,12 +1515,18 @@ def _ensure_tool_format(tool: dict[str, Any]) -> dict[str, Any]:
         return tool
 
     def _format_prompts(
-        self, column_data: list, column_type: str
+        self,
+        column_data: list,
+        column_type: str,
+        content_extras: dict[str, Any] | None = None,
     ) -> list[dict[str, Any]]:
         formatted_data: list[dict[str, Any]] = []
         for item in column_data:
             if column_type == "text_column":
-                formatted_data.append({"type": "input_text", "text": item})
+                content = {"type": "input_text", "text": item}
+                if content_extras:
+                    content.update(content_extras)
+                formatted_data.append(content)
             elif column_type == "image_column":
                 formatted_data.append(
                     {
@@ -1582,8 +1606,14 @@ def _build_turn_input_items(  # noqa: C901
                 items.append({"role": "assistant", "content": content})
         else:
             # Standard or tool_call turn: user content.
+            extras = kwargs.get("extras")
+            content_extras = extras.content if extras is not None else None
             prompts = [
-                self._format_prompts(req.columns.get(col, []), col)
+                self._format_prompts(
+                    req.columns.get(col, []),
+                    col,
+                    content_extras,
+                )
                 for col in (
                     "text_column",
                     "image_column",
@@ -1751,8 +1781,14 @@ def format(  # noqa: C901
                 )
         elif data.turn_type != "tool_response_injection":
             # Standard or tool_call turn: user content.
+            extras = kwargs.get("extras")
+            content_extras = extras.content if extras is not None else None
             prompts = [
-                self._format_prompts(data.columns.get(col, []), col)
+                self._format_prompts(
+                    data.columns.get(col, []),
+                    col,
+                    content_extras,
+                )
                 for col in (
                     "text_column",
                     "image_column",
diff --git a/src/guidellm/schemas/request.py b/src/guidellm/schemas/request.py
index 1367395ce..370291b3f 100644
--- a/src/guidellm/schemas/request.py
+++ b/src/guidellm/schemas/request.py
@@ -72,6 +72,13 @@ class GenerationRequestArguments(StandardBaseDict):
         default=None,
         description="Files to include in the request, if applicable.",
     )
+    content: dict[str, Any] | None = Field(
+        default=None,
+        description=(
+            "Additional fields to include in generated text content objects, "
+            "if applicable."
+        ),
+    )
 
     def model_combine(
         self, additional: GenerationRequestArguments | dict[str, Any]
diff --git a/tests/unit/backends/openai/test_http.py b/tests/unit/backends/openai/test_http.py
index d053699ce..fc8a0f057 100644
--- a/tests/unit/backends/openai/test_http.py
+++ b/tests/unit/backends/openai/test_http.py
@@ -179,6 +179,34 @@ def test_server_history_with_responses_api(self):
         )
         assert backend._args.server_history is True
 
+    @pytest.mark.asyncio
+    @pytest.mark.regression
+    async def test_content_extras_are_forwarded_to_request_handler(
+        self,
+        mock_request_handler,
+    ):
+        """The HTTP backend forwards content extras through its handler boundary.
+
+        ## WRITTEN BY AI ##
+        """
+        extras = GenerationRequestArguments(
+            content={
+                "metadata": {"category": "support"},
+                "priority": 1,
+            }
+        )
+        backend = _make_backend(
+            target="http://localhost:8000",
+            model="test-model",
+            extras=extras,
+        )
+        mock_handler, handler_patch = mock_request_handler
+
+        with handler_patch:
+            await backend._prepare_resolve_request(GenerationRequest())
+
+        assert mock_handler.format.call_args.kwargs["extras"] == extras
+
     @pytest.mark.smoke
     def test_factory_registration(self):
         """Test that OpenAIHTTPBackend is registered with Backend factory."""
diff --git a/tests/unit/backends/openai/test_request_handlers.py b/tests/unit/backends/openai/test_request_handlers.py
index 287b22413..863efb5e8 100644
--- a/tests/unit/backends/openai/test_request_handlers.py
+++ b/tests/unit/backends/openai/test_request_handlers.py
@@ -29,7 +29,12 @@
     GenerativeRequestFinalizer,
     GenerativeRequestFinalizerArgs,
 )
-from guidellm.schemas import GenerationRequest, GenerationResponse, UsageMetrics
+from guidellm.schemas import (
+    GenerationRequest,
+    GenerationRequestArguments,
+    GenerationResponse,
+    UsageMetrics,
+)
 from guidellm.schemas.tool_call import ToolCall, ToolCallFunction
 from guidellm.settings import settings
 from guidellm.utils.registry import RegistryMixin
@@ -502,7 +507,7 @@ def test_format_extras(self, valid_instances):
         """
         instance = valid_instances
         data = GenerationRequest()
-        extras = {"body": {"temperature": 0.7, "top_p": 0.9}}
+        extras = GenerationRequestArguments(body={"temperature": 0.7, "top_p": 0.9})
 
         result = instance.format(data, extras=extras)
 
@@ -925,7 +930,7 @@ def test_format_extras(self, valid_instances):
         """
         instance = valid_instances
         data = GenerationRequest()
-        extras = {"body": {"temperature": 0.5, "top_k": 40}}
+        extras = GenerationRequestArguments(body={"temperature": 0.5, "top_k": 40})
 
         result = instance.format(data, extras=extras)
 
@@ -953,6 +958,35 @@ def test_format_messages_text(self, valid_instances):
         assert result.body["messages"][0]["content"][1]["type"] == "text"
         assert result.body["messages"][0]["content"][1]["text"] == "How are you?"
 
