diff --git a/.env.example b/.env.example
index 6d569e2..cf6050f 100644
--- a/.env.example
+++ b/.env.example
@@ -8,4 +8,10 @@ LISTEN_PORT=5000
 LANGUAGE_DETECTION_MODEL=langdetect
 
 # (Optional. Default: false. Options: true or false) Parameters will be used when LANGUAGE_DETECTION_MODEL=fast_langdetect . Check https://github.com/LlmKira/fast-langdetect for more information
-LOW_MEMORY_MODE=false
\ No newline at end of file
+LOW_MEMORY_MODE=false
+
+# (Optional. Default: false. Options: true or false) Check whether the cache will be enabled or not
+ENABLE_CACHE=false
+
+# (Optional. Default: 60. Options: integer value) Duration of cache in seconds. Parameter will be used when the cache is enabled
+CACHE_DURATION_SECONDS=60
diff --git a/app.py b/app.py
index a1de73e..aeb9959 100644
--- a/app.py
+++ b/app.py
@@ -8,6 +8,7 @@
 
 from fast_langdetect import detect_multilingual
 from langdetect import detect_langs
+from flask_caching import Cache
 
 load_dotenv()
 
@@ -18,6 +19,14 @@
 LISTEN_PORT = os.getenv("LISTEN_PORT", "5000")
 LANGUAGE_DETECTION_MODEL = os.getenv("LANGUAGE_DETECTION_MODEL", "langdetect")
 LOW_MEMORY_MODE = os.getenv("LOW_MEMORY_MODE", "false") == "true"
+CACHE_DURATION_SECONDS = (
+    None
+    if int(os.getenv("CACHE_DURATION_SECONDS", 60)) == 0
+    else int(os.getenv("CACHE_DURATION_SECONDS", 60))
+)
+
+CACHE_DURATION_SECONDS = int(os.getenv("CACHE_DURATION_SECONDS", 60))
+ENABLE_CACHE = os.getenv("ENABLE_CACHE", "false") == "true"
 
 APP_VERSION = "0.0.1"
 
@@ -42,6 +51,14 @@
 
 app = Flask(__name__)
 
+cache_config = {
+    "DEBUG": True if APP_ENV != "production" else False,
+    "CACHE_TYPE": "SimpleCache" if ENABLE_CACHE else "NullCache",
+    "CACHE_DEFAULT_TIMEOUT": CACHE_DURATION_SECONDS,  # Cache duration in seconds
+}
+cache = Cache(config=cache_config)
+cache.init_app(app)
+
 
 def is_valid_api_key(api_key):
     if api_key == API_TOKEN:
@@ -69,6 +86,16 @@ def decorator(*args, **kwargs):
     return decorator
 
 
+def make_key_fn():
+    """A function which is called to derive the key for a computed value.
+       The key in this case is the concat value of all the json request
+       parameters. Other strategy could to use any hashing function.
+    :returns: unique string for which the value should be cached.
+    """
+    user_data = request.get_json()
+    return ",".join([f"{key}={value}" for key, value in user_data.items()])
+
+
 def perform_detect_language(query):
     result = []
     temp_result = []
@@ -115,6 +142,7 @@ def handle_exception(error):
 
 @app.route("/detect", methods=["POST"])
 @api_required
+@cache.cached(make_cache_key=make_key_fn)
 def predict():
     data = request.json
     q = data["q"]
diff --git a/requirements.txt b/requirements.txt
index d5e0bdd..a8bf4c7 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -1,4 +1,5 @@
 Flask==3.0.3
+Flask-Caching==2.3.0
 python-dotenv==1.0.0
 pandas==2.2.2
 fast-langdetect==0.1.1