diff --git a/src/llmperf/ray_clients/openai_chat_completions_client.py b/src/llmperf/ray_clients/openai_chat_completions_client.py
index f2e0a91..afd934b 100644
--- a/src/llmperf/ray_clients/openai_chat_completions_client.py
+++ b/src/llmperf/ray_clients/openai_chat_completions_client.py
@@ -109,7 +109,7 @@ def llm_request(self, request_config: RequestConfig) -> Dict[str, Any]:
             print(f"Warning Or Error: {e}")
             print(error_response_code)
 
-        metrics[common_metrics.INTER_TOKEN_LAT] = sum(time_to_next_token) #This should be same as metrics[common_metrics.E2E_LAT]. Leave it here for now
+        metrics[common_metrics.INTER_TOKEN_LAT] = sum(time_to_next_token) - ttft
         metrics[common_metrics.TTFT] = ttft
         metrics[common_metrics.E2E_LAT] = total_request_time
         metrics[common_metrics.REQ_OUTPUT_THROUGHPUT] = output_throughput
diff --git a/token_benchmark_ray.py b/token_benchmark_ray.py
index 63216b1..e3528d3 100644
--- a/token_benchmark_ray.py
+++ b/token_benchmark_ray.py
@@ -117,8 +117,8 @@ def launch_request(thread_index):
                 num_output_tokens = get_token_length(gen_text)
                 with completed_requests_lock:
                     if num_completed_requests < max_num_completed_requests:
-                        if num_output_tokens:
-                            request_metrics[common_metrics.INTER_TOKEN_LAT] /= request_metrics[common_metrics.NUM_OUTPUT_TOKENS]
+                        if num_output_tokens > 1:
+                            request_metrics[common_metrics.INTER_TOKEN_LAT] /= (num_output_tokens - 1)
                         else:
                             request_metrics[common_metrics.INTER_TOKEN_LAT] = 0
                         request_metrics[common_metrics.NUM_OUTPUT_TOKENS] = num_output_tokens
@@ -154,8 +154,8 @@ def launch_request(thread_index):
         num_output_tokens = get_token_length(gen_text)
         with completed_requests_lock:
             if num_completed_requests < max_num_completed_requests:
-                if num_output_tokens:
-                    request_metrics[common_metrics.INTER_TOKEN_LAT] /= num_output_tokens
+                if num_output_tokens > 1:
+                    request_metrics[common_metrics.INTER_TOKEN_LAT] /= (num_output_tokens - 1)
                 else:
                     request_metrics[common_metrics.INTER_TOKEN_LAT] = 0
                 request_metrics[common_metrics.NUM_OUTPUT_TOKENS] = num_output_tokens