diff --git a/ai/litellm-config.yaml b/ai/litellm-config.yaml
index ea43d54..76cfd1d 100644
--- a/ai/litellm-config.yaml
+++ b/ai/litellm-config.yaml
@@ -32,7 +32,7 @@ model_list:
   # Text Generation - Llama 3.1 8B (Port 8001)
   - model_name: llama-3.1-8b
     litellm_params:
-      model: hosted_vllm/openai/llama-3.1-8b # hosted_vllm/openai/ prefix for proper streaming
+      model: hosted_vllm/meta-llama/Llama-3.1-8B-Instruct # hosted_vllm/openai/ prefix for proper streaming
       api_base: os.environ/GPU_VLLM_LLAMA_URL # Direct to vLLM Llama server
       api_key: "EMPTY" # vLLM doesn't validate API keys
       rpm: 1000
@@ -45,7 +45,7 @@ model_list:
   # Embeddings - BGE Large (Port 8002)
   - model_name: bge-large-en-v1.5
     litellm_params:
-      model: hosted_vllm/openai/bge-large-en-v1.5
+      model: hosted_vllm/BAAI/bge-large-en-v1.5
       api_base: os.environ/GPU_VLLM_EMBED_URL # Direct to vLLM embedding server
       api_key: "EMPTY"
       rpm: 1000