diff --git a/docs/source/commands/trtllm-serve/trtllm-serve.rst b/docs/source/commands/trtllm-serve/trtllm-serve.rst
index 4f0312fe139c..45574943a77a 100644
--- a/docs/source/commands/trtllm-serve/trtllm-serve.rst
+++ b/docs/source/commands/trtllm-serve/trtllm-serve.rst
@@ -115,9 +115,9 @@ Then, start the server with the configuration file:
 Multimodal Chat API
 ~~~~~~~~~~~~~~~~~~~
 
-You can query Completions API with any http clients, a typical example is OpenAI Python client:
+You can query Chat API with any http clients, a typical example is OpenAI Python client:
 
-.. literalinclude:: ../../../../examples/serve/openai_completion_client_for_multimodal.py
+.. literalinclude:: ../../../../examples/serve/openai_chat_client_for_multimodal.py
     :language: python
     :linenos:
 
@@ -352,4 +352,4 @@ This syntax section lists all command line arguments for ``trtllm-serve``'s subc
    :nested: full
 
 Besides the above examples, `trtllm-serve` is also used as an entrypoint for performance benchmarking.
-Please refer to `Performance Benchmarking with `trtllm-serve` <https://github.com/NVIDIA/TensorRT-LLM/blob/main/docs/source/commands/trtllm-serve/trtllm-serve-bench.md>` for more details.
+Please refer to `Performance Benchmarking with `trtllm-serve` <https://github.com/NVIDIA/TensorRT-LLM/blob/main/docs/source/commands/trtllm-serve/trtllm-serve-bench.md>` for more details.
\ No newline at end of file