diff --git a/stacks/litellm/conf/config.yaml b/stacks/litellm/conf/config.yaml
index 6ab7296..7a70218 100644
--- a/stacks/litellm/conf/config.yaml
+++ b/stacks/litellm/conf/config.yaml
@@ -41,6 +41,30 @@ model_list:
     model_info:
       mode: chat
 
+  # alias: classifier -> granite-4.1-8b (operator 2026-06-19). Light/fast classification
+  #   + triage endpoint; same backend as summarizer. Keep api_base in sync above.
+  - model_name: classifier
+    litellm_params:
+      model: hosted_vllm/granite-4.1-8b
+      api_base: http://10.250.50.54:8004/v1
+      api_key: os.environ/VLLM_API_KEY
+    model_info:
+      mode: chat
+
+  # alias: summarizer-large -> gen / qwen3.5-122-a10b (operator 2026-06-19). For heavier
+  #   summarization that wants the 122B Qwopus instead of granite-8b. Thinking OFF (matches
+  #   gen). Keep api_base (:8013) + enable_thinking in sync with the gen record below.
+  - model_name: summarizer-large
+    litellm_params:
+      model: hosted_vllm/qwen3.5-122-a10b
+      api_base: http://10.250.50.54:8013/v1
+      api_key: os.environ/VLLM_API_KEY
+      extra_body:
+        chat_template_kwargs:
+          enable_thinking: false
+    model_info:
+      mode: chat
+
   # --- Qwen-Image-Bench (NVFP4) — text-to-image quality JUDGE, vision-intact. vLLM
   #     on ana-ml2 GPU 1, :8014. REPLACED qwen3.6-35b-a3b (operator 2026-06-19; the
   #     qwen36 VL judge was downed + its FP8 weights freed ~33GB). Multimodal — image