diff --git a/llama_cpp/llama_types.py b/llama_cpp/llama_types.py
index 6ba8023..4225bf4 100644
--- a/llama_cpp/llama_types.py
+++ b/llama_cpp/llama_types.py
@@ -57,6 +57,10 @@ class Completion(TypedDict):
     usage: CompletionUsage
 
 
+class Tokens(TypedDict):
+    prompt_tokens: Union[List[int], List[List[int]]]
+
+
 class ChatCompletionMessage(TypedDict):
     role: Literal["assistant", "user", "system"]
     content: str
diff --git a/llama_cpp/server/app.py b/llama_cpp/server/app.py
index 4afcfd5..09b3042 100644
--- a/llama_cpp/server/app.py
+++ b/llama_cpp/server/app.py
@@ -1,4 +1,5 @@
 import json
+import logging
 import multiprocessing
 from re import compile, Match, Pattern
 from threading import Lock
@@ -534,6 +535,12 @@ class CreateCompletionRequest(BaseModel):
     }
 
 
+class TokenizeRequest(BaseModel):
+    prompt: Union[str, List[str]] = Field(
+        default="", description="The prompt to generate completions for."
+    )
+
+
 def make_logit_bias_processor(
     llama: llama_cpp.Llama,
     logit_bias: Dict[str, float],
@@ -567,6 +574,31 @@ def make_logit_bias_processor(
     return logit_bias_processor
 
 
+@router.post(
+    "/v1/tokenize",
+)
+async def tokenize(
+        body: TokenizeRequest,
+        llama: llama_cpp.Llama = Depends(get_llama),
+) -> llama_cpp.Tokens:
+    if type(body.prompt) == list:
+        try:
+            tokens_list = [llama.tokenize(text=text.encode("utf-8"), add_bos=True) for text in body.prompt]
+        except Exception as e:
+            logging.getLogger("uvicorn").info(f"Error while tokenizing \"{body.prompt}\": {e}")
+        return {
+            "prompt_tokens": tokens_list
+        }
+    elif type(body.prompt) == str:
+        try:
+            tokens = llama.tokenize(text=body.prompt.encode("utf-8"), add_bos=True)
+        except Exception as e:
+            logging.getLogger('uvicorn').info(f"Error while tokenizing \"{body.prompt}\": {e}")
+        return {
+            "prompt_tokens": tokens
+        }
+
+
 @router.post(
     "/v1/completions",
 )