diff --git a/keras/src/backend/openvino/excluded_concrete_tests.txt b/keras/src/backend/openvino/excluded_concrete_tests.txt
index c366943c7eba..2fc1c6c4608d 100644
--- a/keras/src/backend/openvino/excluded_concrete_tests.txt
+++ b/keras/src/backend/openvino/excluded_concrete_tests.txt
@@ -46,7 +46,6 @@ NumpyDtypeTest::test_meshgrid
 NumpyDtypeTest::test_minimum_python_types
 NumpyDtypeTest::test_multiply
 NumpyDtypeTest::test_power
-NumpyDtypeTest::test_prod
 NumpyDtypeTest::test_quantile
 NumpyDtypeTest::test_roll
 NumpyDtypeTest::test_round
@@ -106,7 +105,6 @@ NumpyOneInputOpsCorrectnessTest::test_pad_int16_constant_2
 NumpyOneInputOpsCorrectnessTest::test_pad_int8_constant_2
 NumpyOneInputOpsCorrectnessTest::test_pad_uint8_constant_2
 NumpyOneInputOpsCorrectnessTest::test_pad_int32_constant_2
-NumpyOneInputOpsCorrectnessTest::test_prod
 NumpyOneInputOpsCorrectnessTest::test_real
 NumpyOneInputOpsCorrectnessTest::test_reshape
 NumpyOneInputOpsCorrectnessTest::test_roll
diff --git a/keras/src/backend/openvino/numpy.py b/keras/src/backend/openvino/numpy.py
index 8b3c5e0b5a96..2b310d96a278 100644
--- a/keras/src/backend/openvino/numpy.py
+++ b/keras/src/backend/openvino/numpy.py
@@ -1303,7 +1303,35 @@ def pad(x, pad_width, mode="constant", constant_values=None):
 
 
 def prod(x, axis=None, keepdims=False, dtype=None):
-    raise NotImplementedError("`prod` is not supported with openvino backend")
+    x = get_ov_output(x)
+
+    # If a specific dtype is requested, cast the input to that dtype.
+    if dtype is not None:
+        ov_dtype = OPENVINO_DTYPES[standardize_dtype(dtype)]
+        x = ov_opset.convert(x, ov_dtype).output(0)
+    # Otherwise, apply dtype promotion rules before reduction.
+    else:
+        x_type = x.get_element_type()
+        if x_type == Type.boolean:
+            x = ov_opset.convert(x, Type.i32).output(0)
+        elif x_type in (Type.i8, Type.i16):
+            x = ov_opset.convert(x, Type.i32).output(0)
+        elif x_type in (Type.u8, Type.u16):
+            x = ov_opset.convert(x, Type.u32).output(0)
+
+    if axis is None:
+        flatten_shape = ov_opset.constant([-1], Type.i32).output(0)
+        x = ov_opset.reshape(x, flatten_shape, False).output(0)
+        axis = 0
+
+    if isinstance(axis, tuple):
+        axis = list(axis)
+    axis = ov_opset.constant(axis, Type.i32).output(0)
+
+    # Compute the product
+    result = ov_opset.reduce_prod(x, axis, keepdims).output(0)
+
+    return OpenVINOKerasTensor(result)
 
 
 def quantile(x, q, axis=None, method="linear", keepdims=False):