+    @pytest.mark.regression
+    def test_content_extras_enrich_plain_text_only(self, valid_instances):
+        """Content extras enrich text without changing multimodal parts.
+
+        ## WRITTEN BY AI ##
+        """
+        data = GenerationRequest(
+            columns={
+                "text_column": ["Describe this"],
+                "image_column": [{"image": "https://example.com/image.jpg"}],
+            }
+        )
+
+        result = valid_instances.format(
+            data,
+            extras=GenerationRequestArguments(
+                content={
+                    "metadata": {"category": "vision"},
+                    "priority": 1,
+                }
+            ),
+        )
+
+        text_content, image_content = result.body["messages"][0]["content"]
+        assert text_content["metadata"] == {"category": "vision"}
+        assert text_content["priority"] == 1
+        assert "metadata" not in image_content
+        assert "priority" not in image_content
+
     @pytest.mark.sanity
     def test_format_messages_prefix(self, valid_instances):
         """Test format method with prefix as system message.
@@ -2061,7 +2095,10 @@ def test_format_strips_tool_choice_without_tools(self, valid_instances):
             turn_type="standard",
         )
 
-        result = instance.format(data, extras={"body": {"tool_choice": "required"}})
+        result = instance.format(
+            data,
+            extras=GenerationRequestArguments(body={"tool_choice": "required"}),
+        )
 
         assert "tool_choice" not in result.body
         assert "tools" not in result.body
@@ -2273,7 +2310,7 @@ def test_format_extras(self, valid_instances):
                 ]
             },
         )
-        extras = {"body": {"language": "en", "temperature": 0.0}}
+        extras = GenerationRequestArguments(body={"language": "en", "temperature": 0.0})
 
         result = instance.format(data, extras=extras)
 
@@ -2626,6 +2663,30 @@ def test_chat_format_with_single_turn_history(self, valid_instances):
         assert messages[1]["content"] == "The answer is 4"
         assert messages[2]["role"] == "user"
 
+    @pytest.mark.regression
+    def test_content_extras_apply_to_history_and_current_turn(self, valid_instances):
+        """Content extras are applied consistently across conversation turns.
+
+        ## WRITTEN BY AI ##
+        """
+        prev_request = GenerationRequest(columns={"text_column": ["Previous"]})
+        prev_response = GenerationResponse(
+            request_id="prev",
+            request_args=None,
+            text="Previous response",
+        )
+        data = GenerationRequest(columns={"text_column": ["Current"]})
+
+        result = valid_instances.format(
+            data,
+            history=[(prev_request, prev_response)],
+            extras=GenerationRequestArguments(content={"priority": 3}),
+        )
+
+        messages = result.body["messages"]
+        assert messages[0]["content"][0]["priority"] == 3
+        assert messages[2]["content"][0]["priority"] == 3
+
     @pytest.mark.sanity
     def test_chat_format_with_multi_turn_history(self, valid_instances):
         """Test format with multiple turns alternates user/assistant.
@@ -2813,6 +2874,56 @@ def test_factory_registration(self):
         handler = OpenAIRequestHandlerFactory.create("/v1/responses")
         assert isinstance(handler, ResponsesRequestHandler)
 
+    @pytest.mark.regression
+    def test_content_extras_enrich_text(self, valid_instances):
+        """Content extras are added to Responses API text content.
+
+        ## WRITTEN BY AI ##
+        """
+        data = GenerationRequest(columns={"text_column": ["Handle this request"]})
+
+        result = valid_instances.format(
+            data,
+            extras=GenerationRequestArguments(
+                content={
+                    "priority": 2,
+                    "metadata": {"category": "support"},
+                }
+            ),
+        )
+
+        content = result.body["input"][0]["content"][0]
+        assert content == {
+            "type": "input_text",
+            "text": "Handle this request",
+            "priority": 2,
+            "metadata": {"category": "support"},
+        }
+
+    @pytest.mark.regression
+    def test_content_extras_apply_to_history_and_current_turn(self, valid_instances):
+        """Content extras apply to all Responses API conversation turns.
+
+        ## WRITTEN BY AI ##
+        """
+        prev_request = GenerationRequest(columns={"text_column": ["Previous"]})
+        prev_response = GenerationResponse(
+            request_id="prev",
+            request_args=None,
+            text="Previous response",
+        )
+        data = GenerationRequest(columns={"text_column": ["Current"]})
+
+        result = valid_instances.format(
+            data,
+            history=[(prev_request, prev_response)],
+            extras=GenerationRequestArguments(content={"priority": 3}),
+        )
+
+        input_items = result.body["input"]
+        assert input_items[0]["content"][0]["priority"] == 3
+        assert input_items[2]["content"][0]["priority"] == 3
+
     @pytest.mark.smoke
     def test_format_minimal(self, valid_instances):
         """
@@ -4347,7 +4458,10 @@ def test_format_tool_choice_none_on_non_tool_turn(self, valid_instances):
         tools = [{"type": "function", "function": {"name": "fn", "parameters": {}}}]
         data = GenerationRequest(turn_type="standard")
 
