diff --git a/routstr/upstream/messages_dispatch.py b/routstr/upstream/messages_dispatch.py
index 488129a8..e7429150 100644
--- a/routstr/upstream/messages_dispatch.py
+++ b/routstr/upstream/messages_dispatch.py
@@ -507,6 +507,32 @@ async def dispatch_anthropic_messages(
 
     model_suffix = adapt_request(body) if adapt_request else ""
 
+    # LiteLLM turns Anthropic's server-side web_search tool into the OpenAI
+    # `web_search_options` parameter. Generic OpenAI-compatible chat endpoints
+    # (including those serving Claude through a proxy) may reject that field.
+    # Only a provider with an explicit adaptation (e.g. Venice's model suffix)
+    # can preserve search semantics; do not silently remove the tool and return
+    # an answer that never searched. Native /v1/messages providers bypass this
+    # dispatcher and receive the original tool unchanged.
+    tools = body.get("tools")
+    if provider_prefix == "openai/" and isinstance(tools, list) and any(
+        isinstance(tool, dict)
+        and (
+            (
+                isinstance(tool.get("type"), str)
+                and tool["type"].startswith("web_search")
+            )
+            or tool.get("name") == "web_search"
+        )
+        for tool in tools
+    ):
+        raise UpstreamError(
+            "This upstream does not support Anthropic web search through "
+            "OpenAI-compatible /v1/messages translation",
+            status_code=400,
+            code="UNSUPPORTED_WEB_SEARCH",
+        )
+
     # Convention: `model.id` is the canonical upstream model name;
     # `forwarded_model_id` is the public alias the internal API exposes
     # and echoes back to the client.
diff --git a/tests/unit/test_venice_web_search.py b/tests/unit/test_venice_web_search.py
index a836e956..380ccc33 100644
--- a/tests/unit/test_venice_web_search.py
+++ b/tests/unit/test_venice_web_search.py
@@ -123,13 +123,35 @@ async def test_requests_without_web_search_are_untouched() -> None:
 
 
 @pytest.mark.asyncio
-async def test_other_providers_keep_their_existing_behaviour() -> None:
-    """The base hook is a no-op, so no non-Venice upstream changes shape."""
+async def test_generic_openai_upstream_rejects_untranslatable_web_search() -> None:
+    """Do not let LiteLLM send unsupported web_search_options to a generic API."""
     provider = BaseUpstreamProvider(base_url="http://test", api_key="k")
 
+    with pytest.raises(UpstreamError) as excinfo:
+        await _dispatch(provider, _body(tools=[WEB_SEARCH_TOOL, FUNCTION_TOOL]))
+
+    assert excinfo.value.status_code == 400
+    assert excinfo.value.code == "UNSUPPORTED_WEB_SEARCH"
+
+
+@pytest.mark.asyncio
+async def test_generic_openai_upstream_still_accepts_function_tools() -> None:
+    provider = BaseUpstreamProvider(base_url="http://test", api_key="k")
+
+    kwargs = await _dispatch(provider, _body(tools=[FUNCTION_TOOL]))
+
+    assert kwargs["model"] == "openai/deepseek-v4-flash-0731"
+    assert kwargs["tools"] == [FUNCTION_TOOL]
+
+
+@pytest.mark.asyncio
+async def test_non_openai_adapter_can_still_handle_search_tool() -> None:
+    provider = BaseUpstreamProvider(
+        base_url="https://openrouter.ai/api/v1", api_key="k"
+    )
+
     kwargs = await _dispatch(provider, _body(tools=[WEB_SEARCH_TOOL]))
 
-    assert kwargs["model"] == "openai/deepseek-v4-flash-0731"
     assert kwargs["tools"] == [WEB_SEARCH_TOOL]