diff --git a/src/strands/models/llamaapi.py b/src/strands/models/llamaapi.py
index b1ed4563a..d9280b7e1 100644
--- a/src/strands/models/llamaapi.py
+++ b/src/strands/models/llamaapi.py
@@ -179,7 +179,7 @@ def _format_request_messages(self, messages: Messages, system_prompt: str | None
             # Filter out location sources and unsupported block types
             filtered_contents = []
             for content in contents:
-                if any(block_type in content for block_type in ["toolResult", "toolUse"]):
+                if any(block_type in content for block_type in ["toolResult", "toolUse", "reasoningContent"]):
                     continue
                 if _has_location_source(content):
                     logger.warning("Location sources are not supported by LlamaAPI | skipping content block")
diff --git a/src/strands/models/llamacpp.py b/src/strands/models/llamacpp.py
index c52509816..6e8dab149 100644
--- a/src/strands/models/llamacpp.py
+++ b/src/strands/models/llamacpp.py
@@ -302,7 +302,7 @@ def _format_messages(self, messages: Messages, system_prompt: str | None = None)
             # Filter out location sources and unsupported block types
             filtered_contents = []
             for content in contents:
-                if any(block_type in content for block_type in ["toolResult", "toolUse"]):
+                if any(block_type in content for block_type in ["toolResult", "toolUse", "reasoningContent"]):
                     continue
                 if _has_location_source(content):
                     logger.warning("Location sources are not supported by llama.cpp | skipping content block")
diff --git a/src/strands/models/writer.py b/src/strands/models/writer.py
index 94774b363..0e774134f 100644
--- a/src/strands/models/writer.py
+++ b/src/strands/models/writer.py
@@ -116,7 +116,7 @@ def _format_content_vision(content: ContentBlock) -> dict[str, Any]:
         return [
             _format_content_vision(content)
             for content in contents
-            if not any(block_type in content for block_type in ["toolResult", "toolUse"])
+            if not any(block_type in content for block_type in ["toolResult", "toolUse", "reasoningContent"])
         ]
 
     def _format_request_message_contents(self, contents: list[ContentBlock]) -> str:
@@ -142,7 +142,7 @@ def _format_content(content: ContentBlock) -> str:
         content_blocks = list(
             filter(
                 lambda content: content.get("text")
-                and not any(block_type in content for block_type in ["toolResult", "toolUse"]),
+                and not any(block_type in content for block_type in ["toolResult", "toolUse", "reasoningContent"]),
                 contents,
             )
         )
diff --git a/tests/strands/models/test_llamaapi.py b/tests/strands/models/test_llamaapi.py
index 2bf12d055..8047e6a35 100644
--- a/tests/strands/models/test_llamaapi.py
+++ b/tests/strands/models/test_llamaapi.py
@@ -241,6 +241,26 @@ def test_format_request_with_unsupported_type(model):
         model.format_request(messages)
 
 
+def test_format_request_skips_reasoning_content(model):
+    """Test that reasoningContent blocks from other providers are silently skipped."""
+    messages = [
+        {
+            "role": "user",
+            "content": [
+                {"text": "Hello"},
+                {"reasoningContent": {"reasoningText": {"text": "Let me think...", "signature": "sig"}}},
+            ],
+        },
+    ]
+
+    # Should not raise — reasoningContent is silently dropped
+    request = model.format_request(messages)
+    # Only the text block should appear in the formatted request
+    user_messages = [m for m in request["messages"] if m["role"] == "user"]
+    assert len(user_messages) == 1
+    assert user_messages[0]["content"] == [{"type": "text", "text": "Hello"}]
+
+
 def test_format_chunk_message_start(model):
     event = {"chunk_type": "message_start"}
 
diff --git a/tests/strands/models/test_llamacpp.py b/tests/strands/models/test_llamacpp.py
index 3e023dfce..e3815ca0d 100644
--- a/tests/strands/models/test_llamacpp.py
+++ b/tests/strands/models/test_llamacpp.py
@@ -706,3 +706,25 @@ def test_format_request_filters_location_source_document(caplog) -> None:
     assert len(user_content) == 1
     assert user_content[0]["type"] == "text"
     assert "Location sources are not supported by llama.cpp" in caplog.text
+
+
+def test_format_request_skips_reasoning_content() -> None:
+    """Test that reasoningContent blocks from other providers are silently skipped."""
+    model = LlamaCppModel()
+
+    messages = [
+        {
+            "role": "user",
+            "content": [
+                {"text": "Hello"},
+                {"reasoningContent": {"reasoningText": {"text": "Let me think...", "signature": "sig"}}},
+            ],
+        },
+    ]
+
+    # Should not raise — reasoningContent is silently dropped
+    request = model._format_request(messages)
+    # Only the text block should appear in the formatted request
+    user_messages = [m for m in request["messages"] if m["role"] == "user"]
+    assert len(user_messages) == 1
+    assert user_messages[0]["content"] == [{"type": "text", "text": "Hello"}]
diff --git a/tests/strands/models/test_writer.py b/tests/strands/models/test_writer.py
index 81745f412..497b9cba3 100644
--- a/tests/strands/models/test_writer.py
+++ b/tests/strands/models/test_writer.py
@@ -250,7 +250,6 @@ def test_format_request_with_empty_content(model, model_id, stream_options):
     [
         ({"video": {}}, "video"),
         ({"document": {}}, "document"),
-        ({"reasoningContent": {}}, "reasoningContent"),
         ({"other": {}}, "other"),
     ],
 )
@@ -266,6 +265,22 @@ def test_format_request_with_unsupported_type(model, content, content_type):
         model.format_request(messages)
 
 
+def test_format_request_skips_reasoning_content(model):
+    """Test that reasoningContent blocks from other providers are silently skipped."""
+    messages = [
+        {
+            "role": "user",
+            "content": [
+                {"text": "Hello"},
+                {"reasoningContent": {"reasoningText": {"text": "Let me think...", "signature": "sig"}}},
+            ],
+        },
+    ]
+
+    # Should not raise — reasoningContent is silently dropped
+    model.format_request(messages)
+
+
 class AsyncStreamWrapper:
     def __init__(self, items: list[Any]):
         self.items = items