diff --git a/ai/litellm-config.yaml b/ai/litellm-config.yaml
index 134375e..4dab6ed 100644
--- a/ai/litellm-config.yaml
+++ b/ai/litellm-config.yaml
@@ -33,7 +33,7 @@ model_list:
   - model_name: qwen-2.5-7b
     litellm_params:
       model: openai/qwen-2.5-7b
-      api_base: http://100.100.108.13:9000/v1  # Orchestrator endpoint
+      api_base: http://100.121.199.88:9000/v1  # RunPod GPU via Tailscale
       api_key: dummy
       rpm: 1000
       tpm: 100000
@@ -42,7 +42,7 @@ model_list:
   - model_name: flux-schnell
     litellm_params:
       model: openai/dall-e-3  # OpenAI-compatible mapping
-      api_base: http://100.100.108.13:9000/v1  # Orchestrator endpoint
+      api_base: http://100.121.199.88:9000/v1  # RunPod GPU via Tailscale
       api_key: dummy
       rpm: 100
       max_parallel_requests: 3
@@ -51,7 +51,7 @@ model_list:
   - model_name: musicgen-medium
     litellm_params:
       model: openai/musicgen-medium
-      api_base: http://100.100.108.13:9000/v1  # Orchestrator endpoint
+      api_base: http://100.121.199.88:9000/v1  # RunPod GPU via Tailscale
       api_key: dummy
       rpm: 50
       max_parallel_requests: 1