From ec903c16c233055c4991841d85901c502d5ed60a Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Sebastian=20Kr=C3=BCger?= <valknar@pivoine.art>
Date: Fri, 21 Nov 2025 19:18:33 +0100
Subject: [PATCH] fix: use hosted_vllm/openai/ prefix for vLLM model via
 orchestrator

---
 ai/litellm-config.yaml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/ai/litellm-config.yaml b/ai/litellm-config.yaml
index 38eb995..2f7adb2 100644
--- a/ai/litellm-config.yaml
+++ b/ai/litellm-config.yaml
@@ -32,7 +32,7 @@ model_list:
   # Text Generation
   - model_name: qwen-2.5-7b
     litellm_params:
-      model: hosted_vllm/qwen-2.5-7b  # vLLM model ID from /v1/models endpoint
+      model: hosted_vllm/openai/qwen-2.5-7b  # hosted_vllm/openai/ for vLLM via orchestrator
       api_base: http://100.121.199.88:9000/v1  # RunPod GPU via Tailscale
       api_key: dummy
       rpm: 1000