diff --git a/main.cpp b/main.cpp
index 32c3a68..77260bb 100644
--- a/main.cpp
+++ b/main.cpp
@@ -275,13 +275,16 @@ int main(int argc, char ** argv) {
     // determine newline token
     auto llama_token_newline = ::llama_tokenize(ctx, "\n", false);
 
-    fprintf(stderr, "\n");
-    fprintf(stderr, "%s: prompt: '%s'\n", __func__, params.prompt.c_str());
-    fprintf(stderr, "%s: number of tokens in prompt = %zu\n", __func__, embd_inp.size());
-    for (int i = 0; i < (int) embd_inp.size(); i++) {
-        fprintf(stderr, "%6d -> '%s'\n", embd_inp[i], llama_token_to_str(ctx, embd_inp[i]));
+    if (params.verbose_prompt) {
+        fprintf(stderr, "\n");
+        fprintf(stderr, "%s: prompt: '%s'\n", __func__, params.prompt.c_str());
+        fprintf(stderr, "%s: number of tokens in prompt = %zu\n", __func__, embd_inp.size());
+        for (int i = 0; i < (int) embd_inp.size(); i++) {
+            fprintf(stderr, "%6d -> '%s'\n", embd_inp[i], llama_token_to_str(ctx, embd_inp[i]));
+        }
+        fprintf(stderr, "\n");
     }
-    fprintf(stderr, "\n");
+
     if (params.interactive) {
 #if defined (__unix__) || (defined (__APPLE__) && defined (__MACH__))
         struct sigaction sigint_action;
diff --git a/utils.cpp b/utils.cpp
index 319924c..cea3096 100644
--- a/utils.cpp
+++ b/utils.cpp
@@ -134,6 +134,8 @@ bool gpt_params_parse(int argc, char ** argv, gpt_params & params) {
             params.use_mlock = true;
         } else if (arg == "--mtest") {
             params.mem_test = true;
+        } else if (arg == "--verbose_prompt") {
+            params.verbose_prompt = true;
         } else if (arg == "-r" || arg == "--reverse-prompt") {
             if (++i >= argc) {
                 invalid_param = true;
@@ -212,6 +214,7 @@ void gpt_print_usage(int /*argc*/, char ** argv, const gpt_params & params) {
         fprintf(stderr, "  --mlock               force system to keep model in RAM rather than swapping or compressing\n");
     }
     fprintf(stderr, "  --mtest               compute maximum memory usage\n");
+    fprintf(stderr, "  --verbose-prompt      print prompt before generation\n");
     fprintf(stderr, "  -m FNAME, --model FNAME\n");
     fprintf(stderr, "                        model path (default: %s)\n", params.model.c_str());
     fprintf(stderr, "\n");
diff --git a/utils.h b/utils.h
index 0690ef7..dede803 100644
--- a/utils.h
+++ b/utils.h
@@ -48,6 +48,7 @@ struct gpt_params {
     bool perplexity        = false; // compute perplexity over the prompt
     bool use_mlock         = false; // use mlock to keep model in memory
     bool mem_test          = false; // compute maximum memory usage
+    bool verbose_prompt    = false; // print prompt tokens before generation
 };
 
 bool gpt_params_parse(int argc, char ** argv, gpt_params & params);