diff --git a/ai/litellm-config.yaml b/ai/litellm-config.yaml
index b43f433..b73c189 100644
--- a/ai/litellm-config.yaml
+++ b/ai/litellm-config.yaml
@@ -34,7 +34,6 @@ model_list:
     litellm_params:
       model: hosted_vllm/openai/qwen-2.5-7b  # hosted_vllm/openai/ prefix for proper streaming
       api_base: os.environ/GPU_VLLM_QWEN_URL  # Direct to vLLM Qwen server
-      api_key: dummy
       rpm: 1000
       tpm: 100000
       timeout: 600  # 10 minutes for generation
@@ -47,7 +46,6 @@ model_list:
     litellm_params:
       model: hosted_vllm/openai/llama-3.1-8b  # hosted_vllm/openai/ prefix for proper streaming
       api_base: os.environ/GPU_VLLM_LLAMA_URL  # Direct to vLLM Llama server
-      api_key: dummy
       rpm: 1000
       tpm: 100000
       timeout: 600  # 10 minutes for generation