-        result = instance.format(data, extras={"body": {"tools": tools}})
+        result = instance.format(
+            data,
+            extras=GenerationRequestArguments(body={"tools": tools}),
+        )
 
         assert result.body["tools"] == tools
         assert result.body["tool_choice"] == "none"
@@ -4366,7 +4480,10 @@ def test_format_strips_tool_choice_without_tools(self, valid_instances):
             turn_type="standard",
         )
 
-        result = instance.format(data, extras={"body": {"tool_choice": "required"}})
+        result = instance.format(
+            data,
+            extras=GenerationRequestArguments(body={"tool_choice": "required"}),
+        )
 
         assert "tool_choice" not in result.body
         assert "tools" not in result.body
@@ -4644,7 +4761,7 @@ def test_format_extras(self, valid_instances):
         """
         instance = valid_instances
         data = GenerationRequest()
-        extras = {"body": {"temperature": 0.5, "top_k": 40}}
+        extras = GenerationRequestArguments(body={"temperature": 0.5, "top_k": 40})
 
         result = instance.format(data, extras=extras)
 
@@ -4868,7 +4985,7 @@ def test_format_with_extras(self, valid_instances):
         """
         instance = valid_instances
         data = GenerationRequest()
-        extras = {"body": {"user": "test-user"}}
+        extras = GenerationRequestArguments(body={"user": "test-user"})
 
         result = instance.format(data, extras=extras)
 
@@ -4973,7 +5090,7 @@ def test_tool_choice_none_when_expects_false(self, handler):
             },
             turn_type="standard",
         )
-        extras = {"body": {"tool_choice": "required"}}
+        extras = GenerationRequestArguments(body={"tool_choice": "required"})
         result = handler.format(data, extras=extras)
 
         assert result.body["tool_choice"] == "none"
@@ -4992,7 +5109,7 @@ def test_tool_choice_preserved_when_expects_true(self, handler):
             },
             turn_type="client_tool_call",
         )
-        extras = {"body": {"tool_choice": "required"}}
+        extras = GenerationRequestArguments(body={"tool_choice": "required"})
         result = handler.format(data, extras=extras)
 
         assert result.body["tool_choice"] == "required"
@@ -5011,7 +5128,7 @@ def test_auto_tool_choice_preserved_when_expects_true(self, handler):
             },
             turn_type="client_tool_call",
         )
-        extras = {"body": {"tool_choice": "auto"}}
+        extras = GenerationRequestArguments(body={"tool_choice": "auto"})
         result = handler.format(data, extras=extras)
 
         assert result.body["tool_choice"] == "auto"
diff --git a/tests/unit/schemas/test_request.py b/tests/unit/schemas/test_request.py
index 423dde139..2105bfbf6 100644
--- a/tests/unit/schemas/test_request.py
+++ b/tests/unit/schemas/test_request.py
@@ -37,6 +37,7 @@ class TestGenerationRequestArguments:
                 "params": {"limit": 10},
                 "body": {"prompt": "hello"},
                 "files": {"file": "data.txt"},
+                "content": {"metadata": {"category": "support"}},
             },
         ],
         ids=["empty", "method_body", "method_headers_params", "all_fields"],
@@ -57,7 +58,15 @@ def test_class_signatures(self):
 
         # Check fields
         fields = GenerationRequestArguments.model_fields
-        expected_fields = ["method", "stream", "headers", "params", "body", "files"]
+        expected_fields = [
+            "method",
+            "stream",
+            "headers",
+            "params",
+            "body",
+            "files",
+            "content",
+        ]
         for field in expected_fields:
             assert field in fields
 
@@ -72,7 +81,15 @@ def test_initialization(self, valid_instances):
             assert getattr(instance, key) == expected_value
 
         # Check defaults for fields not provided
-        for field in ["method", "stream", "headers", "params", "body", "files"]:
+        for field in [
+            "method",
+            "stream",
+            "headers",
+            "params",
+            "body",
+            "files",
+            "content",
+        ]:
             if field not in constructor_args:
                 assert getattr(instance, field) is None
 
@@ -99,6 +116,10 @@ def test_invalid_initialization_values(self):
         with pytest.raises(ValidationError):
             GenerationRequestArguments(body="not_dict")
 
+        # Invalid content type
+        with pytest.raises(ValidationError):
+            GenerationRequestArguments(content="not_dict")
+
     @pytest.mark.sanity
     def test_invalid_initialization_missing(self):
         """Test GenerationRequestArguments initialization without any fields."""
@@ -111,6 +132,7 @@ def test_invalid_initialization_missing(self):
         assert instance.params is None
         assert instance.body is None
         assert instance.files is None
+        assert instance.content is None
 
     @pytest.mark.smoke
     @pytest.mark.parametrize(