diff --git a/examples/server/server-context.cpp b/examples/server/server-context.cpp
index a3e8367e..b4fcbee7 100644
--- a/examples/server/server-context.cpp
+++ b/examples/server/server-context.cpp
@@ -1125,7 +1125,7 @@ bool server_context::launch_slot_with_task(server_slot& slot, server_task& task)
     auto stream_opt = json_value(data, "stream_options", json::object());
     slot.params.include_usage = json_value(stream_opt, "include_usage", false);
     slot.params.cache_prompt = json_value(data, "cache_prompt", true);
-    slot.params.n_predict = json_value(data, "n_predict", json_value(data, "max_tokens", defaults.n_predict));
+    slot.params.n_predict = json_value(data, "n_predict", json_value(data, "max_tokens", json_value(data, "max_completion_tokens", defaults.n_predict)));
     slot.saturate_predict = json_value(data, "saturate_predict", false);
     slot.sparams.top_k = json_value(data, "top_k", default_sparams.top_k);
     slot.sparams.top_p = json_value(data, "top_p", default_sparams.top_p);