diff --git a/backend/app/llm/client.py b/backend/app/llm/client.py
index f9951fa0..9fc6a5b9 100644
--- a/backend/app/llm/client.py
+++ b/backend/app/llm/client.py
@@ -116,6 +116,14 @@ def __init__(self, model_config: ModelConfig):
         self.api_key = api_key
         self.model = model_config.model
         self.temperature = model_config.temperature
+        # Reasoning models on some gateways reject the `temperature` parameter
+        # entirely. Omit it for the Anthropic Messages protocol so those models
+        # (e.g. Claude Opus 4.8) accept the request; other protocols keep it.
+        self.request_temperature = (
+            None
+            if protocol is ModelApiProtocol.ANTHROPIC_MESSAGES
+            else self.temperature
+        )
         self.max_output_tokens = model_config.max_output_tokens
         legacy_extra_body = getattr(model_config, "legacy_extra_body", {})
         protocol_options = getattr(model_config, "protocol_options", {})
@@ -160,7 +168,7 @@ def generate_text(
             request: dict[str, Any] = {
                 "model": self.model,
                 "messages": request_messages,
-                "temperature": self.temperature,
+                "temperature": self.request_temperature,
                 "max_tokens": max_output_tokens,
             }
             if cancellation is not None:
@@ -290,7 +298,7 @@ def generate_text_stream(
                     stream_request = {
                         "model": self.model,
                         "messages": request_messages,
-                        "temperature": self.temperature,
+                        "temperature": self.request_temperature,
                         "max_tokens": current_max_tokens,
                         **_thinking_request_kwargs(
                             getattr(self, "thinking_mode", ""),
diff --git a/backend/app/llm/protocol_drivers.py b/backend/app/llm/protocol_drivers.py
index 5c3d46e0..1706e9e3 100644
--- a/backend/app/llm/protocol_drivers.py
+++ b/backend/app/llm/protocol_drivers.py
@@ -388,8 +388,12 @@ def _anthropic_request(request: dict[str, Any]) -> dict[str, Any]:
         "model": request["model"],
         "messages": converted,
         "max_tokens": request["max_tokens"],
-        "temperature": request["temperature"],
     }
+    # Some gateways expose reasoning models (e.g. Claude Opus 4.8) that reject the
+    # `temperature` parameter outright. Only include it when a value is provided.
+    temperature = request.get("temperature")
+    if temperature is not None:
+        payload["temperature"] = temperature
     system = "\n\n".join(part for part in system_parts if part)
     if system:
         payload["system"] = system