diff --git a/paddle/contrib/inference/high_level_api.md b/paddle/contrib/inference/high_level_api.md
new file mode 100644
index 0000000000000000000000000000000000000000..563b696143de9cbf67db38048bbd2f7c11b3a66e
--- /dev/null
+++ b/paddle/contrib/inference/high_level_api.md
@@ -0,0 +1,59 @@
+# Inference High-level APIs
+This document describes the high-level inference APIs one can use to easily deploy a Paddle model for an application.
+
+The APIs are described in `paddle_inference_api.h`, just one header file, and two libaries `libpaddle_fluid.so` and `libpaddle_fluid_api.so` are needed.
+
+## PaddleTensor
+We provide the `PaddleTensor` data structure is to give a general tensor interface.
+
+The definition is 
+
+```c++
+struct PaddleTensor {
+  std::string name;  // variable name.
+  std::vector<int> shape;
+  PaddleBuf data;  // blob of data.
+  PaddleDType dtype;
+};
+```
+
+The data is stored in a continuous memory `PaddleBuf`, and tensor's data type is specified by a `PaddleDType`. 
+The `name` field is used to specify the name of input variable, 
+that is important when there are multiple inputs and need to distiuish which variable to set.
+
+## engine
+The inference APIs has two different underlying implementation, currently there are two valid engines:
+
+- the native engine, which is consists of the native operators and framework,
+- the Anakin engine, which is a Anakin library embeded.
+
+The native engine takes a native Paddle model as input, and supports any model that trained by Paddle, 
+but the Anakin engine can only take the Anakin model as input(user need to manully transform the format first) and currently not all Paddle models are supported.
+
+```c++
+enum class PaddleEngineKind {
+  kNative = 0,  // Use the native Fluid facility.
+  kAnakin,      // Use Anakin for inference.
+};
+```
+
+## PaddlePredictor and how to create one
+The main interface is `PaddlePredictor`, there are following methods 
+
+- `bool Run(const std::vector<PaddleTensor>& inputs, std::vector<PaddleTensor>* output_data)`
+  - take inputs and output `output_data`
+- `Clone` to clone a predictor from an existing one, with model parameter shared.
+
+There is a factory method to help create a predictor, and the user takes the ownership of this object.
+
+```c++
+template <typename ConfigT, PaddleEngineKind engine = PaddleEngineKind::kNative>
+std::unique_ptr<PaddlePredictor> CreatePaddlePredictor(const ConfigT& config);
+```
+
+By specifying the engine kind and config, one can get an specific implementation.
+
+## Reference
+
+- [paddle_inference_api.h](./paddle_inference_api.h)
+- [demos](./demo)
diff --git a/paddle/contrib/inference/paddle_inference_api.h b/paddle/contrib/inference/paddle_inference_api.h
index bd4530fcf9518cb3bf06179d8f60a1dde38ff7dd..38e3cc21413b9ab715b84f278f00b9df23cb7682 100644
--- a/paddle/contrib/inference/paddle_inference_api.h
+++ b/paddle/contrib/inference/paddle_inference_api.h
@@ -109,8 +109,7 @@ class PaddlePredictor {
 
   // The common configs for all the predictors.
   struct Config {
-    std::string model_dir;      // path to the model directory.
-    bool enable_engine{false};  // Enable to execute (part of) the model on
+    std::string model_dir;  // path to the model directory.
   };
 };