diff --git a/stacks/litellm/conf/config.yaml b/stacks/litellm/conf/config.yaml
index 97d0e0d..ceb187b 100644
--- a/stacks/litellm/conf/config.yaml
+++ b/stacks/litellm/conf/config.yaml
@@ -30,6 +30,17 @@ model_list:
     model_info:
       mode: chat
 
+  # alias: summarizer -> granite-4.1-8b (operator 2026-06-19). Duplicate-entry alias
+  #   (not router_settings.model_group_alias — that's hidden from /v1/models and can be
+  #   silently ignored in config per litellm #15020/#5524). Keep api_base in sync above.
+  - model_name: summarizer
+    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
+
   # --- Qwen3.6-35B-A3B vision-language MoE (official FP8) — vision + chat. vLLM
   #     on ana-ml2 GPU 1, :8007. Explicit entry shadows the "*" wildcard llama-swap
   #     route. REPLACED qwen3.5-9b-fp8 2026-06-14 (the 9B is retired; this is a
@@ -95,6 +106,26 @@ model_list:
     model_info:
       mode: chat
 
+  # aliases: gen -> mistral-small-4, gen-reasoning -> mistral-small-4-reasoning
+  #   (operator 2026-06-19). Duplicate-entry aliases — keep api_base in sync with the
+  #   two mistral-small-4 entries above.
+  - model_name: gen
+    litellm_params:
+      model: hosted_vllm/mistral-small-4
+      api_base: http://10.250.50.54:8010/v1
+      api_key: os.environ/VLLM_API_KEY
+    model_info:
+      mode: chat
+  - model_name: gen-reasoning
+    litellm_params:
+      model: hosted_vllm/mistral-small-4
+      api_base: http://10.250.50.54:8010/v1
+      api_key: os.environ/VLLM_API_KEY
+      extra_body:
+        reasoning_effort: high
+    model_info:
+      mode: chat
+
   # --- Selene 1 Mini 8B (AtlaAI judge, FP8) — restored on GPU1 after the
   #     llama-swap teardown (was the Q6_K GGUF in the swap zoo). vLLM dynamic fp8,
   #     :8011. Explicit entry shadows the "*" wildcard (which used to reach it via