diff --git a/src/guidellm/backend/openai.py b/src/guidellm/backend/openai.py
index 680578cc..759665bb 100644
--- a/src/guidellm/backend/openai.py
+++ b/src/guidellm/backend/openai.py
@@ -468,7 +468,6 @@ def _completions_payload(
                 max_output_tokens or self.max_output_tokens,
             )
             payload["max_tokens"] = max_output_tokens or self.max_output_tokens
-            payload["max_completion_tokens"] = payload["max_tokens"]
 
             if max_output_tokens:
                 # only set stop and ignore_eos if max_output_tokens set at request level